From db751e309ff05461a0c8e114b1238d7a69cc1f18 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:43 +0000 Subject: ELF: UAPI and Kconfig additions for ELF program properties Pull the basic ELF definitions relating to the NT_GNU_PROPERTY_TYPE_0 note from Yu-Cheng Yu's earlier x86 shstk series. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Signed-off-by: Yu-cheng Yu Reviewed-by: Catalin Marinas Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- include/uapi/linux/elf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 34c02e4290fe..c37731407074 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -36,6 +36,7 @@ typedef __s64 Elf64_Sxword; #define PT_LOPROC 0x70000000 #define PT_HIPROC 0x7fffffff #define PT_GNU_EH_FRAME 0x6474e550 +#define PT_GNU_PROPERTY 0x6474e553 #define PT_GNU_STACK (PT_LOOS + 0x474e551) -- cgit v1.2.3 From 00e19ceec80b03a43f626f891fcc53e57919f1b3 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:44 +0000 Subject: ELF: Add ELF program property parsing support ELF program properties will be needed for detecting whether to enable optional architecture or ABI features for a new ELF process. For now, there are no generic properties that we care about, so do nothing unless CONFIG_ARCH_USE_GNU_PROPERTY=y. Otherwise, the presence of properties using the PT_PROGRAM_PROPERTY phdrs entry (if any), and notify each property to the arch code. For now, the added code is not used. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- fs/binfmt_elf.c | 127 +++++++++++++++++++++++++++++++++++++++++++++++ fs/compat_binfmt_elf.c | 4 ++ include/linux/elf.h | 19 +++++++ include/uapi/linux/elf.h | 4 ++ 4 files changed, 154 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index f4713ea76e82..1fb67e506b68 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -39,12 +39,18 @@ #include #include #include +#include +#include #include #include #include #include #include +#ifndef ELF_COMPAT +#define ELF_COMPAT 0 +#endif + #ifndef user_long_t #define user_long_t long #endif @@ -681,6 +687,111 @@ out: * libraries. There is no binary dependent code anywhere else. */ +static int parse_elf_property(const char *data, size_t *off, size_t datasz, + struct arch_elf_state *arch, + bool have_prev_type, u32 *prev_type) +{ + size_t o, step; + const struct gnu_property *pr; + int ret; + + if (*off == datasz) + return -ENOENT; + + if (WARN_ON_ONCE(*off > datasz || *off % ELF_GNU_PROPERTY_ALIGN)) + return -EIO; + o = *off; + datasz -= *off; + + if (datasz < sizeof(*pr)) + return -ENOEXEC; + pr = (const struct gnu_property *)(data + o); + o += sizeof(*pr); + datasz -= sizeof(*pr); + + if (pr->pr_datasz > datasz) + return -ENOEXEC; + + WARN_ON_ONCE(o % ELF_GNU_PROPERTY_ALIGN); + step = round_up(pr->pr_datasz, ELF_GNU_PROPERTY_ALIGN); + if (step > datasz) + return -ENOEXEC; + + /* Properties are supposed to be unique and sorted on pr_type: */ + if (have_prev_type && pr->pr_type <= *prev_type) + return -ENOEXEC; + *prev_type = pr->pr_type; + + ret = arch_parse_elf_property(pr->pr_type, data + o, + pr->pr_datasz, ELF_COMPAT, arch); + if (ret) + return ret; + + *off = o + step; + return 0; +} + +#define NOTE_DATA_SZ SZ_1K +#define GNU_PROPERTY_TYPE_0_NAME "GNU" +#define NOTE_NAME_SZ (sizeof(GNU_PROPERTY_TYPE_0_NAME)) + +static int parse_elf_properties(struct file *f, const struct elf_phdr *phdr, + struct arch_elf_state *arch) +{ + union { + struct elf_note nhdr; + char data[NOTE_DATA_SZ]; + } note; + loff_t pos; + ssize_t n; + size_t off, datasz; + int ret; + bool have_prev_type; + u32 prev_type; + + if (!IS_ENABLED(CONFIG_ARCH_USE_GNU_PROPERTY) || !phdr) + return 0; + + /* load_elf_binary() shouldn't call us unless this is true... */ + if (WARN_ON_ONCE(phdr->p_type != PT_GNU_PROPERTY)) + return -ENOEXEC; + + /* If the properties are crazy large, that's too bad (for now): */ + if (phdr->p_filesz > sizeof(note)) + return -ENOEXEC; + + pos = phdr->p_offset; + n = kernel_read(f, ¬e, phdr->p_filesz, &pos); + + BUILD_BUG_ON(sizeof(note) < sizeof(note.nhdr) + NOTE_NAME_SZ); + if (n < 0 || n < sizeof(note.nhdr) + NOTE_NAME_SZ) + return -EIO; + + if (note.nhdr.n_type != NT_GNU_PROPERTY_TYPE_0 || + note.nhdr.n_namesz != NOTE_NAME_SZ || + strncmp(note.data + sizeof(note.nhdr), + GNU_PROPERTY_TYPE_0_NAME, n - sizeof(note.nhdr))) + return -ENOEXEC; + + off = round_up(sizeof(note.nhdr) + NOTE_NAME_SZ, + ELF_GNU_PROPERTY_ALIGN); + if (off > n) + return -ENOEXEC; + + if (note.nhdr.n_descsz > n - off) + return -ENOEXEC; + datasz = off + note.nhdr.n_descsz; + + have_prev_type = false; + do { + ret = parse_elf_property(note.data, &off, datasz, arch, + have_prev_type, &prev_type); + have_prev_type = true; + } while (!ret); + + return ret == -ENOENT ? 0 : ret; +} + static int load_elf_binary(struct linux_binprm *bprm) { struct file *interpreter = NULL; /* to shut gcc up */ @@ -688,6 +799,7 @@ static int load_elf_binary(struct linux_binprm *bprm) int load_addr_set = 0; unsigned long error; struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL; + struct elf_phdr *elf_property_phdata = NULL; unsigned long elf_bss, elf_brk; int bss_prot = 0; int retval, i; @@ -733,6 +845,11 @@ static int load_elf_binary(struct linux_binprm *bprm) for (i = 0; i < elf_ex->e_phnum; i++, elf_ppnt++) { char *elf_interpreter; + if (elf_ppnt->p_type == PT_GNU_PROPERTY) { + elf_property_phdata = elf_ppnt; + continue; + } + if (elf_ppnt->p_type != PT_INTERP) continue; @@ -820,9 +937,14 @@ out_free_interp: goto out_free_dentry; /* Pass PT_LOPROC..PT_HIPROC headers to arch code */ + elf_property_phdata = NULL; elf_ppnt = interp_elf_phdata; for (i = 0; i < loc->interp_elf_ex.e_phnum; i++, elf_ppnt++) switch (elf_ppnt->p_type) { + case PT_GNU_PROPERTY: + elf_property_phdata = elf_ppnt; + break; + case PT_LOPROC ... PT_HIPROC: retval = arch_elf_pt_proc(&loc->interp_elf_ex, elf_ppnt, interpreter, @@ -833,6 +955,11 @@ out_free_interp: } } + retval = parse_elf_properties(interpreter ?: bprm->file, + elf_property_phdata, &arch_state); + if (retval) + goto out_free_dentry; + /* * Allow arch code to reject the ELF at this point, whilst it's * still possible to return an error to the code that invoked diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c index aaad4ca1217e..13a087bc816b 100644 --- a/fs/compat_binfmt_elf.c +++ b/fs/compat_binfmt_elf.c @@ -17,6 +17,8 @@ #include #include +#define ELF_COMPAT 1 + /* * Rename the basic ELF layout types to refer to the 32-bit class of files. */ @@ -28,11 +30,13 @@ #undef elf_shdr #undef elf_note #undef elf_addr_t +#undef ELF_GNU_PROPERTY_ALIGN #define elfhdr elf32_hdr #define elf_phdr elf32_phdr #define elf_shdr elf32_shdr #define elf_note elf32_note #define elf_addr_t Elf32_Addr +#define ELF_GNU_PROPERTY_ALIGN ELF32_GNU_PROPERTY_ALIGN /* * Some data types as stored in coredump. diff --git a/include/linux/elf.h b/include/linux/elf.h index f7b24c5fcfb6..db5113479f5e 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -22,6 +22,9 @@ SET_PERSONALITY(ex) #endif +#define ELF32_GNU_PROPERTY_ALIGN 4 +#define ELF64_GNU_PROPERTY_ALIGN 8 + #if ELF_CLASS == ELFCLASS32 extern Elf32_Dyn _DYNAMIC []; @@ -32,6 +35,7 @@ extern Elf32_Dyn _DYNAMIC []; #define elf_addr_t Elf32_Off #define Elf_Half Elf32_Half #define Elf_Word Elf32_Word +#define ELF_GNU_PROPERTY_ALIGN ELF32_GNU_PROPERTY_ALIGN #else @@ -43,6 +47,7 @@ extern Elf64_Dyn _DYNAMIC []; #define elf_addr_t Elf64_Off #define Elf_Half Elf64_Half #define Elf_Word Elf64_Word +#define ELF_GNU_PROPERTY_ALIGN ELF64_GNU_PROPERTY_ALIGN #endif @@ -68,4 +73,18 @@ struct gnu_property { u32 pr_datasz; }; +struct arch_elf_state; + +#ifndef CONFIG_ARCH_USE_GNU_PROPERTY +static inline int arch_parse_elf_property(u32 type, const void *data, + size_t datasz, bool compat, + struct arch_elf_state *arch) +{ + return 0; +} +#else +extern int arch_parse_elf_property(u32 type, const void *data, size_t datasz, + bool compat, struct arch_elf_state *arch); +#endif + #endif /* _LINUX_ELF_H */ diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index c37731407074..20900f4496b7 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -368,6 +368,7 @@ typedef struct elf64_shdr { * Notes used in ET_CORE. Architectures export some of the arch register sets * using the corresponding note types via the PTRACE_GETREGSET and * PTRACE_SETREGSET requests. + * The note name for all these is "LINUX". */ #define NT_PRSTATUS 1 #define NT_PRFPREG 2 @@ -430,6 +431,9 @@ typedef struct elf64_shdr { #define NT_MIPS_FP_MODE 0x801 /* MIPS floating-point mode */ #define NT_MIPS_MSA 0x802 /* MIPS SIMD registers */ +/* Note types with note name "GNU" */ +#define NT_GNU_PROPERTY_TYPE_0 5 + /* Note header in a PT_NOTE section */ typedef struct elf32_note { Elf32_Word n_namesz; /* Name size */ -- cgit v1.2.3 From ab7876a98a2160092133de4c648e94b18bc3f139 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:47 +0000 Subject: arm64: elf: Enable BTI at exec based on ELF program properties For BTI protection to be as comprehensive as possible, it is desirable to have BTI enabled from process startup. If this is not done, the process must use mprotect() to enable BTI for each of its executable mappings, but this is painful to do in the libc startup code. It's simpler and more sound to have the kernel do it instead. To this end, detect BTI support in the executable (or ELF interpreter, as appropriate), via the NT_GNU_PROGRAM_PROPERTY_TYPE_0 note, and tweak the initial prot flags for the process' executable pages to include PROT_BTI as appropriate. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- arch/arm64/Kconfig | 3 +++ arch/arm64/include/asm/elf.h | 50 ++++++++++++++++++++++++++++++++++++++++++++ arch/arm64/kernel/process.c | 19 +++++++++++++++++ include/uapi/linux/elf.h | 6 ++++++ 4 files changed, 78 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 0b30e884e088..8a15bc68dadd 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -9,6 +9,7 @@ config ARM64 select ACPI_MCFG if (ACPI && PCI) select ACPI_SPCR_TABLE if ACPI select ACPI_PPTT if ACPI + select ARCH_BINFMT_ELF_STATE select ARCH_CLOCKSOURCE_DATA select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEVMEM_IS_ALLOWED @@ -33,6 +34,7 @@ config ARM64 select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_TEARDOWN_DMA_OPS if IOMMU_SUPPORT select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST + select ARCH_HAVE_ELF_PROT select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_INLINE_READ_LOCK if !PREEMPTION select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION @@ -62,6 +64,7 @@ config ARM64 select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION select ARCH_KEEP_MEMBLOCK select ARCH_USE_CMPXCHG_LOCKREF + select ARCH_USE_GNU_PROPERTY if BINFMT_ELF select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS select ARCH_SUPPORTS_MEMORY_FAILURE diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index b618017205a3..4f00d50585a4 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -114,7 +114,11 @@ #ifndef __ASSEMBLY__ +#include #include +#include +#include +#include #include /* for signal_minsigstksz, used by ARCH_DLINFO */ typedef unsigned long elf_greg_t; @@ -224,6 +228,52 @@ extern int aarch32_setup_additional_pages(struct linux_binprm *bprm, #endif /* CONFIG_COMPAT */ +struct arch_elf_state { + int flags; +}; + +#define ARM64_ELF_BTI (1 << 0) + +#define INIT_ARCH_ELF_STATE { \ + .flags = 0, \ +} + +static inline int arch_parse_elf_property(u32 type, const void *data, + size_t datasz, bool compat, + struct arch_elf_state *arch) +{ + /* No known properties for AArch32 yet */ + if (IS_ENABLED(CONFIG_COMPAT) && compat) + return 0; + + if (type == GNU_PROPERTY_AARCH64_FEATURE_1_AND) { + const u32 *p = data; + + if (datasz != sizeof(*p)) + return -ENOEXEC; + + if (system_supports_bti() && + (*p & GNU_PROPERTY_AARCH64_FEATURE_1_BTI)) + arch->flags |= ARM64_ELF_BTI; + } + + return 0; +} + +static inline int arch_elf_pt_proc(void *ehdr, void *phdr, + struct file *f, bool is_interp, + struct arch_elf_state *state) +{ + return 0; +} + +static inline int arch_check_elf(void *ehdr, bool has_interp, + void *interp_ehdr, + struct arch_elf_state *state) +{ + return 0; +} + #endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 00626057a384..b8e3faa8d406 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -11,6 +11,7 @@ #include #include +#include #include #include #include @@ -18,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -654,3 +656,20 @@ asmlinkage void __sched arm64_preempt_schedule_irq(void) if (system_capabilities_finalized()) preempt_schedule_irq(); } + +#ifdef CONFIG_BINFMT_ELF +int arch_elf_adjust_prot(int prot, const struct arch_elf_state *state, + bool has_interp, bool is_interp) +{ + if (is_interp != has_interp) + return prot; + + if (!(state->flags & ARM64_ELF_BTI)) + return prot; + + if (prot & PROT_EXEC) + prot |= PROT_BTI; + + return prot; +} +#endif diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 20900f4496b7..c6dd0215482e 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -448,4 +448,10 @@ typedef struct elf64_note { Elf64_Word n_type; /* Content type */ } Elf64_Nhdr; +/* .note.gnu.property types for EM_AARCH64: */ +#define GNU_PROPERTY_AARCH64_FEATURE_1_AND 0xc0000000 + +/* Bits for GNU_PROPERTY_AARCH64_FEATURE_1_BTI */ +#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI (1U << 0) + #endif /* _UAPI_LINUX_ELF_H */ -- cgit v1.2.3 From 980737282232b752bb14dab96d77665c15889c36 Mon Sep 17 00:00:00 2001 From: Alexey Budankov Date: Thu, 2 Apr 2020 11:45:31 +0300 Subject: capabilities: Introduce CAP_PERFMON to kernel and user space Introduce the CAP_PERFMON capability designed to secure system performance monitoring and observability operations so that CAP_PERFMON can assist CAP_SYS_ADMIN capability in its governing role for performance monitoring and observability subsystems. CAP_PERFMON hardens system security and integrity during performance monitoring and observability operations by decreasing attack surface that is available to a CAP_SYS_ADMIN privileged process [2]. Providing the access to system performance monitoring and observability operations under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes the operation more secure. Thus, CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e: 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required) CAP_PERFMON meets the demand to secure system performance monitoring and observability operations for adoption in security sensitive, restricted, multiuser production environments (e.g. HPC clusters, cloud and virtual compute environments), where root or CAP_SYS_ADMIN credentials are not available to mass users of a system, and securely unblocks applicability and scalability of system performance monitoring and observability operations beyond root and CAP_SYS_ADMIN use cases. CAP_PERFMON takes over CAP_SYS_ADMIN credentials related to system performance monitoring and observability operations and balances amount of CAP_SYS_ADMIN credentials following the recommendations in the capabilities man page [1] for CAP_SYS_ADMIN: "Note: this capability is overloaded; see Notes to kernel developers, below." For backward compatibility reasons access to system performance monitoring and observability subsystems of the kernel remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN capability usage for secure system performance monitoring and observability operations is discouraged with respect to the designed CAP_PERFMON capability. Although the software running under CAP_PERFMON can not ensure avoidance of related hardware issues, the software can still mitigate these issues following the official hardware issues mitigation procedure [2]. The bugs in the software itself can be fixed following the standard kernel development process [3] to maintain and harden security of system performance monitoring and observability operations. [1] http://man7.org/linux/man-pages/man7/capabilities.7.html [2] https://www.kernel.org/doc/html/latest/process/embargoed-hardware-issues.html [3] https://www.kernel.org/doc/html/latest/admin-guide/security-bugs.html Signed-off-by: Alexey Budankov Acked-by: James Morris Acked-by: Serge E. Hallyn Acked-by: Song Liu Acked-by: Stephen Smalley Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Andi Kleen Cc: Igor Lubashev Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: intel-gfx@lists.freedesktop.org Cc: linux-doc@vger.kernel.org Cc: linux-man@vger.kernel.org Cc: linux-security-module@vger.kernel.org Cc: selinux@vger.kernel.org Link: http://lore.kernel.org/lkml/5590d543-82c6-490a-6544-08e6a5517db0@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/capability.h | 4 ++++ include/uapi/linux/capability.h | 8 +++++++- security/selinux/include/classmap.h | 4 ++-- 3 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index ecce0f43c73a..027d7e4a853b 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -251,6 +251,10 @@ extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap); extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); +static inline bool perfmon_capable(void) +{ + return capable(CAP_PERFMON) || capable(CAP_SYS_ADMIN); +} /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index 272dc69fa080..e58c9636741b 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -367,8 +367,14 @@ struct vfs_ns_cap_data { #define CAP_AUDIT_READ 37 +/* + * Allow system performance and observability privileged operations + * using perf_events, i915_perf and other kernel subsystems + */ + +#define CAP_PERFMON 38 -#define CAP_LAST_CAP CAP_AUDIT_READ +#define CAP_LAST_CAP CAP_PERFMON #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP) diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index 986f3ac14282..d233ab3f1533 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -27,9 +27,9 @@ "audit_control", "setfcap" #define COMMON_CAP2_PERMS "mac_override", "mac_admin", "syslog", \ - "wake_alarm", "block_suspend", "audit_read" + "wake_alarm", "block_suspend", "audit_read", "perfmon" -#if CAP_LAST_CAP > CAP_AUDIT_READ +#if CAP_LAST_CAP > CAP_PERFMON #error New capability defined, please update COMMON_CAP2_PERMS. #endif -- cgit v1.2.3 From 29e4276667e24ee6b91d9f91064d8fda9a210ea1 Mon Sep 17 00:00:00 2001 From: Antony Antony Date: Wed, 15 Apr 2020 21:47:10 +0200 Subject: xfrm: fix error in comment s/xfrm_state_offload/xfrm_user_offload/ Fixes: d77e38e612a ("xfrm: Add an IPsec hardware offloading API") Signed-off-by: Antony Antony Signed-off-by: Steffen Klassert --- include/uapi/linux/xfrm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 5f3b9fec7b5f..ff7cfdc6cb44 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -304,7 +304,7 @@ enum xfrm_attr_type_t { XFRMA_PROTO, /* __u8 */ XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */ XFRMA_PAD, - XFRMA_OFFLOAD_DEV, /* struct xfrm_state_offload */ + XFRMA_OFFLOAD_DEV, /* struct xfrm_user_offload */ XFRMA_SET_MARK, /* __u32 */ XFRMA_SET_MARK_MASK, /* __u32 */ XFRMA_IF_ID, /* __u32 */ -- cgit v1.2.3 From 104edb94cc4b3101bab33161cd861de13e85610b Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Fri, 27 Mar 2020 10:59:48 +0530 Subject: tee: add private login method for kernel clients There are use-cases where user-space shouldn't be allowed to communicate directly with a TEE device which is dedicated to provide a specific service for a kernel client. So add a private login method for kernel clients and disallow user-space to open-session using GP implementation defined login method range: (0x80000000 - 0xBFFFFFFF). Reviewed-by: Jerome Forissier Signed-off-by: Sumit Garg Signed-off-by: Jens Wiklander --- drivers/tee/tee_core.c | 7 +++++++ include/uapi/linux/tee.h | 9 +++++++++ 2 files changed, 16 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c index 6aec502c495c..fb907bf43708 100644 --- a/drivers/tee/tee_core.c +++ b/drivers/tee/tee_core.c @@ -333,6 +333,13 @@ static int tee_ioctl_open_session(struct tee_context *ctx, goto out; } + if (arg.clnt_login >= TEE_IOCTL_LOGIN_REE_KERNEL_MIN && + arg.clnt_login <= TEE_IOCTL_LOGIN_REE_KERNEL_MAX) { + pr_debug("login method not allowed for user-space client\n"); + rc = -EPERM; + goto out; + } + rc = ctx->teedev->desc->ops->open_session(ctx, &arg, params); if (rc) goto out; diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h index 6596f3a09e54..b619f37ee03e 100644 --- a/include/uapi/linux/tee.h +++ b/include/uapi/linux/tee.h @@ -173,6 +173,15 @@ struct tee_ioctl_buf_data { #define TEE_IOCTL_LOGIN_APPLICATION 4 #define TEE_IOCTL_LOGIN_USER_APPLICATION 5 #define TEE_IOCTL_LOGIN_GROUP_APPLICATION 6 +/* + * Disallow user-space to use GP implementation specific login + * method range (0x80000000 - 0xBFFFFFFF). This range is rather + * being reserved for REE kernel clients or TEE implementation. + */ +#define TEE_IOCTL_LOGIN_REE_KERNEL_MIN 0x80000000 +#define TEE_IOCTL_LOGIN_REE_KERNEL_MAX 0xBFFFFFFF +/* Private login method for REE kernel clients */ +#define TEE_IOCTL_LOGIN_REE_KERNEL 0x80000000 /** * struct tee_ioctl_param - parameter -- cgit v1.2.3 From eec517cdb4810b3843eb7707971de3164088bff1 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 20 Apr 2020 00:11:50 +0200 Subject: net: Add IF_OPER_TESTING RFC 2863 defines the operational state testing. Add support for this state, both as a IF_LINK_MODE_ and __LINK_STATE_. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/netdevice.h | 41 +++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/if.h | 1 + net/core/dev.c | 5 +++++ net/core/link_watch.c | 12 ++++++++++-- net/core/rtnetlink.c | 9 ++++++++- 5 files changed, 65 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 130a668049ab..0750b54b3765 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -288,6 +288,7 @@ enum netdev_state_t { __LINK_STATE_NOCARRIER, __LINK_STATE_LINKWATCH_PENDING, __LINK_STATE_DORMANT, + __LINK_STATE_TESTING, }; @@ -3907,6 +3908,46 @@ static inline bool netif_dormant(const struct net_device *dev) } +/** + * netif_testing_on - mark device as under test. + * @dev: network device + * + * Mark device as under test (as per RFC2863). + * + * The testing state indicates that some test(s) must be performed on + * the interface. After completion, of the test, the interface state + * will change to up, dormant, or down, as appropriate. + */ +static inline void netif_testing_on(struct net_device *dev) +{ + if (!test_and_set_bit(__LINK_STATE_TESTING, &dev->state)) + linkwatch_fire_event(dev); +} + +/** + * netif_testing_off - set device as not under test. + * @dev: network device + * + * Device is not in testing state. + */ +static inline void netif_testing_off(struct net_device *dev) +{ + if (test_and_clear_bit(__LINK_STATE_TESTING, &dev->state)) + linkwatch_fire_event(dev); +} + +/** + * netif_testing - test if device is under test + * @dev: network device + * + * Check if device is under test + */ +static inline bool netif_testing(const struct net_device *dev) +{ + return test_bit(__LINK_STATE_TESTING, &dev->state); +} + + /** * netif_oper_up - test if device is operational * @dev: network device diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h index be714cd8c826..797ba2c1562a 100644 --- a/include/uapi/linux/if.h +++ b/include/uapi/linux/if.h @@ -178,6 +178,7 @@ enum { enum { IF_LINK_MODE_DEFAULT, IF_LINK_MODE_DORMANT, /* limit upward transition to dormant */ + IF_LINK_MODE_TESTING, /* limit upward transition to testing */ }; /* diff --git a/net/core/dev.c b/net/core/dev.c index 522288177bbd..fb61522b1ce1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9136,6 +9136,11 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev, else netif_dormant_off(dev); + if (rootdev->operstate == IF_OPER_TESTING) + netif_testing_on(dev); + else + netif_testing_off(dev); + if (netif_carrier_ok(rootdev)) netif_carrier_on(dev); else diff --git a/net/core/link_watch.c b/net/core/link_watch.c index f153e0601838..75431ca9300f 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -34,6 +34,9 @@ static DEFINE_SPINLOCK(lweventlist_lock); static unsigned char default_operstate(const struct net_device *dev) { + if (netif_testing(dev)) + return IF_OPER_TESTING; + if (!netif_carrier_ok(dev)) return (dev->ifindex != dev_get_iflink(dev) ? IF_OPER_LOWERLAYERDOWN : IF_OPER_DOWN); @@ -55,11 +58,15 @@ static void rfc2863_policy(struct net_device *dev) write_lock_bh(&dev_base_lock); switch(dev->link_mode) { + case IF_LINK_MODE_TESTING: + if (operstate == IF_OPER_UP) + operstate = IF_OPER_TESTING; + break; + case IF_LINK_MODE_DORMANT: if (operstate == IF_OPER_UP) operstate = IF_OPER_DORMANT; break; - case IF_LINK_MODE_DEFAULT: default: break; @@ -74,7 +81,8 @@ static void rfc2863_policy(struct net_device *dev) void linkwatch_init_dev(struct net_device *dev) { /* Handle pre-registration link state changes */ - if (!netif_carrier_ok(dev) || netif_dormant(dev)) + if (!netif_carrier_ok(dev) || netif_dormant(dev) || + netif_testing(dev)) rfc2863_policy(dev); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 709ebbf8ab5b..d6f4f4a9e8ba 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -829,11 +829,18 @@ static void set_operstate(struct net_device *dev, unsigned char transition) switch (transition) { case IF_OPER_UP: if ((operstate == IF_OPER_DORMANT || + operstate == IF_OPER_TESTING || operstate == IF_OPER_UNKNOWN) && - !netif_dormant(dev)) + !netif_dormant(dev) && !netif_testing(dev)) operstate = IF_OPER_UP; break; + case IF_OPER_TESTING: + if (operstate == IF_OPER_UP || + operstate == IF_OPER_UNKNOWN) + operstate = IF_OPER_TESTING; + break; + case IF_OPER_DORMANT: if (operstate == IF_OPER_UP || operstate == IF_OPER_UNKNOWN) -- cgit v1.2.3 From 72ef5e52b3f74c0be47b20f5c434b7ecc830cf40 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 14 Apr 2020 18:48:35 +0200 Subject: docs: fix broken references to text files Several references got broken due to txt to ReST conversion. Several of them can be automatically fixed with: scripts/documentation-file-ref-check --fix Reviewed-by: Mathieu Poirier # hwtracing/coresight/Kconfig Reviewed-by: Paul E. McKenney # memory-barrier.txt Acked-by: Alex Shi # translations/zh_CN Acked-by: Federico Vaga # translations/it_IT Acked-by: Marc Zyngier # kvm/arm64 Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/6f919ddb83a33b5f2a63b6b5f0575737bb2b36aa.1586881715.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- Documentation/memory-barriers.txt | 2 +- Documentation/process/submit-checklist.rst | 2 +- .../translations/it_IT/process/submit-checklist.rst | 2 +- Documentation/translations/ko_KR/memory-barriers.txt | 2 +- Documentation/translations/zh_CN/filesystems/sysfs.txt | 2 +- .../translations/zh_CN/process/submit-checklist.rst | 2 +- Documentation/virt/kvm/arm/pvtime.rst | 2 +- Documentation/virt/kvm/devices/vcpu.rst | 2 +- Documentation/virt/kvm/hypercalls.rst | 4 ++-- arch/powerpc/include/uapi/asm/kvm_para.h | 2 +- drivers/gpu/drm/Kconfig | 2 +- drivers/gpu/drm/drm_ioctl.c | 2 +- drivers/hwtracing/coresight/Kconfig | 2 +- fs/fat/Kconfig | 8 ++++---- fs/fuse/Kconfig | 2 +- fs/fuse/dev.c | 2 +- fs/overlayfs/Kconfig | 6 +++--- include/linux/mm.h | 4 ++-- include/uapi/linux/ethtool_netlink.h | 2 +- include/uapi/rdma/rdma_user_ioctl_cmds.h | 2 +- mm/gup.c | 12 ++++++------ virt/kvm/arm/vgic/vgic-mmio-v3.c | 2 +- virt/kvm/arm/vgic/vgic.h | 4 ++-- 23 files changed, 36 insertions(+), 36 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index e1c355e84edd..eaabc3134294 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -620,7 +620,7 @@ because the CPUs that the Linux kernel supports don't do writes until they are certain (1) that the write will actually happen, (2) of the location of the write, and (3) of the value to be written. But please carefully read the "CONTROL DEPENDENCIES" section and the -Documentation/RCU/rcu_dereference.txt file: The compiler can and does +Documentation/RCU/rcu_dereference.rst file: The compiler can and does break dependencies in a great many highly creative ways. CPU 1 CPU 2 diff --git a/Documentation/process/submit-checklist.rst b/Documentation/process/submit-checklist.rst index 8e56337d422d..3f8e9d5d95c2 100644 --- a/Documentation/process/submit-checklist.rst +++ b/Documentation/process/submit-checklist.rst @@ -107,7 +107,7 @@ and elsewhere regarding submitting Linux kernel patches. and why. 26) If any ioctl's are added by the patch, then also update - ``Documentation/ioctl/ioctl-number.rst``. + ``Documentation/userspace-api/ioctl/ioctl-number.rst``. 27) If your modified source code depends on or uses any of the kernel APIs or features that are related to the following ``Kconfig`` symbols, diff --git a/Documentation/translations/it_IT/process/submit-checklist.rst b/Documentation/translations/it_IT/process/submit-checklist.rst index 995ee69fab11..3e575502690f 100644 --- a/Documentation/translations/it_IT/process/submit-checklist.rst +++ b/Documentation/translations/it_IT/process/submit-checklist.rst @@ -117,7 +117,7 @@ sottomissione delle patch, in particolare sorgenti che ne spieghi la logica: cosa fanno e perché. 25) Se la patch aggiunge nuove chiamate ioctl, allora aggiornate - ``Documentation/ioctl/ioctl-number.rst``. + ``Documentation/userspace-api/ioctl/ioctl-number.rst``. 26) Se il codice che avete modificato dipende o usa una qualsiasi interfaccia o funzionalità del kernel che è associata a uno dei seguenti simboli diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt index 2e831ece6e26..e50fe6541335 100644 --- a/Documentation/translations/ko_KR/memory-barriers.txt +++ b/Documentation/translations/ko_KR/memory-barriers.txt @@ -641,7 +641,7 @@ P 는 짝수 번호 캐시 라인에 저장되어 있고, 변수 B 는 홀수 리눅스 커널이 지원하는 CPU 들은 (1) 쓰기가 정말로 일어날지, (2) 쓰기가 어디에 이루어질지, 그리고 (3) 쓰여질 값을 확실히 알기 전까지는 쓰기를 수행하지 않기 때문입니다. 하지만 "컨트롤 의존성" 섹션과 -Documentation/RCU/rcu_dereference.txt 파일을 주의 깊게 읽어 주시기 바랍니다: +Documentation/RCU/rcu_dereference.rst 파일을 주의 깊게 읽어 주시기 바랍니다: 컴파일러는 매우 창의적인 많은 방법으로 종속성을 깰 수 있습니다. CPU 1 CPU 2 diff --git a/Documentation/translations/zh_CN/filesystems/sysfs.txt b/Documentation/translations/zh_CN/filesystems/sysfs.txt index ee1f37da5b23..a15c3ebdfa82 100644 --- a/Documentation/translations/zh_CN/filesystems/sysfs.txt +++ b/Documentation/translations/zh_CN/filesystems/sysfs.txt @@ -281,7 +281,7 @@ drivers/ 包含了每个已为特定总线上的设备而挂载的驱动程序 假定驱动没有跨越多个总线类型)。 fs/ 包含了一个为文件系统设立的目录。现在每个想要导出属性的文件系统必须 -在 fs/ 下创建自己的层次结构(参见Documentation/filesystems/fuse.txt)。 +在 fs/ 下创建自己的层次结构(参见Documentation/filesystems/fuse.rst)。 dev/ 包含两个子目录： char/ 和 block/。在这两个子目录中，有以 : 格式命名的符号链接。这些符号链接指向 sysfs 目录 diff --git a/Documentation/translations/zh_CN/process/submit-checklist.rst b/Documentation/translations/zh_CN/process/submit-checklist.rst index 8738c55e42a2..50386e0e42e7 100644 --- a/Documentation/translations/zh_CN/process/submit-checklist.rst +++ b/Documentation/translations/zh_CN/process/submit-checklist.rst @@ -97,7 +97,7 @@ Linux内核补丁提交清单 24) 所有内存屏障例如 ``barrier()``, ``rmb()``, ``wmb()`` 都需要源代码中的注 释来解释它们正在执行的操作及其原因的逻辑。 -25) 如果补丁添加了任何ioctl，那么也要更新 ``Documentation/ioctl/ioctl-number.rst`` +25) 如果补丁添加了任何ioctl，那么也要更新 ``Documentation/userspace-api/ioctl/ioctl-number.rst`` 26) 如果修改后的源代码依赖或使用与以下 ``Kconfig`` 符号相关的任何内核API或 功能，则在禁用相关 ``Kconfig`` 符号和/或 ``=m`` （如果该选项可用）的情况 diff --git a/Documentation/virt/kvm/arm/pvtime.rst b/Documentation/virt/kvm/arm/pvtime.rst index 2357dd2d8655..687b60d76ca9 100644 --- a/Documentation/virt/kvm/arm/pvtime.rst +++ b/Documentation/virt/kvm/arm/pvtime.rst @@ -76,5 +76,5 @@ It is advisable that one or more 64k pages are set aside for the purpose of these structures and not used for other purposes, this enables the guest to map the region using 64k pages and avoids conflicting attributes with other memory. -For the user space interface see Documentation/virt/kvm/devices/vcpu.txt +For the user space interface see Documentation/virt/kvm/devices/vcpu.rst section "3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL". diff --git a/Documentation/virt/kvm/devices/vcpu.rst b/Documentation/virt/kvm/devices/vcpu.rst index 9963e680770a..ca374d3fe085 100644 --- a/Documentation/virt/kvm/devices/vcpu.rst +++ b/Documentation/virt/kvm/devices/vcpu.rst @@ -110,5 +110,5 @@ Returns: Specifies the base address of the stolen time structure for this VCPU. The base address must be 64 byte aligned and exist within a valid guest memory -region. See Documentation/virt/kvm/arm/pvtime.txt for more information +region. See Documentation/virt/kvm/arm/pvtime.rst for more information including the layout of the stolen time structure. diff --git a/Documentation/virt/kvm/hypercalls.rst b/Documentation/virt/kvm/hypercalls.rst index dbaf207e560d..ed4fddd364ea 100644 --- a/Documentation/virt/kvm/hypercalls.rst +++ b/Documentation/virt/kvm/hypercalls.rst @@ -22,7 +22,7 @@ S390: number in R1. For further information on the S390 diagnose call as supported by KVM, - refer to Documentation/virt/kvm/s390-diag.txt. + refer to Documentation/virt/kvm/s390-diag.rst. PowerPC: It uses R3-R10 and hypercall number in R11. R4-R11 are used as output registers. @@ -30,7 +30,7 @@ PowerPC: KVM hypercalls uses 4 byte opcode, that are patched with 'hypercall-instructions' property inside the device tree's /hypervisor node. - For more information refer to Documentation/virt/kvm/ppc-pv.txt + For more information refer to Documentation/virt/kvm/ppc-pv.rst MIPS: KVM hypercalls use the HYPCALL instruction with code 0 and the hypercall diff --git a/arch/powerpc/include/uapi/asm/kvm_para.h b/arch/powerpc/include/uapi/asm/kvm_para.h index be48c2215fa2..a809b1b44ddf 100644 --- a/arch/powerpc/include/uapi/asm/kvm_para.h +++ b/arch/powerpc/include/uapi/asm/kvm_para.h @@ -31,7 +31,7 @@ * Struct fields are always 32 or 64 bit aligned, depending on them being 32 * or 64 bit wide respectively. * - * See Documentation/virt/kvm/ppc-pv.txt + * See Documentation/virt/kvm/ppc-pv.rst */ struct kvm_vcpu_arch_shared { __u64 scratch1; diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 43594978958e..fb92be7e8aa7 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -161,7 +161,7 @@ config DRM_LOAD_EDID_FIRMWARE monitor are unable to provide appropriate EDID data. Since this feature is provided as a workaround for broken hardware, the default case is N. Details and instructions how to build your own - EDID data are given in Documentation/driver-api/edid.rst. + EDID data are given in Documentation/admin-guide/edid.rst. config DRM_DP_CEC bool "Enable DisplayPort CEC-Tunneling-over-AUX HDMI support" diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index 9e41972c4bbc..c2b8d2a953ae 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -741,7 +741,7 @@ static const struct drm_ioctl_desc drm_ioctls[] = { * }; * * Please make sure that you follow all the best practices from - * ``Documentation/ioctl/botching-up-ioctls.rst``. Note that drm_ioctl() + * ``Documentation/process/botching-up-ioctls.rst``. Note that drm_ioctl() * automatically zero-extends structures, hence make sure you can add more stuff * at the end, i.e. don't put a variable sized array there. * diff --git a/drivers/hwtracing/coresight/Kconfig b/drivers/hwtracing/coresight/Kconfig index 83e841be1081..02dbb5ca3bcf 100644 --- a/drivers/hwtracing/coresight/Kconfig +++ b/drivers/hwtracing/coresight/Kconfig @@ -107,7 +107,7 @@ config CORESIGHT_CPU_DEBUG can quickly get to know program counter (PC), secure state, exception level, etc. Before use debugging functionality, platform needs to ensure the clock domain and power domain are enabled - properly, please refer Documentation/trace/coresight-cpu-debug.rst + properly, please refer Documentation/trace/coresight/coresight-cpu-debug.rst for detailed description and the example for usage. config CORESIGHT_CTI diff --git a/fs/fat/Kconfig b/fs/fat/Kconfig index 718163d0c621..ca31993dcb47 100644 --- a/fs/fat/Kconfig +++ b/fs/fat/Kconfig @@ -69,7 +69,7 @@ config VFAT_FS The VFAT support enlarges your kernel by about 10 KB and it only works if you said Y to the "DOS FAT fs support" above. Please read - the file for details. If + the file for details. If unsure, say Y. To compile this as a module, choose M here: the module will be called @@ -82,7 +82,7 @@ config FAT_DEFAULT_CODEPAGE help This option should be set to the codepage of your FAT filesystems. It can be overridden with the "codepage" mount option. - See for more information. + See for more information. config FAT_DEFAULT_IOCHARSET string "Default iocharset for FAT" @@ -96,7 +96,7 @@ config FAT_DEFAULT_IOCHARSET Note that "utf8" is not recommended for FAT filesystems. If unsure, you shouldn't set "utf8" here - select the next option instead if you would like to use UTF-8 encoded file names by default. - See for more information. + See for more information. Enable any character sets you need in File Systems/Native Language Support. @@ -114,4 +114,4 @@ config FAT_DEFAULT_UTF8 Say Y if you use UTF-8 encoding for file names, N otherwise. - See for more information. + See for more information. diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig index eb2a585572dc..774b2618018a 100644 --- a/fs/fuse/Kconfig +++ b/fs/fuse/Kconfig @@ -12,7 +12,7 @@ config FUSE_FS although chances are your distribution already has that library installed if you've installed the "fuse" package itself. - See for more information. + See for more information. See for needed library/utility version. If you want to develop a userspace FS, or if you want to use diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 97eec7522bf2..c7a65cf2bcca 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2081,7 +2081,7 @@ static void end_polls(struct fuse_conn *fc) * The same effect is usually achievable through killing the filesystem daemon * and all users of the filesystem. The exception is the combination of an * asynchronous request and the tricky deadlock (see - * Documentation/filesystems/fuse.txt). + * Documentation/filesystems/fuse.rst). * * Aborting requests under I/O goes as follows: 1: Separate out unlocked * requests, they should be finished off immediately. Locked requests will be diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig index 714c14c47ca5..dd188c7996b3 100644 --- a/fs/overlayfs/Kconfig +++ b/fs/overlayfs/Kconfig @@ -9,7 +9,7 @@ config OVERLAY_FS 'lower' filesystem is either hidden or, in the case of directories, merged with the 'upper' object. - For more information see Documentation/filesystems/overlayfs.txt + For more information see Documentation/filesystems/overlayfs.rst config OVERLAY_FS_REDIRECT_DIR bool "Overlayfs: turn on redirect directory feature by default" @@ -38,7 +38,7 @@ config OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW If backward compatibility is not an issue, then it is safe and recommended to say N here. - For more information, see Documentation/filesystems/overlayfs.txt + For more information, see Documentation/filesystems/overlayfs.rst If unsure, say Y. @@ -103,7 +103,7 @@ config OVERLAY_FS_XINO_AUTO If compatibility with applications that expect 32bit inodes is not an issue, then it is safe and recommended to say Y here. - For more information, see Documentation/filesystems/overlayfs.txt + For more information, see Documentation/filesystems/overlayfs.rst If unsure, say N. diff --git a/include/linux/mm.h b/include/linux/mm.h index 5a323422d783..1f2850465f59 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1219,7 +1219,7 @@ void unpin_user_pages(struct page **pages, unsigned long npages); * used to track the pincount (instead using of the GUP_PIN_COUNTING_BIAS * scheme). * - * For more information, please see Documentation/vm/pin_user_pages.rst. + * For more information, please see Documentation/core-api/pin_user_pages.rst. * * @page: pointer to page to be queried. * @Return: True, if it is likely that the page has been "dma-pinned". @@ -2834,7 +2834,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * releasing pages: get_user_pages*() pages must be released via put_page(), * while pin_user_pages*() pages must be released via unpin_user_page(). * - * Please see Documentation/vm/pin_user_pages.rst for more information. + * Please see Documentation/core-api/pin_user_pages.rst for more information. */ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 7fde76366ba4..1711e57f7848 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -2,7 +2,7 @@ /* * include/uapi/linux/ethtool_netlink.h - netlink interface for ethtool * - * See Documentation/networking/ethtool-netlink.txt in kernel source tree for + * See Documentation/networking/ethtool-netlink.rst in kernel source tree for * doucumentation of the interface. */ diff --git a/include/uapi/rdma/rdma_user_ioctl_cmds.h b/include/uapi/rdma/rdma_user_ioctl_cmds.h index 7b1ec806f8f9..38ab7accb7be 100644 --- a/include/uapi/rdma/rdma_user_ioctl_cmds.h +++ b/include/uapi/rdma/rdma_user_ioctl_cmds.h @@ -36,7 +36,7 @@ #include #include -/* Documentation/ioctl/ioctl-number.rst */ +/* Documentation/userspace-api/ioctl/ioctl-number.rst */ #define RDMA_IOCTL_MAGIC 0x1b #define RDMA_VERBS_IOCTL \ _IOWR(RDMA_IOCTL_MAGIC, 1, struct ib_uverbs_ioctl_hdr) diff --git a/mm/gup.c b/mm/gup.c index 6076df8e04a4..81e4d0b377fd 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2843,9 +2843,9 @@ EXPORT_SYMBOL_GPL(get_user_pages_fast); * the arguments here are identical. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please - * see Documentation/vm/pin_user_pages.rst for further details. + * see Documentation/core-api/pin_user_pages.rst for further details. * - * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It + * This is intended for Case 1 (DIO) in Documentation/core-api/pin_user_pages.rst. It * is NOT intended for Case 2 (RDMA: long-term pins). */ int pin_user_pages_fast(unsigned long start, int nr_pages, @@ -2883,9 +2883,9 @@ EXPORT_SYMBOL_GPL(pin_user_pages_fast); * the arguments here are identical. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please - * see Documentation/vm/pin_user_pages.rst for details. + * see Documentation/core-api/pin_user_pages.rst for details. * - * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It + * This is intended for Case 1 (DIO) in Documentation/core-api/pin_user_pages.rst. It * is NOT intended for Case 2 (RDMA: long-term pins). */ long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, @@ -2919,9 +2919,9 @@ EXPORT_SYMBOL(pin_user_pages_remote); * FOLL_PIN is set. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please - * see Documentation/vm/pin_user_pages.rst for details. + * see Documentation/core-api/pin_user_pages.rst for details. * - * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It + * This is intended for Case 1 (DIO) in Documentation/core-api/pin_user_pages.rst. It * is NOT intended for Case 2 (RDMA: long-term pins). */ long pin_user_pages(unsigned long start, unsigned long nr_pages, diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index e72dcc454247..859464fd413f 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -301,7 +301,7 @@ static unsigned long vgic_v3_uaccess_read_pending(struct kvm_vcpu *vcpu, * pending state of interrupt is latched in pending_latch variable. * Userspace will save and restore pending state and line_level * separately. - * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.txt + * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.rst * for handling of ISPENDR and ICPENDR. */ for (i = 0; i < len * 8; i++) { diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 769e4802645e..64fcd7511110 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -42,7 +42,7 @@ VGIC_AFFINITY_LEVEL(val, 3)) /* - * As per Documentation/virt/kvm/devices/arm-vgic-v3.txt, + * As per Documentation/virt/kvm/devices/arm-vgic-v3.rst, * below macros are defined for CPUREG encoding. */ #define KVM_REG_ARM_VGIC_SYSREG_OP0_MASK 0x000000000000c000 @@ -63,7 +63,7 @@ KVM_REG_ARM_VGIC_SYSREG_OP2_MASK) /* - * As per Documentation/virt/kvm/devices/arm-vgic-its.txt, + * As per Documentation/virt/kvm/devices/arm-vgic-its.rst, * below macros are defined for ITS table entry encoding. */ #define KVM_ITS_CTE_VALID_SHIFT 63 -- cgit v1.2.3 From 3ecad8c2c1ff333e204c26e2f0dddfa623153f87 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 14 Apr 2020 18:48:36 +0200 Subject: docs: fix broken references for ReST files that moved around Some broken references happened due to shifting files around and ReST renames. Those can't be auto-fixed by the script, so let's fix them manually. Signed-off-by: Mauro Carvalho Chehab Acked-by: Corentin Labbe Link: https://lore.kernel.org/r/64773a12b4410aaf3e3be89e3ec7e34de2484eea.1586881715.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- Documentation/doc-guide/maintainer-profile.rst | 2 +- Documentation/virt/kvm/mmu.rst | 2 +- Documentation/virt/kvm/review-checklist.rst | 2 +- arch/x86/kvm/mmu/mmu.c | 2 +- drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c | 2 +- drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c | 2 +- drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c | 2 +- drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c | 2 +- drivers/media/v4l2-core/v4l2-fwnode.c | 2 +- include/uapi/linux/kvm.h | 4 ++-- tools/include/uapi/linux/kvm.h | 4 ++-- 11 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/doc-guide/maintainer-profile.rst b/Documentation/doc-guide/maintainer-profile.rst index 5afc0ddba40a..755d39f0d407 100644 --- a/Documentation/doc-guide/maintainer-profile.rst +++ b/Documentation/doc-guide/maintainer-profile.rst @@ -6,7 +6,7 @@ Documentation subsystem maintainer entry profile The documentation "subsystem" is the central coordinating point for the kernel's documentation and associated infrastructure. It covers the hierarchy under Documentation/ (with the exception of -Documentation/device-tree), various utilities under scripts/ and, at least +Documentation/devicetree), various utilities under scripts/ and, at least some of the time, LICENSES/. It's worth noting, though, that the boundaries of this subsystem are rather diff --git a/Documentation/virt/kvm/mmu.rst b/Documentation/virt/kvm/mmu.rst index 60981887d20b..46126ecc70f7 100644 --- a/Documentation/virt/kvm/mmu.rst +++ b/Documentation/virt/kvm/mmu.rst @@ -319,7 +319,7 @@ Handling a page fault is performed as follows: - If both P bit and R/W bit of error code are set, this could possibly be handled as a "fast page fault" (fixed without taking the MMU lock). See - the description in Documentation/virt/kvm/locking.txt. + the description in Documentation/virt/kvm/locking.rst. - if needed, walk the guest page tables to determine the guest translation (gva->gpa or ngpa->gpa) diff --git a/Documentation/virt/kvm/review-checklist.rst b/Documentation/virt/kvm/review-checklist.rst index 1f86a9d3f705..dc01aea4057b 100644 --- a/Documentation/virt/kvm/review-checklist.rst +++ b/Documentation/virt/kvm/review-checklist.rst @@ -10,7 +10,7 @@ Review checklist for kvm patches 2. Patches should be against kvm.git master branch. 3. If the patch introduces or modifies a new userspace API: - - the API must be documented in Documentation/virt/kvm/api.txt + - the API must be documented in Documentation/virt/kvm/api.rst - the API must be discoverable using KVM_CHECK_EXTENSION 4. New state must include support for save/restore. diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 8071952e9cf2..fd59fee84631 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3586,7 +3586,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, /* * Currently, fast page fault only works for direct mapping * since the gfn is not stable for indirect shadow page. See - * Documentation/virt/kvm/locking.txt to get more detail. + * Documentation/virt/kvm/locking.rst to get more detail. */ fault_handled = fast_pf_fix_direct_spte(vcpu, sp, iterator.sptep, spte, diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c index a5fd8975f3d3..a6abb701bfc6 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c @@ -8,7 +8,7 @@ * This file add support for AES cipher with 128,192,256 bits keysize in * CBC and ECB mode. * - * You could find a link for the datasheet in Documentation/arm/sunxi/README + * You could find a link for the datasheet in Documentation/arm/sunxi.rst */ #include diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c index 3e4e4bbda34c..b957061424a1 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c @@ -7,7 +7,7 @@ * * Core file which registers crypto algorithms supported by the CryptoEngine. * - * You could find a link for the datasheet in Documentation/arm/sunxi/README + * You could find a link for the datasheet in Documentation/arm/sunxi.rst */ #include #include diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c index 84d52fc3a2da..c89cb2ee2496 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c @@ -8,7 +8,7 @@ * This file add support for AES cipher with 128,192,256 bits keysize in * CBC and ECB mode. * - * You could find a link for the datasheet in Documentation/arm/sunxi/README + * You could find a link for the datasheet in Documentation/arm/sunxi.rst */ #include diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c index 6b301afffd11..8ba4f9c81dac 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c @@ -7,7 +7,7 @@ * * Core file which registers crypto algorithms supported by the SecuritySystem * - * You could find a link for the datasheet in Documentation/arm/sunxi/README + * You could find a link for the datasheet in Documentation/arm/sunxi.rst */ #include #include diff --git a/drivers/media/v4l2-core/v4l2-fwnode.c b/drivers/media/v4l2-core/v4l2-fwnode.c index 97f0f8b23b5d..8a1e1b95b379 100644 --- a/drivers/media/v4l2-core/v4l2-fwnode.c +++ b/drivers/media/v4l2-core/v4l2-fwnode.c @@ -980,7 +980,7 @@ static int v4l2_fwnode_reference_parse(struct device *dev, * * THIS EXAMPLE EXISTS MERELY TO DOCUMENT THIS FUNCTION. DO NOT USE IT AS A * REFERENCE IN HOW ACPI TABLES SHOULD BE WRITTEN!! See documentation under - * Documentation/acpi/dsd instead and especially graph.txt, + * Documentation/firmware-guide/acpi/dsd/ instead and especially graph.txt, * data-node-references.txt and leds.txt . * * Scope (\_SB.PCI0.I2C2) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 428c7dde6b4b..fdd632c833b4 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -116,7 +116,7 @@ struct kvm_irq_level { * ACPI gsi notion of irq. * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47.. * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23.. - * For ARM: See Documentation/virt/kvm/api.txt + * For ARM: See Documentation/virt/kvm/api.rst */ union { __u32 irq; @@ -1107,7 +1107,7 @@ struct kvm_xen_hvm_config { * * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies * the irqfd to operate in resampling mode for level triggered interrupt - * emulation. See Documentation/virt/kvm/api.txt. + * emulation. See Documentation/virt/kvm/api.rst. */ #define KVM_IRQFD_FLAG_RESAMPLE (1 << 1) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 4b95f9a31a2f..e5f32fcec68f 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -116,7 +116,7 @@ struct kvm_irq_level { * ACPI gsi notion of irq. * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47.. * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23.. - * For ARM: See Documentation/virt/kvm/api.txt + * For ARM: See Documentation/virt/kvm/api.rst */ union { __u32 irq; @@ -1100,7 +1100,7 @@ struct kvm_xen_hvm_config { * * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies * the irqfd to operate in resampling mode for level triggered interrupt - * emulation. See Documentation/virt/kvm/api.txt. + * emulation. See Documentation/virt/kvm/api.rst. */ #define KVM_IRQFD_FLAG_RESAMPLE (1 << 1) -- cgit v1.2.3 From af690f459393017ce40bb9beef6a00e79511574d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 14 Apr 2020 18:48:56 +0200 Subject: firewire: firewire-cdev.hL get rid of a docs warning This warning: ./include/uapi/linux/firewire-cdev.h:312: WARNING: Inline literal start-string without end-string. is because %FOO doesn't work if there's a parenthesis at the string (as a parenthesis may indicate a function). So, mark the literal block using the alternate ``FOO`` syntax. Acked-by: Stefan Richter Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/9b2501a41eba27ccdd4603cac2353c0efba7a90a.1586881715.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/uapi/linux/firewire-cdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/firewire-cdev.h b/include/uapi/linux/firewire-cdev.h index 1acd2b179aef..7e5b5c10a49c 100644 --- a/include/uapi/linux/firewire-cdev.h +++ b/include/uapi/linux/firewire-cdev.h @@ -308,7 +308,7 @@ struct fw_cdev_event_iso_interrupt_mc { /** * struct fw_cdev_event_iso_resource - Iso resources were allocated or freed * @closure: See &fw_cdev_event_common; - * set by %FW_CDEV_IOC_(DE)ALLOCATE_ISO_RESOURCE(_ONCE) ioctl + * set by``FW_CDEV_IOC_(DE)ALLOCATE_ISO_RESOURCE(_ONCE)`` ioctl * @type: %FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED or * %FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED * @handle: Reference by which an allocated resource can be deallocated -- cgit v1.2.3 From 1ca3cb46a992d83ebd093acc64241007b20c5033 Mon Sep 17 00:00:00 2001 From: Maheshwar Ajja Date: Mon, 16 Mar 2020 23:42:30 +0100 Subject: media: v4l2-ctrl: Add H264 profile and levels Add H264 profile "Contrained High" and H264 levels "5.2", "6.0", "6.1" and "6.2". Signed-off-by: Maheshwar Ajja Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-ctrls.c | 5 +++++ include/uapi/linux/v4l2-controls.h | 5 +++++ 2 files changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 93d33d1db4e8..0186ba85aac7 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -336,6 +336,10 @@ const char * const *v4l2_ctrl_get_menu(u32 id) "4.2", "5", "5.1", + "5.2", + "6.0", + "6.1", + "6.2", NULL, }; static const char * const h264_loop_filter[] = { @@ -362,6 +366,7 @@ const char * const *v4l2_ctrl_get_menu(u32 id) "Scalable High Intra", "Stereo High", "Multiview High", + "Constrained High", NULL, }; static const char * const vui_sar_idc[] = { diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 1a58d7cc4ccc..0ba1005c9651 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -473,6 +473,10 @@ enum v4l2_mpeg_video_h264_level { V4L2_MPEG_VIDEO_H264_LEVEL_4_2 = 13, V4L2_MPEG_VIDEO_H264_LEVEL_5_0 = 14, V4L2_MPEG_VIDEO_H264_LEVEL_5_1 = 15, + V4L2_MPEG_VIDEO_H264_LEVEL_5_2 = 16, + V4L2_MPEG_VIDEO_H264_LEVEL_6_0 = 17, + V4L2_MPEG_VIDEO_H264_LEVEL_6_1 = 18, + V4L2_MPEG_VIDEO_H264_LEVEL_6_2 = 19, }; #define V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_ALPHA (V4L2_CID_MPEG_BASE+360) #define V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_BETA (V4L2_CID_MPEG_BASE+361) @@ -501,6 +505,7 @@ enum v4l2_mpeg_video_h264_profile { V4L2_MPEG_VIDEO_H264_PROFILE_SCALABLE_HIGH_INTRA = 14, V4L2_MPEG_VIDEO_H264_PROFILE_STEREO_HIGH = 15, V4L2_MPEG_VIDEO_H264_PROFILE_MULTIVIEW_HIGH = 16, + V4L2_MPEG_VIDEO_H264_PROFILE_CONSTRAINED_HIGH = 17, }; #define V4L2_CID_MPEG_VIDEO_H264_VUI_EXT_SAR_HEIGHT (V4L2_CID_MPEG_BASE+364) #define V4L2_CID_MPEG_VIDEO_H264_VUI_EXT_SAR_WIDTH (V4L2_CID_MPEG_BASE+365) -- cgit v1.2.3 From 4d797fce783a8eb11dd23463828db84743795046 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Wed, 1 Apr 2020 17:25:47 +0300 Subject: cfg80211: Unprotected Beacon frame RX indication Extend cfg80211_rx_unprot_mlme_mgmt() to cover indication of unprotected Beacon frames in addition to the previously used Deauthentication and Disassociation frames. The Beacon frame case is quite similar, but has couple of exceptions: this is used both with fully unprotected and also incorrectly protected frames and there is a rate limit on the events to avoid unnecessary flooding netlink events in case something goes wrong. Signed-off-by: Jouni Malinen Link: https://lore.kernel.org/r/20200401142548.6990-1-jouni@codeaurora.org [add missing kernel-doc] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 12 ++++++++++-- include/uapi/linux/nl80211.h | 7 +++++++ net/wireless/nl80211.c | 13 +++++++++++-- net/wireless/sme.c | 2 ++ 4 files changed, 30 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 70e48f66dac8..775952677b3d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5045,6 +5045,8 @@ struct cfg80211_cqm_config; * @pmsr_list: (private) peer measurement requests * @pmsr_lock: (private) peer measurements requests/results lock * @pmsr_free_wk: (private) peer measurements cleanup work + * @unprot_beacon_reported: (private) timestamp of last + * unprotected beacon report */ struct wireless_dev { struct wiphy *wiphy; @@ -5121,6 +5123,8 @@ struct wireless_dev { struct list_head pmsr_list; spinlock_t pmsr_lock; struct work_struct pmsr_free_wk; + + unsigned long unprot_beacon_reported; }; static inline u8 *wdev_address(struct wireless_dev *wdev) @@ -6135,12 +6139,16 @@ void cfg80211_tx_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len); /** * cfg80211_rx_unprot_mlme_mgmt - notification of unprotected mlme mgmt frame * @dev: network device - * @buf: deauthentication frame (header + body) + * @buf: received management frame (header + body) * @len: length of the frame data * * This function is called whenever a received deauthentication or dissassoc * frame has been dropped in station mode because of MFP being used but the - * frame was not protected. This function may sleep. + * frame was not protected. This is also used to notify reception of a Beacon + * frame that was dropped because it did not include a valid MME MIC while + * beacon protection was enabled (BIGTK configured in station mode). + * + * This function may sleep. */ void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len); diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 2b691161830f..afdd9802ccb8 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1151,6 +1151,11 @@ * @NL80211_CMD_SET_TID_CONFIG: Data frame TID specific configuration * is passed using %NL80211_ATTR_TID_CONFIG attribute. * + * @NL80211_CMD_UNPROT_BEACON: Unprotected or incorrectly protected Beacon + * frame. This event is used to indicate that a received Beacon frame was + * dropped because it did not include a valid MME MIC while beacon + * protection was enabled (BIGTK configured in station mode). + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1377,6 +1382,8 @@ enum nl80211_commands { NL80211_CMD_SET_TID_CONFIG, + NL80211_CMD_UNPROT_BEACON, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 692bcd35f809..2127e5344b1a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -15542,10 +15542,19 @@ void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf, if (WARN_ON(len < 2)) return; - if (ieee80211_is_deauth(mgmt->frame_control)) + if (ieee80211_is_deauth(mgmt->frame_control)) { cmd = NL80211_CMD_UNPROT_DEAUTHENTICATE; - else + } else if (ieee80211_is_disassoc(mgmt->frame_control)) { cmd = NL80211_CMD_UNPROT_DISASSOCIATE; + } else if (ieee80211_is_beacon(mgmt->frame_control)) { + if (wdev->unprot_beacon_reported && + elapsed_jiffies_msecs(wdev->unprot_beacon_reported) < 10000) + return; + cmd = NL80211_CMD_UNPROT_BEACON; + wdev->unprot_beacon_reported = jiffies; + } else { + return; + } trace_cfg80211_rx_unprot_mlme_mgmt(dev, buf, len); nl80211_send_mlme_event(rdev, dev, buf, len, cmd, GFP_ATOMIC, -1, diff --git a/net/wireless/sme.c b/net/wireless/sme.c index ac3e60aa1fc8..3554c0d951f4 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -694,6 +694,7 @@ void __cfg80211_connect_result(struct net_device *dev, return; } + wdev->unprot_beacon_reported = 0; nl80211_send_connect_result(wiphy_to_rdev(wdev->wiphy), dev, cr, GFP_KERNEL); @@ -921,6 +922,7 @@ void __cfg80211_roamed(struct wireless_dev *wdev, cfg80211_hold_bss(bss_from_pub(info->bss)); wdev->current_bss = bss_from_pub(info->bss); + wdev->unprot_beacon_reported = 0; nl80211_send_roamed(wiphy_to_rdev(wdev->wiphy), wdev->netdev, info, GFP_KERNEL); -- cgit v1.2.3 From 9dba48a6ece79da064655736dc7347a5fcadedef Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 17 Apr 2020 12:40:15 +0200 Subject: cfg80211: support multicast RX registration For DPP, there's a need to receive multicast action frames, but many drivers need a special filter configuration for this. Support announcing from userspace in the management registration that multicast RX is required, with an extended feature flag if the driver handles this. Signed-off-by: Johannes Berg Reviewed-by: Sergey Matyukevich Link: https://lore.kernel.org/r/20200417124013.c46238801048.Ib041d437ce0bff28a0c6d5dc915f68f1d8591002@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 ++++ include/uapi/linux/nl80211.h | 13 +++++++++++++ net/wireless/core.h | 3 ++- net/wireless/mlme.c | 38 ++++++++++++++++++++++++++++++-------- net/wireless/nl80211.c | 10 ++++++++++ 5 files changed, 59 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index bc273f6d60f2..dbb9675fe38f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3390,9 +3390,13 @@ struct cfg80211_update_owe_info { * for the entire device * @interface_stypes: bitmap of management frame subtypes registered * for the given interface + * @global_mcast_rx: mcast RX is needed globally for these subtypes + * @interface_mcast_stypes: mcast RX is needed on this interface + * for these subtypes */ struct mgmt_frame_regs { u32 global_stypes, interface_stypes; + u32 global_mcast_stypes, interface_mcast_stypes; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index afdd9802ccb8..e0dc89eceab8 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -687,6 +687,10 @@ * four bytes for vendor frames including the OUI. The registration * cannot be dropped, but is removed automatically when the netlink * socket is closed. Multiple registrations can be made. + * The %NL80211_ATTR_RECEIVE_MULTICAST flag attribute can be given if + * %NL80211_EXT_FEATURE_MULTICAST_REGISTRATIONS is available, in which + * case the registration can also be modified to include/exclude the + * flag, rather than requiring unregistration to change it. * @NL80211_CMD_REGISTER_ACTION: Alias for @NL80211_CMD_REGISTER_FRAME for * backward compatibility * @NL80211_CMD_FRAME: Management frame TX request and RX notification. This @@ -2477,6 +2481,9 @@ enum nl80211_commands { * no roaming occurs between the reauth threshold and PMK expiration, * disassociation is still forced. * + * @NL80211_ATTR_RECEIVE_MULTICAST: multicast flag for the + * %NL80211_CMD_REGISTER_FRAME command, see the description there. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2952,6 +2959,8 @@ enum nl80211_attrs { NL80211_ATTR_PMK_LIFETIME, NL80211_ATTR_PMK_REAUTH_THRESHOLD, + NL80211_ATTR_RECEIVE_MULTICAST, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -5691,6 +5700,9 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_DEL_IBSS_STA: The driver supports removing stations * in IBSS mode, essentially by dropping their state. * + * @NL80211_EXT_FEATURE_MULTICAST_REGISTRATIONS: management frame registrations + * are possible for multicast frames and those will be reported properly. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5742,6 +5754,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_CONTROL_PORT_NO_PREAUTH, NL80211_EXT_FEATURE_PROTECTED_TWT, NL80211_EXT_FEATURE_DEL_IBSS_STA, + NL80211_EXT_FEATURE_MULTICAST_REGISTRATIONS, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/core.h b/net/wireless/core.h index 30fb2c35ae43..639d41896573 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -381,7 +381,8 @@ void cfg80211_mlme_down(struct cfg80211_registered_device *rdev, struct net_device *dev); int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_pid, u16 frame_type, const u8 *match_data, - int match_len, struct netlink_ext_ack *extack); + int match_len, bool multicast_rx, + struct netlink_ext_ack *extack); void cfg80211_mgmt_registrations_update_wk(struct work_struct *wk); void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlpid); void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 2e1a21e90b83..409497a3527d 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -426,6 +426,8 @@ struct cfg80211_mgmt_registration { __le16 frame_type; + bool multicast_rx; + u8 match[]; }; @@ -442,10 +444,18 @@ static void cfg80211_mgmt_registrations_update(struct wireless_dev *wdev) list_for_each_entry_rcu(tmp, &rdev->wiphy.wdev_list, list) { list_for_each_entry_rcu(reg, &tmp->mgmt_registrations, list) { u32 mask = BIT(le16_to_cpu(reg->frame_type) >> 4); + u32 mcast_mask = 0; + + if (reg->multicast_rx) + mcast_mask = mask; upd.global_stypes |= mask; - if (tmp == wdev) + upd.global_mcast_stypes |= mcast_mask; + + if (tmp == wdev) { upd.interface_stypes |= mask; + upd.interface_mcast_stypes |= mcast_mask; + } } } rcu_read_unlock(); @@ -465,11 +475,13 @@ void cfg80211_mgmt_registrations_update_wk(struct work_struct *wk) int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, u16 frame_type, const u8 *match_data, - int match_len, struct netlink_ext_ack *extack) + int match_len, bool multicast_rx, + struct netlink_ext_ack *extack) { struct cfg80211_mgmt_registration *reg, *nreg; int err = 0; u16 mgmt_type; + bool update_multicast = false; if (!wdev->wiphy->mgmt_stypes) return -EOPNOTSUPP; @@ -520,6 +532,11 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, continue; if (memcmp(reg->match, match_data, mlen) == 0) { + if (reg->multicast_rx != multicast_rx) { + update_multicast = true; + reg->multicast_rx = multicast_rx; + break; + } NL_SET_ERR_MSG(extack, "Match already configured"); err = -EALREADY; break; @@ -529,12 +546,17 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, if (err) goto out; - memcpy(nreg->match, match_data, match_len); - nreg->match_len = match_len; - nreg->nlportid = snd_portid; - nreg->frame_type = cpu_to_le16(frame_type); - nreg->wdev = wdev; - list_add(&nreg->list, &wdev->mgmt_registrations); + if (update_multicast) { + kfree(nreg); + } else { + memcpy(nreg->match, match_data, match_len); + nreg->match_len = match_len; + nreg->nlportid = snd_portid; + nreg->frame_type = cpu_to_le16(frame_type); + nreg->wdev = wdev; + nreg->multicast_rx = multicast_rx; + list_add(&nreg->list, &wdev->mgmt_registrations); + } spin_unlock_bh(&wdev->mgmt_registrations_lock); cfg80211_mgmt_registrations_update(wdev); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 2127e5344b1a..73a3e885d4dd 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -661,6 +661,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_CONTROL_PORT_NO_PREAUTH] = { .type = NLA_FLAG }, [NL80211_ATTR_PMK_LIFETIME] = NLA_POLICY_MIN(NLA_U32, 1), [NL80211_ATTR_PMK_REAUTH_THRESHOLD] = NLA_POLICY_RANGE(NLA_U8, 1, 100), + [NL80211_ATTR_RECEIVE_MULTICAST] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -10773,9 +10774,18 @@ static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->mgmt_tx) return -EOPNOTSUPP; + if (info->attrs[NL80211_ATTR_RECEIVE_MULTICAST] && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_MULTICAST_REGISTRATIONS)) { + GENL_SET_ERR_MSG(info, + "multicast RX registrations are not supported"); + return -EOPNOTSUPP; + } + return cfg80211_mlme_register_mgmt(wdev, info->snd_portid, frame_type, nla_data(info->attrs[NL80211_ATTR_FRAME_MATCH]), nla_len(info->attrs[NL80211_ATTR_FRAME_MATCH]), + info->attrs[NL80211_ATTR_RECEIVE_MULTICAST], info->extack); } -- cgit v1.2.3 From 155d7c733807190258639c66b36340948f369349 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 20 Apr 2020 14:06:00 +0200 Subject: nl80211: allow client-only BIGTK support The current NL80211_EXT_FEATURE_BEACON_PROTECTION feature flag requires both AP and client support, add a new one called NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT that enables only support in client (and P2P-client) modes. Link: https://lore.kernel.org/r/20200420140559.6ba704053a5a.Ifeb869fb0b48e52fe0cb9c15572b93ac8a924f8d@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 3 +++ net/wireless/nl80211.c | 19 +++++++++++++++---- 2 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index e0dc89eceab8..9679d561f7d0 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5690,6 +5690,8 @@ enum nl80211_feature_flags { * * @NL80211_EXT_FEATURE_BEACON_PROTECTION: The driver supports Beacon protection * and can receive key configuration for BIGTK using key indexes 6 and 7. + * @NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT: The driver supports Beacon + * protection as a client only and cannot transmit protected beacons. * * @NL80211_EXT_FEATURE_CONTROL_PORT_NO_PREAUTH: The driver can disable the * forwarding of preauth frames over the control port. They are then @@ -5755,6 +5757,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_PROTECTED_TWT, NL80211_EXT_FEATURE_DEL_IBSS_STA, NL80211_EXT_FEATURE_MULTICAST_REGISTRATIONS, + NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 73a3e885d4dd..d470d77d2eb6 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3905,14 +3905,25 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) }; void *hdr; struct sk_buff *msg; + bool bigtk_support = false; + + if (wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_BEACON_PROTECTION)) + bigtk_support = true; + + if ((dev->ieee80211_ptr->iftype == NL80211_IFTYPE_STATION || + dev->ieee80211_ptr->iftype == NL80211_IFTYPE_P2P_CLIENT) && + wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT)) + bigtk_support = true; if (info->attrs[NL80211_ATTR_KEY_IDX]) { key_idx = nla_get_u8(info->attrs[NL80211_ATTR_KEY_IDX]); - if (key_idx > 5 && - !wiphy_ext_feature_isset( - &rdev->wiphy, - NL80211_EXT_FEATURE_BEACON_PROTECTION)) + + if (key_idx >= 6 && key_idx <= 7 && !bigtk_support) { + GENL_SET_ERR_MSG(info, "BIGTK not supported"); return -EINVAL; + } } if (info->attrs[NL80211_ATTR_MAC]) -- cgit v1.2.3 From acd05785e48c01edb2c4f4d014d28478b5f19fb5 Mon Sep 17 00:00:00 2001 From: David Matlack Date: Fri, 17 Apr 2020 15:14:46 -0700 Subject: kvm: add capability for halt polling KVM_CAP_HALT_POLL is a per-VM capability that lets userspace control the halt-polling time, allowing halt-polling to be tuned or disabled on particular VMs. With dynamic halt-polling, a VM's VCPUs can poll from anywhere from [0, halt_poll_ns] on each halt. KVM_CAP_HALT_POLL sets the upper limit on the poll time. Signed-off-by: David Matlack Signed-off-by: Jon Cargille Reviewed-by: Jim Mattson Message-Id: <20200417221446.108733-1-jcargill@google.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 17 +++++++++++++++++ include/linux/kvm_host.h | 1 + include/uapi/linux/kvm.h | 1 + virt/kvm/kvm_main.c | 19 +++++++++++++++---- 4 files changed, 34 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index efbbe570aa9b..d871dacb984e 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5802,6 +5802,23 @@ If present, this capability can be enabled for a VM, meaning that KVM will allow the transition to secure guest mode. Otherwise KVM will veto the transition. +7.20 KVM_CAP_HALT_POLL +---------------------- + +:Architectures: all +:Target: VM +:Parameters: args[0] is the maximum poll time in nanoseconds +:Returns: 0 on success; -1 on error + +This capability overrides the kvm module parameter halt_poll_ns for the +target VM. + +VCPU polling allows a VCPU to poll for wakeup events instead of immediately +scheduling during guest halts. The maximum time a VCPU can spend polling is +controlled by the kvm module parameter halt_poll_ns. This capability allows +the maximum halt time to specified on a per-VM basis, effectively overriding +the module parameter for the target VM. + 8. Other capabilities. ====================== diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5285a5568208..3cc6ccbb1183 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -503,6 +503,7 @@ struct kvm { struct srcu_struct srcu; struct srcu_struct irq_srcu; pid_t userspace_pid; + unsigned int max_halt_poll_ns; }; #define kvm_err(fmt, ...) \ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 428c7dde6b4b..ac9eba0289d1 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1017,6 +1017,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_VCPU_RESETS 179 #define KVM_CAP_S390_PROTECTED 180 #define KVM_CAP_PPC_SECURE_GUEST 181 +#define KVM_CAP_HALT_POLL 182 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index e7436d054305..33e1eee96f75 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -710,6 +710,8 @@ static struct kvm *kvm_create_vm(unsigned long type) goto out_err_no_arch_destroy_vm; } + kvm->max_halt_poll_ns = halt_poll_ns; + r = kvm_arch_init_vm(kvm, type); if (r) goto out_err_no_arch_destroy_vm; @@ -2713,15 +2715,16 @@ out: if (!kvm_arch_no_poll(vcpu)) { if (!vcpu_valid_wakeup(vcpu)) { shrink_halt_poll_ns(vcpu); - } else if (halt_poll_ns) { + } else if (vcpu->kvm->max_halt_poll_ns) { if (block_ns <= vcpu->halt_poll_ns) ; /* we had a long block, shrink polling */ - else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns) + else if (vcpu->halt_poll_ns && + block_ns > vcpu->kvm->max_halt_poll_ns) shrink_halt_poll_ns(vcpu); /* we had a short halt and our poll time is too small */ - else if (vcpu->halt_poll_ns < halt_poll_ns && - block_ns < halt_poll_ns) + else if (vcpu->halt_poll_ns < vcpu->kvm->max_halt_poll_ns && + block_ns < vcpu->kvm->max_halt_poll_ns) grow_halt_poll_ns(vcpu); } else { vcpu->halt_poll_ns = 0; @@ -3510,6 +3513,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_IOEVENTFD_ANY_LENGTH: case KVM_CAP_CHECK_EXTENSION_VM: case KVM_CAP_ENABLE_CAP_VM: + case KVM_CAP_HALT_POLL: return 1; #ifdef CONFIG_KVM_MMIO case KVM_CAP_COALESCED_MMIO: @@ -3560,6 +3564,13 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, return 0; } #endif + case KVM_CAP_HALT_POLL: { + if (cap->flags || cap->args[0] != (unsigned int)cap->args[0]) + return -EINVAL; + + kvm->max_halt_poll_ns = cap->args[0]; + return 0; + } default: return kvm_vm_ioctl_enable_cap(kvm, cap); } -- cgit v1.2.3 From 71d19214776e61b33da48f7c1b46e522c7f78221 Mon Sep 17 00:00:00 2001 From: Maciej Żenczykowski Date: Sun, 26 Apr 2020 09:15:25 -0700 Subject: bpf: add bpf_ktime_get_boot_ns() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On a device like a cellphone which is constantly suspending and resuming CLOCK_MONOTONIC is not particularly useful for keeping track of or reacting to external network events. Instead you want to use CLOCK_BOOTTIME. Hence add bpf_ktime_get_boot_ns() as a mirror of bpf_ktime_get_ns() based around CLOCK_BOOTTIME instead of CLOCK_MONOTONIC. Signed-off-by: Maciej Żenczykowski Signed-off-by: Alexei Starovoitov --- drivers/media/rc/bpf-lirc.c | 2 ++ include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 13 ++++++++++++- kernel/bpf/core.c | 1 + kernel/bpf/helpers.c | 14 ++++++++++++++ kernel/trace/bpf_trace.c | 2 ++ tools/include/uapi/linux/bpf.h | 13 ++++++++++++- 7 files changed, 44 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index 0f3417d161b8..069c42f22a8c 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -103,6 +103,8 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_map_peek_elem_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; + case BPF_FUNC_ktime_get_boot_ns: + return &bpf_ktime_get_boot_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_prandom_u32: diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5147e11e53ff..10960cfabea4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1509,6 +1509,7 @@ extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; extern const struct bpf_func_proto bpf_get_numa_node_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; extern const struct bpf_func_proto bpf_ktime_get_ns_proto; +extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7bbf1b65be10..4a6c47f3febe 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -652,6 +652,8 @@ union bpf_attr { * u64 bpf_ktime_get_ns(void) * Description * Return the time elapsed since system boot, in nanoseconds. + * Does not include time the system was suspended. + * See: clock_gettime(CLOCK_MONOTONIC) * Return * Current *ktime*. * @@ -3025,6 +3027,14 @@ union bpf_attr { * * **-EOPNOTSUPP** Unsupported operation, for example a * call from outside of TC ingress. * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport). + * + * u64 bpf_ktime_get_boot_ns(void) + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Does include the time the system was suspended. + * See: clock_gettime(CLOCK_BOOTTIME) + * Return + * Current *ktime*. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3151,7 +3161,8 @@ union bpf_attr { FN(xdp_output), \ FN(get_netns_cookie), \ FN(get_current_ancestor_cgroup_id), \ - FN(sk_assign), + FN(sk_assign), \ + FN(ktime_get_boot_ns), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 0cc91805069a..6aa11de67315 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2156,6 +2156,7 @@ const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; const struct bpf_func_proto bpf_get_numa_node_id_proto __weak; const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; +const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 9a6b23387d02..5c0290e0696e 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -155,6 +155,18 @@ const struct bpf_func_proto bpf_ktime_get_ns_proto = { .ret_type = RET_INTEGER, }; +BPF_CALL_0(bpf_ktime_get_boot_ns) +{ + /* NMI safe access to clock boottime */ + return ktime_get_boot_fast_ns(); +} + +const struct bpf_func_proto bpf_ktime_get_boot_ns_proto = { + .func = bpf_ktime_get_boot_ns, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + BPF_CALL_0(bpf_get_current_pid_tgid) { struct task_struct *task = current; @@ -615,6 +627,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_tail_call_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; + case BPF_FUNC_ktime_get_boot_ns: + return &bpf_ktime_get_boot_ns_proto; default: break; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index ca1796747a77..e875c95d3ced 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -797,6 +797,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_map_peek_elem_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; + case BPF_FUNC_ktime_get_boot_ns: + return &bpf_ktime_get_boot_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7bbf1b65be10..4a6c47f3febe 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -652,6 +652,8 @@ union bpf_attr { * u64 bpf_ktime_get_ns(void) * Description * Return the time elapsed since system boot, in nanoseconds. + * Does not include time the system was suspended. + * See: clock_gettime(CLOCK_MONOTONIC) * Return * Current *ktime*. * @@ -3025,6 +3027,14 @@ union bpf_attr { * * **-EOPNOTSUPP** Unsupported operation, for example a * call from outside of TC ingress. * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport). + * + * u64 bpf_ktime_get_boot_ns(void) + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Does include the time the system was suspended. + * See: clock_gettime(CLOCK_BOOTTIME) + * Return + * Current *ktime*. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3151,7 +3161,8 @@ union bpf_attr { FN(xdp_output), \ FN(get_netns_cookie), \ FN(get_current_ancestor_cgroup_id), \ - FN(sk_assign), + FN(sk_assign), \ + FN(ktime_get_boot_ns), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call -- cgit v1.2.3 From 74f99482eae03195ced512b440b31d62bdb6e943 Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Tue, 21 Apr 2020 10:04:16 -0500 Subject: netfilter: nf_conntrack: add IPS_HW_OFFLOAD status bit This bit indicates that the conntrack entry is offloaded to hardware flow table. nf_conntrack entry will be tagged with [HW_OFFLOAD] if it's offload to hardware. cat /proc/net/nf_conntrack ipv4 2 tcp 6 \ src=1.1.1.17 dst=1.1.1.16 sport=56394 dport=5001 \ src=1.1.1.16 dst=1.1.1.17 sport=5001 dport=56394 [HW_OFFLOAD] \ mark=0 zone=0 use=3 Note that HW_OFFLOAD/OFFLOAD/ASSURED are mutually exclusive. Changelog: * V1->V2: - Remove check of lastused from stats. It was meant for cases such as removing driver module while traffic still running. Better to handle such cases from garbage collector. Signed-off-by: Bodong Wang Reviewed-by: Oz Shlomo Reviewed-by: Paul Blakey Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_conntrack_common.h | 8 ++++++-- net/netfilter/nf_conntrack_standalone.c | 4 +++- net/netfilter/nf_flow_table_offload.c | 3 +++ 3 files changed, 12 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index b6f0bb1dc799..4b3395082d15 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -114,15 +114,19 @@ enum ip_conntrack_status { IPS_OFFLOAD_BIT = 14, IPS_OFFLOAD = (1 << IPS_OFFLOAD_BIT), + /* Conntrack has been offloaded to hardware. */ + IPS_HW_OFFLOAD_BIT = 15, + IPS_HW_OFFLOAD = (1 << IPS_HW_OFFLOAD_BIT), + /* Be careful here, modifying these bits can make things messy, * so don't let users modify them directly. */ IPS_UNCHANGEABLE_MASK = (IPS_NAT_DONE_MASK | IPS_NAT_MASK | IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING | IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_UNTRACKED | - IPS_OFFLOAD), + IPS_OFFLOAD | IPS_HW_OFFLOAD), - __IPS_MAX_BIT = 15, + __IPS_MAX_BIT = 16, }; /* Connection tracking event types */ diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 9b57330c81f8..5a3e6c43ee68 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -348,7 +348,9 @@ static int ct_seq_show(struct seq_file *s, void *v) if (seq_print_acct(s, ct, IP_CT_DIR_REPLY)) goto release; - if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) + if (test_bit(IPS_HW_OFFLOAD_BIT, &ct->status)) + seq_puts(s, "[HW_OFFLOAD] "); + else if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) seq_puts(s, "[OFFLOAD] "); else if (test_bit(IPS_ASSURED_BIT, &ct->status)) seq_puts(s, "[ASSURED] "); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index e3b099c14eff..a2abb0feab7f 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -754,12 +754,15 @@ static void flow_offload_work_add(struct flow_offload_work *offload) err = flow_offload_rule_add(offload, flow_rule); if (err < 0) set_bit(NF_FLOW_HW_REFRESH, &offload->flow->flags); + else + set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); nf_flow_offload_destroy(flow_rule); } static void flow_offload_work_del(struct flow_offload_work *offload) { + clear_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_ORIGINAL); flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY); set_bit(NF_FLOW_HW_DEAD, &offload->flow->flags); -- cgit v1.2.3 From 4714d13791f831d253852c8b5d657270becb8b2a Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Sun, 26 Apr 2020 15:21:58 +0200 Subject: bridge: uapi: mrp: Add mrp attributes. Add new nested netlink attribute to configure the MRP. These attributes are used by the userspace to add/delete/configure MRP instances and by the kernel to notify the userspace when the MRP ring gets open/closed. MRP nested attribute has the following attributes: IFLA_BRIDGE_MRP_INSTANCE - the parameter type is br_mrp_instance which contains the instance id, and the ifindex of the two ports. The ports can't be part of multiple instances. This is used to create/delete MRP instances. IFLA_BRIDGE_MRP_PORT_STATE - the parameter type is u32. Which can be forwarding, blocking or disabled. IFLA_BRIDGE_MRP_PORT_ROLE - the parameter type is br_mrp_port_role which contains the instance id and the role. The role can be primary or secondary. IFLA_BRIDGE_MRP_RING_STATE - the parameter type is br_mrp_ring_state which contains the instance id and the state. The state can be open or closed. IFLA_BRIDGE_MRP_RING_ROLE - the parameter type is br_mrp_ring_role which contains the instance id and the ring role. The role can be MRM or MRC. IFLA_BRIDGE_MRP_START_TEST - the parameter type is br_mrp_start_test which contains the instance id, the interval at which to send the MRP_Test frames, how many test frames can be missed before declaring the ring open and the period which represent for how long to send the test frames. Also add the file include/uapi/linux/mrp_bridge.h which defines all the types used by MRP that are also needed by the userpace. Reviewed-by: Nikolay Aleksandrov Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 42 +++++++++++++++++++++ include/uapi/linux/if_ether.h | 1 + include/uapi/linux/mrp_bridge.h | 84 +++++++++++++++++++++++++++++++++++++++++ 3 files changed, 127 insertions(+) create mode 100644 include/uapi/linux/mrp_bridge.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index bfe621ea51b3..bd8c95488f16 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -120,6 +120,7 @@ enum { IFLA_BRIDGE_MODE, IFLA_BRIDGE_VLAN_INFO, IFLA_BRIDGE_VLAN_TUNNEL_INFO, + IFLA_BRIDGE_MRP, __IFLA_BRIDGE_MAX, }; #define IFLA_BRIDGE_MAX (__IFLA_BRIDGE_MAX - 1) @@ -157,6 +158,47 @@ struct bridge_vlan_xstats { __u32 pad2; }; +enum { + IFLA_BRIDGE_MRP_UNSPEC, + IFLA_BRIDGE_MRP_INSTANCE, + IFLA_BRIDGE_MRP_PORT_STATE, + IFLA_BRIDGE_MRP_PORT_ROLE, + IFLA_BRIDGE_MRP_RING_STATE, + IFLA_BRIDGE_MRP_RING_ROLE, + IFLA_BRIDGE_MRP_START_TEST, + __IFLA_BRIDGE_MRP_MAX, +}; + +struct br_mrp_instance { + __u32 ring_id; + __u32 p_ifindex; + __u32 s_ifindex; +}; + +struct br_mrp_port_role { + __u32 ring_id; + __u32 role; +}; + +struct br_mrp_ring_state { + __u32 ring_id; + __u32 ring_state; +}; + +struct br_mrp_ring_role { + __u32 ring_id; + __u32 ring_role; +}; + +struct br_mrp_start_test { + __u32 ring_id; + __u32 interval; + __u32 max_miss; + __u32 period; +}; + +#define IFLA_BRIDGE_MRP_MAX (__IFLA_BRIDGE_MRP_MAX - 1) + struct bridge_stp_xstats { __u64 transition_blk; __u64 transition_fwd; diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index f6ceb2e63d1e..d6de2b167448 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -92,6 +92,7 @@ #define ETH_P_PREAUTH 0x88C7 /* 802.11 Preauthentication */ #define ETH_P_TIPC 0x88CA /* TIPC */ #define ETH_P_LLDP 0x88CC /* Link Layer Discovery Protocol */ +#define ETH_P_MRP 0x88E3 /* Media Redundancy Protocol */ #define ETH_P_MACSEC 0x88E5 /* 802.1ae MACsec */ #define ETH_P_8021AH 0x88E7 /* 802.1ah Backbone Service Tag */ #define ETH_P_MVRP 0x88F5 /* 802.1Q MVRP */ diff --git a/include/uapi/linux/mrp_bridge.h b/include/uapi/linux/mrp_bridge.h new file mode 100644 index 000000000000..2600cdf5a284 --- /dev/null +++ b/include/uapi/linux/mrp_bridge.h @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ + +#ifndef _UAPI_LINUX_MRP_BRIDGE_H_ +#define _UAPI_LINUX_MRP_BRIDGE_H_ + +#include +#include + +#define MRP_MAX_FRAME_LENGTH 200 +#define MRP_DEFAULT_PRIO 0x8000 +#define MRP_DOMAIN_UUID_LENGTH 16 +#define MRP_VERSION 1 +#define MRP_FRAME_PRIO 7 + +enum br_mrp_ring_role_type { + BR_MRP_RING_ROLE_DISABLED, + BR_MRP_RING_ROLE_MRC, + BR_MRP_RING_ROLE_MRM, +}; + +enum br_mrp_ring_state_type { + BR_MRP_RING_STATE_OPEN, + BR_MRP_RING_STATE_CLOSED, +}; + +enum br_mrp_port_state_type { + BR_MRP_PORT_STATE_DISABLED, + BR_MRP_PORT_STATE_BLOCKED, + BR_MRP_PORT_STATE_FORWARDING, + BR_MRP_PORT_STATE_NOT_CONNECTED, +}; + +enum br_mrp_port_role_type { + BR_MRP_PORT_ROLE_PRIMARY, + BR_MRP_PORT_ROLE_SECONDARY, + BR_MRP_PORT_ROLE_NONE, +}; + +enum br_mrp_tlv_header_type { + BR_MRP_TLV_HEADER_END = 0x0, + BR_MRP_TLV_HEADER_COMMON = 0x1, + BR_MRP_TLV_HEADER_RING_TEST = 0x2, + BR_MRP_TLV_HEADER_RING_TOPO = 0x3, + BR_MRP_TLV_HEADER_RING_LINK_DOWN = 0x4, + BR_MRP_TLV_HEADER_RING_LINK_UP = 0x5, +}; + +struct br_mrp_tlv_hdr { + __u8 type; + __u8 length; +}; + +struct br_mrp_end_hdr { + struct br_mrp_tlv_hdr hdr; +}; + +struct br_mrp_common_hdr { + __u16 seq_id; + __u8 domain[MRP_DOMAIN_UUID_LENGTH]; +}; + +struct br_mrp_ring_test_hdr { + __u16 prio; + __u8 sa[ETH_ALEN]; + __u16 port_role; + __u16 state; + __u16 transitions; + __u32 timestamp; +}; + +struct br_mrp_ring_topo_hdr { + __u16 prio; + __u8 sa[ETH_ALEN]; + __u16 interval; +}; + +struct br_mrp_ring_link_hdr { + __u8 sa[ETH_ALEN]; + __u16 port_role; + __u16 interval; + __u16 blocked; +}; + +#endif -- cgit v1.2.3 From 3e54442c93845316762b1b3c75e654463fd1b715 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Sun, 26 Apr 2020 15:22:01 +0200 Subject: net: bridge: Add port attribute IFLA_BRPORT_MRP_RING_OPEN This patch adds a new port attribute, IFLA_BRPORT_MRP_RING_OPEN, which allows to notify the userspace when the port lost the continuite of MRP frames. This attribute is set by kernel whenever the SW or HW detects that the ring is being open or closed. Reviewed-by: Nikolay Aleksandrov Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 3 +++ tools/include/uapi/linux/if_link.h | 1 + 3 files changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 127c704eeba9..a009365ad67b 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -343,6 +343,7 @@ enum { IFLA_BRPORT_NEIGH_SUPPRESS, IFLA_BRPORT_ISOLATED, IFLA_BRPORT_BACKUP_PORT, + IFLA_BRPORT_MRP_RING_OPEN, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 43dab4066f91..4084f1ef8641 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -151,6 +151,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ #endif + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_RING_OPEN */ + 0; } @@ -213,6 +214,8 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) || nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS, !!(p->flags & BR_NEIGH_SUPPRESS)) || + nla_put_u8(skb, IFLA_BRPORT_MRP_RING_OPEN, !!(p->flags & + BR_MRP_LOST_CONT)) || nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(p->flags & BR_ISOLATED))) return -EMSGSIZE; diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index ca6665ea758a..cafedbbfefbe 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -343,6 +343,7 @@ enum { IFLA_BRPORT_NEIGH_SUPPRESS, IFLA_BRPORT_ISOLATED, IFLA_BRPORT_BACKUP_PORT, + IFLA_BRPORT_MRP_RING_OPEN, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) -- cgit v1.2.3 From 9d2161bed4e39ef7a5e5f18f69c4a57d001051b9 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 22 Apr 2020 17:37:04 -0400 Subject: audit: log audit netlink multicast bind and unbind Log information about programs connecting to and disconnecting from the audit netlink multicast socket. This is needed so that during investigations a security officer can tell who or what had access to the audit trail. This helps to meet the FAU_SAR.2 requirement for Common Criteria. Here is the systemd startup event: type=PROCTITLE msg=audit(2020-04-22 10:10:21.787:10) : proctitle=/init type=SYSCALL msg=audit(2020-04-22 10:10:21.787:10) : arch=x86_64 syscall=bind success=yes exit=0 a0=0x19 a1=0x555f4aac7e90 a2=0xc a3=0x7ffcb792ff44 items=0 ppid=0 pid=1 auid=unset uid=root gid=root euid=root suid=root fsuid=root egid=root sgid=root fsgid=root tty=(none) ses=unset comm=systemd exe=/usr/lib/systemd/systemd subj=kernel key=(null) type=UNKNOWN[1335] msg=audit(2020-04-22 10:10:21.787:10) : pid=1 uid=root auid=unset tty=(none) ses=unset subj=kernel comm=systemd exe=/usr/lib/systemd/systemd nl-mcgrp=1 op=connect res=yes And events from the test suite that just uses close(): type=PROCTITLE msg=audit(2020-04-22 11:47:08.501:442) : proctitle=/usr/bin/perl -w amcast_joinpart/test type=SYSCALL msg=audit(2020-04-22 11:47:08.501:442) : arch=x86_64 syscall=bind success=yes exit=0 a0=0x7 a1=0x563004378760 a2=0xc a3=0x0 items=0 ppid=815 pid=818 auid=root uid=root gid=root euid=root suid=root fsuid=root egid=root sgid=root fsgid=root tty=ttyS0 ses=1 comm=perl exe=/usr/bin/perl subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key=(null) type=UNKNOWN[1335] msg=audit(2020-04-22 11:47:08.501:442) : pid=818 uid=root auid=root tty=ttyS0 ses=1 subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 comm=perl exe=/usr/bin/perl nl-mcgrp=1 op=connect res=yes type=UNKNOWN[1335] msg=audit(2020-04-22 11:47:08.501:443) : pid=818 uid=root auid=root tty=ttyS0 ses=1 subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 comm=perl exe=/usr/bin/perl nl-mcgrp=1 op=disconnect res=yes And the events from the test suite using setsockopt with NETLINK_DROP_MEMBERSHIP: type=PROCTITLE msg=audit(2020-04-22 11:39:53.291:439) : proctitle=/usr/bin/perl -w amcast_joinpart/test type=SYSCALL msg=audit(2020-04-22 11:39:53.291:439) : arch=x86_64 syscall=bind success=yes exit=0 a0=0x7 a1=0x5560877c2d20 a2=0xc a3=0x0 items=0 ppid=772 pid=775 auid=root uid=root gid=root euid=root suid=root fsuid=root egid=root sgid=root fsgid=root tty=ttyS0 ses=1 comm=perl exe=/usr/bin/perl subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key=(null) type=UNKNOWN[1335] msg=audit(2020-04-22 11:39:53.291:439) : pid=775 uid=root auid=root tty=ttyS0 ses=1 subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 comm=perl exe=/usr/bin/perl nl-mcgrp=1 op=connect res=yes type=PROCTITLE msg=audit(2020-04-22 11:39:53.292:440) : proctitle=/usr/bin/perl -w amcast_joinpart/test type=SYSCALL msg=audit(2020-04-22 11:39:53.292:440) : arch=x86_64 syscall=setsockopt success=yes exit=0 a0=0x7 a1=SOL_NETLINK a2=0x2 a3=0x7ffc8366f000 items=0 ppid=772 pid=775 auid=root uid=root gid=root euid=root suid=root fsuid=root egid=root sgid=root fsgid=root tty=ttyS0 ses=1 comm=perl exe=/usr/bin/perl subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key=(null) type=UNKNOWN[1335] msg=audit(2020-04-22 11:39:53.292:440) : pid=775 uid=root auid=root tty=ttyS0 ses=1 subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 comm=perl exe=/usr/bin/perl nl-mcgrp=1 op=disconnect res=yes Please see the upstream issue tracker at https://github.com/linux-audit/audit-kernel/issues/28 With the feature description at https://github.com/linux-audit/audit-kernel/wiki/RFE-Audit-Multicast-Socket-Join-Part The testsuite support is at https://github.com/rgbriggs/audit-testsuite/compare/ghak28-mcast-part-join https://github.com/linux-audit/audit-testsuite/pull/93 And the userspace support patch is at https://github.com/linux-audit/audit-userspace/pull/114 Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/uapi/linux/audit.h | 1 + kernel/audit.c | 48 ++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 45 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index a534d71e689a..9b6a973f4cc3 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -117,6 +117,7 @@ #define AUDIT_TIME_INJOFFSET 1332 /* Timekeeping offset injected */ #define AUDIT_TIME_ADJNTPVAL 1333 /* NTP value adjustment */ #define AUDIT_BPF 1334 /* BPF subsystem */ +#define AUDIT_EVENT_LISTENER 1335 /* Task joined multicast read socket */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/kernel/audit.c b/kernel/audit.c index 622c30246d19..e33460e01b3b 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1530,20 +1530,60 @@ static void audit_receive(struct sk_buff *skb) audit_ctl_unlock(); } +/* Log information about who is connecting to the audit multicast socket */ +static void audit_log_multicast(int group, const char *op, int err) +{ + const struct cred *cred; + struct tty_struct *tty; + char comm[sizeof(current->comm)]; + struct audit_buffer *ab; + + if (!audit_enabled) + return; + + ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_EVENT_LISTENER); + if (!ab) + return; + + cred = current_cred(); + tty = audit_get_tty(); + audit_log_format(ab, "pid=%u uid=%u auid=%u tty=%s ses=%u", + task_pid_nr(current), + from_kuid(&init_user_ns, cred->uid), + from_kuid(&init_user_ns, audit_get_loginuid(current)), + tty ? tty_name(tty) : "(none)", + audit_get_sessionid(current)); + audit_put_tty(tty); + audit_log_task_context(ab); /* subj= */ + audit_log_format(ab, " comm="); + audit_log_untrustedstring(ab, get_task_comm(comm, current)); + audit_log_d_path_exe(ab, current->mm); /* exe= */ + audit_log_format(ab, " nl-mcgrp=%d op=%s res=%d", group, op, !err); + audit_log_end(ab); +} + /* Run custom bind function on netlink socket group connect or bind requests. */ -static int audit_bind(struct net *net, int group) +static int audit_multicast_bind(struct net *net, int group) { + int err = 0; + if (!capable(CAP_AUDIT_READ)) - return -EPERM; + err = -EPERM; + audit_log_multicast(group, "connect", err); + return err; +} - return 0; +static void audit_multicast_unbind(struct net *net, int group) +{ + audit_log_multicast(group, "disconnect", 0); } static int __net_init audit_net_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = audit_receive, - .bind = audit_bind, + .bind = audit_multicast_bind, + .unbind = audit_multicast_unbind, .flags = NL_CFG_F_NONROOT_RECV, .groups = AUDIT_NLGRP_MAX, }; -- cgit v1.2.3 From 3ff7ddb1353da9b535e65702704cbadea1da9a00 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 24 Apr 2020 21:55:37 +0200 Subject: netfilter: nft_nat: add netmap support This patch allows you to NAT the network address prefix onto another network address prefix, a.k.a. netmapping. Userspace must specify the NF_NAT_RANGE_NETMAP flag and the prefix address through the NFTA_NAT_REG_ADDR_MIN and NFTA_NAT_REG_ADDR_MAX netlink attributes. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_nat.h | 4 ++- net/netfilter/nft_nat.c | 46 ++++++++++++++++++++++++++++++++++- 2 files changed, 48 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_nat.h b/include/uapi/linux/netfilter/nf_nat.h index 4a95c0db14d4..a64586e77b24 100644 --- a/include/uapi/linux/netfilter/nf_nat.h +++ b/include/uapi/linux/netfilter/nf_nat.h @@ -11,6 +11,7 @@ #define NF_NAT_RANGE_PERSISTENT (1 << 3) #define NF_NAT_RANGE_PROTO_RANDOM_FULLY (1 << 4) #define NF_NAT_RANGE_PROTO_OFFSET (1 << 5) +#define NF_NAT_RANGE_NETMAP (1 << 6) #define NF_NAT_RANGE_PROTO_RANDOM_ALL \ (NF_NAT_RANGE_PROTO_RANDOM | NF_NAT_RANGE_PROTO_RANDOM_FULLY) @@ -18,7 +19,8 @@ #define NF_NAT_RANGE_MASK \ (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED | \ NF_NAT_RANGE_PROTO_RANDOM | NF_NAT_RANGE_PERSISTENT | \ - NF_NAT_RANGE_PROTO_RANDOM_FULLY | NF_NAT_RANGE_PROTO_OFFSET) + NF_NAT_RANGE_PROTO_RANDOM_FULLY | NF_NAT_RANGE_PROTO_OFFSET | \ + NF_NAT_RANGE_NETMAP) struct nf_nat_ipv4_range { unsigned int flags; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 7442aa8b1555..23a7bfd10521 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -60,6 +60,46 @@ static void nft_nat_setup_proto(struct nf_nat_range2 *range, nft_reg_load16(®s->data[priv->sreg_proto_max]); } +static void nft_nat_setup_netmap(struct nf_nat_range2 *range, + const struct nft_pktinfo *pkt, + const struct nft_nat *priv) +{ + struct sk_buff *skb = pkt->skb; + union nf_inet_addr new_addr; + __be32 netmask; + int i, len = 0; + + switch (priv->type) { + case NFT_NAT_SNAT: + if (nft_pf(pkt) == NFPROTO_IPV4) { + new_addr.ip = ip_hdr(skb)->saddr; + len = sizeof(struct in_addr); + } else { + new_addr.in6 = ipv6_hdr(skb)->saddr; + len = sizeof(struct in6_addr); + } + break; + case NFT_NAT_DNAT: + if (nft_pf(pkt) == NFPROTO_IPV4) { + new_addr.ip = ip_hdr(skb)->daddr; + len = sizeof(struct in_addr); + } else { + new_addr.in6 = ipv6_hdr(skb)->daddr; + len = sizeof(struct in6_addr); + } + break; + } + + for (i = 0; i < len / sizeof(__be32); i++) { + netmask = ~(range->min_addr.ip6[i] ^ range->max_addr.ip6[i]); + new_addr.ip6[i] &= ~netmask; + new_addr.ip6[i] |= range->min_addr.ip6[i] & netmask; + } + + range->min_addr = new_addr; + range->max_addr = new_addr; +} + static void nft_nat_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -70,8 +110,12 @@ static void nft_nat_eval(const struct nft_expr *expr, struct nf_nat_range2 range; memset(&range, 0, sizeof(range)); - if (priv->sreg_addr_min) + + if (priv->sreg_addr_min) { nft_nat_setup_addr(&range, regs, priv); + if (priv->flags & NF_NAT_RANGE_NETMAP) + nft_nat_setup_netmap(&range, pkt, priv); + } if (priv->sreg_proto_min) nft_nat_setup_proto(&range, regs, priv); -- cgit v1.2.3 From 5bb4b78be9c67b02a7f138850e9e89825181f555 Mon Sep 17 00:00:00 2001 From: Oak Zeng Date: Mon, 6 May 2019 22:11:14 -0500 Subject: drm/amdkfd: New IOCTL to allocate queue GWS (v2) Add a new kfd ioctl to allocate queue GWS. Queue GWS is released on queue destroy. v2: re-introduce this API with the following fixes squashed in: - drm/amdkfd: fix null pointer dereference on dev - drm/amdkfd: Return proper error code for gws alloc API - drm/amdkfd: Remove GPU ID in GWS queue creation Signed-off-by: Oak Zeng Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 39 ++++++++++++++++++++++ drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 2 ++ .../gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 9 +++++ include/uapi/linux/kfd_ioctl.h | 19 ++++++++++- 4 files changed, 68 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 0ec5f25adf56..5eb1314f500b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1584,6 +1584,43 @@ copy_from_user_failed: return err; } +static int kfd_ioctl_alloc_queue_gws(struct file *filep, + struct kfd_process *p, void *data) +{ + int retval; + struct kfd_ioctl_alloc_queue_gws_args *args = data; + struct queue *q; + struct kfd_dev *dev; + + if (!hws_gws_support) + return -ENODEV; + + mutex_lock(&p->mutex); + q = pqm_get_user_queue(&p->pqm, args->queue_id); + + if (q) { + dev = q->device; + } else { + retval = -EINVAL; + goto out_unlock; + } + + if (dev->dqm->sched_policy == KFD_SCHED_POLICY_NO_HWS) { + retval = -ENODEV; + goto out_unlock; + } + + retval = pqm_set_gws(&p->pqm, args->queue_id, args->num_gws ? dev->gws : NULL); + mutex_unlock(&p->mutex); + + args->first_gws = 0; + return retval; + +out_unlock: + mutex_unlock(&p->mutex); + return retval; +} + static int kfd_ioctl_get_dmabuf_info(struct file *filep, struct kfd_process *p, void *data) { @@ -1786,6 +1823,8 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { AMDKFD_IOCTL_DEF(AMDKFD_IOC_IMPORT_DMABUF, kfd_ioctl_import_dmabuf, 0), + AMDKFD_IOCTL_DEF(AMDKFD_IOC_ALLOC_QUEUE_GWS, + kfd_ioctl_alloc_queue_gws, 0), }; #define AMDKFD_CORE_IOCTL_COUNT ARRAY_SIZE(amdkfd_ioctls) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 4a3049841086..5e7f1fb6761b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -923,6 +923,8 @@ int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid, void *gws); struct kernel_queue *pqm_get_kernel_queue(struct process_queue_manager *pqm, unsigned int qid); +struct queue *pqm_get_user_queue(struct process_queue_manager *pqm, + unsigned int qid); int pqm_get_wave_state(struct process_queue_manager *pqm, unsigned int qid, void __user *ctl_stack, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 084c35f55d59..eb1635ac8988 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -476,6 +476,15 @@ struct kernel_queue *pqm_get_kernel_queue( return NULL; } +struct queue *pqm_get_user_queue(struct process_queue_manager *pqm, + unsigned int qid) +{ + struct process_queue_node *pqn; + + pqn = get_queue_by_qid(pqm, qid); + return pqn ? pqn->q : NULL; +} + int pqm_get_wave_state(struct process_queue_manager *pqm, unsigned int qid, void __user *ctl_stack, diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 20917c59f39c..4f6676428c5c 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -410,6 +410,20 @@ struct kfd_ioctl_unmap_memory_from_gpu_args { __u32 n_success; /* to/from KFD */ }; +/* Allocate GWS for specific queue + * + * @queue_id: queue's id that GWS is allocated for + * @num_gws: how many GWS to allocate + * @first_gws: index of the first GWS allocated. + * only support contiguous GWS allocation + */ +struct kfd_ioctl_alloc_queue_gws_args { + __u32 queue_id; /* to KFD */ + __u32 num_gws; /* to KFD */ + __u32 first_gws; /* from KFD */ + __u32 pad; +}; + struct kfd_ioctl_get_dmabuf_info_args { __u64 size; /* from KFD */ __u64 metadata_ptr; /* to KFD */ @@ -529,7 +543,10 @@ enum kfd_mmio_remap { #define AMDKFD_IOC_IMPORT_DMABUF \ AMDKFD_IOWR(0x1D, struct kfd_ioctl_import_dmabuf_args) +#define AMDKFD_IOC_ALLOC_QUEUE_GWS \ + AMDKFD_IOWR(0x1E, struct kfd_ioctl_alloc_queue_gws_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x1E +#define AMDKFD_COMMAND_END 0x1F #endif -- cgit v1.2.3 From a3b80e1078943dc12553166fb08e258463dec013 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Apr 2020 17:16:06 -0700 Subject: bpf: Allocate ID for bpf_link Generate ID for each bpf_link using IDR, similarly to bpf_map and bpf_prog. bpf_link creation, initialization, attachment, and exposing to user-space through FD and ID is a complicated multi-step process, abstract it away through bpf_link_primer and bpf_link_prime(), bpf_link_settle(), and bpf_link_cleanup() internal API. They guarantee that until bpf_link is properly attached, user-space won't be able to access partially-initialized bpf_link either from FD or ID. All this allows to simplify bpf_link attachment and error handling code. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200429001614.1544-3-andriin@fb.com --- include/linux/bpf.h | 17 ++++-- include/uapi/linux/bpf.h | 1 + kernel/bpf/cgroup.c | 14 ++--- kernel/bpf/syscall.c | 143 ++++++++++++++++++++++++++++++++--------------- 4 files changed, 118 insertions(+), 57 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 81c8620cb4c4..875d1f0af803 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1085,11 +1085,19 @@ int bpf_prog_new_fd(struct bpf_prog *prog); struct bpf_link { atomic64_t refcnt; + u32 id; const struct bpf_link_ops *ops; struct bpf_prog *prog; struct work_struct work; }; +struct bpf_link_primer { + struct bpf_link *link; + struct file *file; + int fd; + u32 id; +}; + struct bpf_link_ops { void (*release)(struct bpf_link *link); void (*dealloc)(struct bpf_link *link); @@ -1097,10 +1105,11 @@ struct bpf_link_ops { struct bpf_prog *old_prog); }; -void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops, - struct bpf_prog *prog); -void bpf_link_cleanup(struct bpf_link *link, struct file *link_file, - int link_fd); +void bpf_link_init(struct bpf_link *link, + const struct bpf_link_ops *ops, struct bpf_prog *prog); +int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); +int bpf_link_settle(struct bpf_link_primer *primer); +void bpf_link_cleanup(struct bpf_link_primer *primer); void bpf_link_inc(struct bpf_link *link); void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4a6c47f3febe..6121aa487465 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -523,6 +523,7 @@ union bpf_attr { __u32 prog_id; __u32 map_id; __u32 btf_id; + __u32 link_id; }; __u32 next_id; __u32 open_flags; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index da6e48e802b2..1bdf37fca879 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -841,10 +841,10 @@ const struct bpf_link_ops bpf_cgroup_link_lops = { int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { + struct bpf_link_primer link_primer; struct bpf_cgroup_link *link; - struct file *link_file; struct cgroup *cgrp; - int err, link_fd; + int err; if (attr->link_create.flags) return -EINVAL; @@ -862,22 +862,20 @@ int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) link->cgroup = cgrp; link->type = attr->link_create.attach_type; - link_file = bpf_link_new_file(&link->link, &link_fd); - if (IS_ERR(link_file)) { + err = bpf_link_prime(&link->link, &link_primer); + if (err) { kfree(link); - err = PTR_ERR(link_file); goto out_put_cgroup; } err = cgroup_bpf_attach(cgrp, NULL, NULL, link, link->type, BPF_F_ALLOW_MULTI); if (err) { - bpf_link_cleanup(&link->link, link_file, link_fd); + bpf_link_cleanup(&link_primer); goto out_put_cgroup; } - fd_install(link_fd, link_file); - return link_fd; + return bpf_link_settle(&link_primer); out_put_cgroup: cgroup_put(cgrp); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f5358e1462eb..5439e05e3d25 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -42,6 +42,8 @@ static DEFINE_IDR(prog_idr); static DEFINE_SPINLOCK(prog_idr_lock); static DEFINE_IDR(map_idr); static DEFINE_SPINLOCK(map_idr_lock); +static DEFINE_IDR(link_idr); +static DEFINE_SPINLOCK(link_idr_lock); int sysctl_unprivileged_bpf_disabled __read_mostly; @@ -2181,25 +2183,38 @@ static int bpf_obj_get(const union bpf_attr *attr) attr->file_flags); } -void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops, - struct bpf_prog *prog) +void bpf_link_init(struct bpf_link *link, + const struct bpf_link_ops *ops, struct bpf_prog *prog) { atomic64_set(&link->refcnt, 1); + link->id = 0; link->ops = ops; link->prog = prog; } +static void bpf_link_free_id(int id) +{ + if (!id) + return; + + spin_lock_bh(&link_idr_lock); + idr_remove(&link_idr, id); + spin_unlock_bh(&link_idr_lock); +} + /* Clean up bpf_link and corresponding anon_inode file and FD. After * anon_inode is created, bpf_link can't be just kfree()'d due to deferred - * anon_inode's release() call. This helper manages marking bpf_link as - * defunct, releases anon_inode file and puts reserved FD. + * anon_inode's release() call. This helper marksbpf_link as + * defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt + * is not decremented, it's the responsibility of a calling code that failed + * to complete bpf_link initialization. */ -void bpf_link_cleanup(struct bpf_link *link, struct file *link_file, - int link_fd) +void bpf_link_cleanup(struct bpf_link_primer *primer) { - link->prog = NULL; - fput(link_file); - put_unused_fd(link_fd); + primer->link->prog = NULL; + bpf_link_free_id(primer->id); + fput(primer->file); + put_unused_fd(primer->fd); } void bpf_link_inc(struct bpf_link *link) @@ -2210,6 +2225,7 @@ void bpf_link_inc(struct bpf_link *link) /* bpf_link_free is guaranteed to be called from process context */ static void bpf_link_free(struct bpf_link *link) { + bpf_link_free_id(link->id); if (link->prog) { /* detach BPF program, clean up used resources */ link->ops->release(link); @@ -2275,9 +2291,11 @@ static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, "link_type:\t%s\n" + "link_id:\t%u\n" "prog_tag:\t%s\n" "prog_id:\t%u\n", link_type, + link->id, prog_tag, prog->aux->id); } @@ -2292,36 +2310,76 @@ static const struct file_operations bpf_link_fops = { .write = bpf_dummy_write, }; -int bpf_link_new_fd(struct bpf_link *link) +static int bpf_link_alloc_id(struct bpf_link *link) { - return anon_inode_getfd("bpf-link", &bpf_link_fops, link, O_CLOEXEC); -} + int id; + + idr_preload(GFP_KERNEL); + spin_lock_bh(&link_idr_lock); + id = idr_alloc_cyclic(&link_idr, link, 1, INT_MAX, GFP_ATOMIC); + spin_unlock_bh(&link_idr_lock); + idr_preload_end(); -/* Similar to bpf_link_new_fd, create anon_inode for given bpf_link, but - * instead of immediately installing fd in fdtable, just reserve it and - * return. Caller then need to either install it with fd_install(fd, file) or - * release with put_unused_fd(fd). - * This is useful for cases when bpf_link attachment/detachment are - * complicated and expensive operations and should be delayed until all the fd - * reservation and anon_inode creation succeeds. + return id; +} + +/* Prepare bpf_link to be exposed to user-space by allocating anon_inode file, + * reserving unused FD and allocating ID from link_idr. This is to be paired + * with bpf_link_settle() to install FD and ID and expose bpf_link to + * user-space, if bpf_link is successfully attached. If not, bpf_link and + * pre-allocated resources are to be freed with bpf_cleanup() call. All the + * transient state is passed around in struct bpf_link_primer. + * This is preferred way to create and initialize bpf_link, especially when + * there are complicated and expensive operations inbetween creating bpf_link + * itself and attaching it to BPF hook. By using bpf_link_prime() and + * bpf_link_settle() kernel code using bpf_link doesn't have to perform + * expensive (and potentially failing) roll back operations in a rare case + * that file, FD, or ID can't be allocated. */ -struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd) +int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer) { struct file *file; - int fd; + int fd, id; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) - return ERR_PTR(fd); + return fd; file = anon_inode_getfile("bpf_link", &bpf_link_fops, link, O_CLOEXEC); if (IS_ERR(file)) { put_unused_fd(fd); - return file; + return PTR_ERR(file); } - *reserved_fd = fd; - return file; + id = bpf_link_alloc_id(link); + if (id < 0) { + put_unused_fd(fd); + fput(file); + return id; + } + + primer->link = link; + primer->file = file; + primer->fd = fd; + primer->id = id; + return 0; +} + +int bpf_link_settle(struct bpf_link_primer *primer) +{ + /* make bpf_link fetchable by ID */ + spin_lock_bh(&link_idr_lock); + primer->link->id = primer->id; + spin_unlock_bh(&link_idr_lock); + /* make bpf_link fetchable by FD */ + fd_install(primer->fd, primer->file); + /* pass through installed FD */ + return primer->fd; +} + +int bpf_link_new_fd(struct bpf_link *link) +{ + return anon_inode_getfd("bpf-link", &bpf_link_fops, link, O_CLOEXEC); } struct bpf_link *bpf_link_get_from_fd(u32 ufd) @@ -2367,9 +2425,9 @@ static const struct bpf_link_ops bpf_tracing_link_lops = { static int bpf_tracing_prog_attach(struct bpf_prog *prog) { + struct bpf_link_primer link_primer; struct bpf_tracing_link *link; - struct file *link_file; - int link_fd, err; + int err; switch (prog->type) { case BPF_PROG_TYPE_TRACING: @@ -2404,22 +2462,19 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog) } bpf_link_init(&link->link, &bpf_tracing_link_lops, prog); - link_file = bpf_link_new_file(&link->link, &link_fd); - if (IS_ERR(link_file)) { + err = bpf_link_prime(&link->link, &link_primer); + if (err) { kfree(link); - err = PTR_ERR(link_file); goto out_put_prog; } err = bpf_trampoline_link_prog(prog); if (err) { - bpf_link_cleanup(&link->link, link_file, link_fd); + bpf_link_cleanup(&link_primer); goto out_put_prog; } - fd_install(link_fd, link_file); - return link_fd; - + return bpf_link_settle(&link_primer); out_put_prog: bpf_prog_put(prog); return err; @@ -2447,7 +2502,7 @@ static void bpf_raw_tp_link_dealloc(struct bpf_link *link) kfree(raw_tp); } -static const struct bpf_link_ops bpf_raw_tp_lops = { +static const struct bpf_link_ops bpf_raw_tp_link_lops = { .release = bpf_raw_tp_link_release, .dealloc = bpf_raw_tp_link_dealloc, }; @@ -2456,13 +2511,13 @@ static const struct bpf_link_ops bpf_raw_tp_lops = { static int bpf_raw_tracepoint_open(const union bpf_attr *attr) { + struct bpf_link_primer link_primer; struct bpf_raw_tp_link *link; struct bpf_raw_event_map *btp; - struct file *link_file; struct bpf_prog *prog; const char *tp_name; char buf[128]; - int link_fd, err; + int err; if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) return -EINVAL; @@ -2515,24 +2570,22 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) err = -ENOMEM; goto out_put_btp; } - bpf_link_init(&link->link, &bpf_raw_tp_lops, prog); + bpf_link_init(&link->link, &bpf_raw_tp_link_lops, prog); link->btp = btp; - link_file = bpf_link_new_file(&link->link, &link_fd); - if (IS_ERR(link_file)) { + err = bpf_link_prime(&link->link, &link_primer); + if (err) { kfree(link); - err = PTR_ERR(link_file); goto out_put_btp; } err = bpf_probe_register(link->btp, prog); if (err) { - bpf_link_cleanup(&link->link, link_file, link_fd); + bpf_link_cleanup(&link_primer); goto out_put_btp; } - fd_install(link_fd, link_file); - return link_fd; + return bpf_link_settle(&link_primer); out_put_btp: bpf_put_raw_tracepoint(btp); @@ -3464,7 +3517,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr, if (file->f_op == &bpf_link_fops) { struct bpf_link *link = file->private_data; - if (link->ops == &bpf_raw_tp_lops) { + if (link->ops == &bpf_raw_tp_link_lops) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); struct bpf_raw_event_map *btp = raw_tp->btp; -- cgit v1.2.3 From 2d602c8cf40d65d4a7ac34fe18648d8778e6e594 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Apr 2020 17:16:07 -0700 Subject: bpf: Support GET_FD_BY_ID and GET_NEXT_ID for bpf_link Add support to look up bpf_link by ID and iterate over all existing bpf_links in the system. GET_FD_BY_ID code handles not-yet-ready bpf_link by checking that its ID hasn't been set to non-zero value yet. Setting bpf_link's ID is done as the very last step in finalizing bpf_link, together with installing FD. This approach allows users of bpf_link in kernel code to not worry about races between user-space and kernel code that hasn't finished attaching and initializing bpf_link. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200429001614.1544-4-andriin@fb.com --- include/uapi/linux/bpf.h | 2 ++ kernel/bpf/syscall.c | 49 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6121aa487465..7e6541fceade 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -113,6 +113,8 @@ enum bpf_cmd { BPF_MAP_DELETE_BATCH, BPF_LINK_CREATE, BPF_LINK_UPDATE, + BPF_LINK_GET_FD_BY_ID, + BPF_LINK_GET_NEXT_ID, }; enum bpf_map_type { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5439e05e3d25..1c213a730502 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3713,6 +3713,48 @@ out_put_link: return ret; } +static int bpf_link_inc_not_zero(struct bpf_link *link) +{ + return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? 0 : -ENOENT; +} + +#define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id + +static int bpf_link_get_fd_by_id(const union bpf_attr *attr) +{ + struct bpf_link *link; + u32 id = attr->link_id; + int fd, err; + + if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + spin_lock_bh(&link_idr_lock); + link = idr_find(&link_idr, id); + /* before link is "settled", ID is 0, pretend it doesn't exist yet */ + if (link) { + if (link->id) + err = bpf_link_inc_not_zero(link); + else + err = -EAGAIN; + } else { + err = -ENOENT; + } + spin_unlock_bh(&link_idr_lock); + + if (err) + return err; + + fd = bpf_link_new_fd(link); + if (fd < 0) + bpf_link_put(link); + + return fd; +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr; @@ -3830,6 +3872,13 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_LINK_UPDATE: err = link_update(&attr); break; + case BPF_LINK_GET_FD_BY_ID: + err = bpf_link_get_fd_by_id(&attr); + break; + case BPF_LINK_GET_NEXT_ID: + err = bpf_obj_get_next_id(&attr, uattr, + &link_idr, &link_idr_lock); + break; default: err = -EINVAL; break; -- cgit v1.2.3 From f2e10bff16a0fdd41ba278c84da9813700e356af Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Apr 2020 17:16:08 -0700 Subject: bpf: Add support for BPF_OBJ_GET_INFO_BY_FD for bpf_link Add ability to fetch bpf_link details through BPF_OBJ_GET_INFO_BY_FD command. Also enhance show_fdinfo to potentially include bpf_link type-specific information (similarly to obj_info). Also introduce enum bpf_link_type stored in bpf_link itself and expose it in UAPI. bpf_link_tracing also now will store and return bpf_attach_type. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200429001614.1544-5-andriin@fb.com --- include/linux/bpf-cgroup.h | 2 - include/linux/bpf.h | 8 ++- include/linux/bpf_types.h | 6 ++ include/uapi/linux/bpf.h | 28 ++++++++ kernel/bpf/btf.c | 2 + kernel/bpf/cgroup.c | 43 +++++++++++- kernel/bpf/syscall.c | 155 ++++++++++++++++++++++++++++++++++++----- kernel/bpf/verifier.c | 2 + tools/include/uapi/linux/bpf.h | 31 +++++++++ 9 files changed, 253 insertions(+), 24 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index a9cb9a5bf8e9..272626cc3fc9 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -57,8 +57,6 @@ struct bpf_cgroup_link { enum bpf_attach_type type; }; -extern const struct bpf_link_ops bpf_cgroup_link_lops; - struct bpf_prog_list { struct list_head node; struct bpf_prog *prog; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 875d1f0af803..c07b1d2f3824 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1026,9 +1026,11 @@ extern const struct file_operations bpf_prog_fops; extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ extern const struct bpf_map_ops _ops; +#define BPF_LINK_TYPE(_id, _name) #include #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE +#undef BPF_LINK_TYPE extern const struct bpf_prog_ops bpf_offload_prog_ops; extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops; @@ -1086,6 +1088,7 @@ int bpf_prog_new_fd(struct bpf_prog *prog); struct bpf_link { atomic64_t refcnt; u32 id; + enum bpf_link_type type; const struct bpf_link_ops *ops; struct bpf_prog *prog; struct work_struct work; @@ -1103,9 +1106,12 @@ struct bpf_link_ops { void (*dealloc)(struct bpf_link *link); int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog); + void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); + int (*fill_link_info)(const struct bpf_link *link, + struct bpf_link_info *info); }; -void bpf_link_init(struct bpf_link *link, +void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog); int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); int bpf_link_settle(struct bpf_link_primer *primer); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index ba0c2d56f8a3..8345cdf553b8 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -118,3 +118,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) #if defined(CONFIG_BPF_JIT) BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops) #endif + +BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) +BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) +#ifdef CONFIG_CGROUP_BPF +BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup) +#endif diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7e6541fceade..0eccafae55bb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -222,6 +222,15 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +enum bpf_link_type { + BPF_LINK_TYPE_UNSPEC = 0, + BPF_LINK_TYPE_RAW_TRACEPOINT = 1, + BPF_LINK_TYPE_TRACING = 2, + BPF_LINK_TYPE_CGROUP = 3, + + MAX_BPF_LINK_TYPE, +}; + /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command * * NONE(default): No further bpf programs allowed in the subtree. @@ -3612,6 +3621,25 @@ struct bpf_btf_info { __u32 id; } __attribute__((aligned(8))); +struct bpf_link_info { + __u32 type; + __u32 id; + __u32 prog_id; + union { + struct { + __aligned_u64 tp_name; /* in/out: tp_name buffer ptr */ + __u32 tp_name_len; /* in/out: tp_name buffer len */ + } raw_tracepoint; + struct { + __u32 attach_type; + } tracing; + struct { + __u64 cgroup_id; + __u32 attach_type; + } cgroup; + }; +} __attribute__((aligned(8))); + /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed * by user and intended to be used by socket (e.g. to bind to, depends on * attach attach type). diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index d65c6912bdaf..a2cfba89a8e1 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3482,6 +3482,7 @@ extern char __weak __stop_BTF[]; extern struct btf *btf_vmlinux; #define BPF_MAP_TYPE(_id, _ops) +#define BPF_LINK_TYPE(_id, _name) static union { struct bpf_ctx_convert { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ @@ -3508,6 +3509,7 @@ static u8 bpf_ctx_convert_map[] = { 0, /* avoid empty array */ }; #undef BPF_MAP_TYPE +#undef BPF_LINK_TYPE static const struct btf_member * btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf, diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 1bdf37fca879..5c0e964105ac 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -833,10 +833,48 @@ static void bpf_cgroup_link_dealloc(struct bpf_link *link) kfree(cg_link); } -const struct bpf_link_ops bpf_cgroup_link_lops = { +static void bpf_cgroup_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + struct bpf_cgroup_link *cg_link = + container_of(link, struct bpf_cgroup_link, link); + u64 cg_id = 0; + + mutex_lock(&cgroup_mutex); + if (cg_link->cgroup) + cg_id = cgroup_id(cg_link->cgroup); + mutex_unlock(&cgroup_mutex); + + seq_printf(seq, + "cgroup_id:\t%llu\n" + "attach_type:\t%d\n", + cg_id, + cg_link->type); +} + +static int bpf_cgroup_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + struct bpf_cgroup_link *cg_link = + container_of(link, struct bpf_cgroup_link, link); + u64 cg_id = 0; + + mutex_lock(&cgroup_mutex); + if (cg_link->cgroup) + cg_id = cgroup_id(cg_link->cgroup); + mutex_unlock(&cgroup_mutex); + + info->cgroup.cgroup_id = cg_id; + info->cgroup.attach_type = cg_link->type; + return 0; +} + +static const struct bpf_link_ops bpf_cgroup_link_lops = { .release = bpf_cgroup_link_release, .dealloc = bpf_cgroup_link_dealloc, .update_prog = cgroup_bpf_replace, + .show_fdinfo = bpf_cgroup_link_show_fdinfo, + .fill_link_info = bpf_cgroup_link_fill_link_info, }; int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) @@ -858,7 +896,8 @@ int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) err = -ENOMEM; goto out_put_cgroup; } - bpf_link_init(&link->link, &bpf_cgroup_link_lops, prog); + bpf_link_init(&link->link, BPF_LINK_TYPE_CGROUP, &bpf_cgroup_link_lops, + prog); link->cgroup = cgrp; link->type = attr->link_create.attach_type; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 1c213a730502..d23c04cbe14f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -51,9 +51,11 @@ static const struct bpf_map_ops * const bpf_map_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) #define BPF_MAP_TYPE(_id, _ops) \ [_id] = &_ops, +#define BPF_LINK_TYPE(_id, _name) #include #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE +#undef BPF_LINK_TYPE }; /* @@ -1548,9 +1550,11 @@ static const struct bpf_prog_ops * const bpf_prog_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _prog_ops, #define BPF_MAP_TYPE(_id, _ops) +#define BPF_LINK_TYPE(_id, _name) #include #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE +#undef BPF_LINK_TYPE }; static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) @@ -2183,10 +2187,11 @@ static int bpf_obj_get(const union bpf_attr *attr) attr->file_flags); } -void bpf_link_init(struct bpf_link *link, +void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog) { atomic64_set(&link->refcnt, 1); + link->type = type; link->id = 0; link->ops = ops; link->prog = prog; @@ -2266,27 +2271,23 @@ static int bpf_link_release(struct inode *inode, struct file *filp) return 0; } -#ifdef CONFIG_PROC_FS -static const struct bpf_link_ops bpf_raw_tp_lops; -static const struct bpf_link_ops bpf_tracing_link_lops; +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) +#define BPF_MAP_TYPE(_id, _ops) +#define BPF_LINK_TYPE(_id, _name) [_id] = #_name, +static const char *bpf_link_type_strs[] = { + [BPF_LINK_TYPE_UNSPEC] = "", +#include +}; +#undef BPF_PROG_TYPE +#undef BPF_MAP_TYPE +#undef BPF_LINK_TYPE +#ifdef CONFIG_PROC_FS static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_link *link = filp->private_data; const struct bpf_prog *prog = link->prog; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; - const char *link_type; - - if (link->ops == &bpf_raw_tp_lops) - link_type = "raw_tracepoint"; - else if (link->ops == &bpf_tracing_link_lops) - link_type = "tracing"; -#ifdef CONFIG_CGROUP_BPF - else if (link->ops == &bpf_cgroup_link_lops) - link_type = "cgroup"; -#endif - else - link_type = "unknown"; bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, @@ -2294,10 +2295,12 @@ static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) "link_id:\t%u\n" "prog_tag:\t%s\n" "prog_id:\t%u\n", - link_type, + bpf_link_type_strs[link->type], link->id, prog_tag, prog->aux->id); + if (link->ops->show_fdinfo) + link->ops->show_fdinfo(link, m); } #endif @@ -2403,6 +2406,7 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd) struct bpf_tracing_link { struct bpf_link link; + enum bpf_attach_type attach_type; }; static void bpf_tracing_link_release(struct bpf_link *link) @@ -2418,9 +2422,33 @@ static void bpf_tracing_link_dealloc(struct bpf_link *link) kfree(tr_link); } +static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + struct bpf_tracing_link *tr_link = + container_of(link, struct bpf_tracing_link, link); + + seq_printf(seq, + "attach_type:\t%d\n", + tr_link->attach_type); +} + +static int bpf_tracing_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + struct bpf_tracing_link *tr_link = + container_of(link, struct bpf_tracing_link, link); + + info->tracing.attach_type = tr_link->attach_type; + + return 0; +} + static const struct bpf_link_ops bpf_tracing_link_lops = { .release = bpf_tracing_link_release, .dealloc = bpf_tracing_link_dealloc, + .show_fdinfo = bpf_tracing_link_show_fdinfo, + .fill_link_info = bpf_tracing_link_fill_link_info, }; static int bpf_tracing_prog_attach(struct bpf_prog *prog) @@ -2460,7 +2488,9 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog) err = -ENOMEM; goto out_put_prog; } - bpf_link_init(&link->link, &bpf_tracing_link_lops, prog); + bpf_link_init(&link->link, BPF_LINK_TYPE_TRACING, + &bpf_tracing_link_lops, prog); + link->attach_type = prog->expected_attach_type; err = bpf_link_prime(&link->link, &link_primer); if (err) { @@ -2502,9 +2532,56 @@ static void bpf_raw_tp_link_dealloc(struct bpf_link *link) kfree(raw_tp); } +static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + struct bpf_raw_tp_link *raw_tp_link = + container_of(link, struct bpf_raw_tp_link, link); + + seq_printf(seq, + "tp_name:\t%s\n", + raw_tp_link->btp->tp->name); +} + +static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + struct bpf_raw_tp_link *raw_tp_link = + container_of(link, struct bpf_raw_tp_link, link); + char __user *ubuf = u64_to_user_ptr(info->raw_tracepoint.tp_name); + const char *tp_name = raw_tp_link->btp->tp->name; + u32 ulen = info->raw_tracepoint.tp_name_len; + size_t tp_len = strlen(tp_name); + + if (ulen && !ubuf) + return -EINVAL; + + info->raw_tracepoint.tp_name_len = tp_len + 1; + + if (!ubuf) + return 0; + + if (ulen >= tp_len + 1) { + if (copy_to_user(ubuf, tp_name, tp_len + 1)) + return -EFAULT; + } else { + char zero = '\0'; + + if (copy_to_user(ubuf, tp_name, ulen - 1)) + return -EFAULT; + if (put_user(zero, ubuf + ulen - 1)) + return -EFAULT; + return -ENOSPC; + } + + return 0; +} + static const struct bpf_link_ops bpf_raw_tp_link_lops = { .release = bpf_raw_tp_link_release, .dealloc = bpf_raw_tp_link_dealloc, + .show_fdinfo = bpf_raw_tp_link_show_fdinfo, + .fill_link_info = bpf_raw_tp_link_fill_link_info, }; #define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd @@ -2570,7 +2647,8 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) err = -ENOMEM; goto out_put_btp; } - bpf_link_init(&link->link, &bpf_raw_tp_link_lops, prog); + bpf_link_init(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT, + &bpf_raw_tp_link_lops, prog); link->btp = btp; err = bpf_link_prime(&link->link, &link_primer); @@ -3366,6 +3444,42 @@ static int bpf_btf_get_info_by_fd(struct btf *btf, return btf_get_info_by_fd(btf, attr, uattr); } +static int bpf_link_get_info_by_fd(struct bpf_link *link, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct bpf_link_info __user *uinfo = u64_to_user_ptr(attr->info.info); + struct bpf_link_info info; + u32 info_len = attr->info.info_len; + int err; + + err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); + if (err) + return err; + info_len = min_t(u32, sizeof(info), info_len); + + memset(&info, 0, sizeof(info)); + if (copy_from_user(&info, uinfo, info_len)) + return -EFAULT; + + info.type = link->type; + info.id = link->id; + info.prog_id = link->prog->aux->id; + + if (link->ops->fill_link_info) { + err = link->ops->fill_link_info(link, &info); + if (err) + return err; + } + + if (copy_to_user(uinfo, &info, info_len) || + put_user(info_len, &uattr->info.info_len)) + return -EFAULT; + + return 0; +} + + #define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, @@ -3390,6 +3504,9 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, uattr); else if (f.file->f_op == &btf_fops) err = bpf_btf_get_info_by_fd(f.file->private_data, attr, uattr); + else if (f.file->f_op == &bpf_link_fops) + err = bpf_link_get_info_by_fd(f.file->private_data, + attr, uattr); else err = -EINVAL; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 91728e0f27eb..2b337e32aa94 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -28,9 +28,11 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _verifier_ops, #define BPF_MAP_TYPE(_id, _ops) +#define BPF_LINK_TYPE(_id, _name) #include #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE +#undef BPF_LINK_TYPE }; /* bpf_check() is a static code analyzer that walks eBPF program diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 4a6c47f3febe..0eccafae55bb 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -113,6 +113,8 @@ enum bpf_cmd { BPF_MAP_DELETE_BATCH, BPF_LINK_CREATE, BPF_LINK_UPDATE, + BPF_LINK_GET_FD_BY_ID, + BPF_LINK_GET_NEXT_ID, }; enum bpf_map_type { @@ -220,6 +222,15 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +enum bpf_link_type { + BPF_LINK_TYPE_UNSPEC = 0, + BPF_LINK_TYPE_RAW_TRACEPOINT = 1, + BPF_LINK_TYPE_TRACING = 2, + BPF_LINK_TYPE_CGROUP = 3, + + MAX_BPF_LINK_TYPE, +}; + /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command * * NONE(default): No further bpf programs allowed in the subtree. @@ -523,6 +534,7 @@ union bpf_attr { __u32 prog_id; __u32 map_id; __u32 btf_id; + __u32 link_id; }; __u32 next_id; __u32 open_flags; @@ -3609,6 +3621,25 @@ struct bpf_btf_info { __u32 id; } __attribute__((aligned(8))); +struct bpf_link_info { + __u32 type; + __u32 id; + __u32 prog_id; + union { + struct { + __aligned_u64 tp_name; /* in/out: tp_name buffer ptr */ + __u32 tp_name_len; /* in/out: tp_name buffer len */ + } raw_tracepoint; + struct { + __u32 attach_type; + } tracing; + struct { + __u64 cgroup_id; + __u32 attach_type; + } cgroup; + }; +} __attribute__((aligned(8))); + /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed * by user and intended to be used by socket (e.g. to bind to, depends on * attach attach type). -- cgit v1.2.3 From 97f9ac3db6612f14ac0c509e1a63ce14fd4cc0eb Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Tue, 21 Apr 2020 12:44:49 -0500 Subject: crypto: ccp - Add support for SEV-ES to the PSP driver To provide support for SEV-ES, the hypervisor must provide an area of memory to the PSP. Once this Trusted Memory Region (TMR) is provided to the PSP, the contents of this area of memory are no longer available to the x86. Update the PSP driver to allocate a 1MB region for the TMR that is 1MB aligned and then provide it to the PSP through the SEV INIT command. Signed-off-by: Tom Lendacky Reviewed-by: Brijesh Singh Reviewed-by: Joerg Roedel Signed-off-by: Herbert Xu --- drivers/crypto/ccp/sev-dev.c | 43 +++++++++++++++++++++++++++++++++++++++++++ include/linux/psp-sev.h | 2 ++ include/uapi/linux/psp-sev.h | 2 ++ 3 files changed, 47 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 896f190b9a50..439cd737076e 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -20,6 +20,7 @@ #include #include #include +#include #include @@ -44,6 +45,14 @@ MODULE_PARM_DESC(psp_probe_timeout, " default timeout value, in seconds, during static bool psp_dead; static int psp_timeout; +/* Trusted Memory Region (TMR): + * The TMR is a 1MB area that must be 1MB aligned. Use the page allocator + * to allocate the memory, which will return aligned memory for the specified + * allocation order. + */ +#define SEV_ES_TMR_SIZE (1024 * 1024) +static void *sev_es_tmr; + static inline bool sev_version_greater_or_equal(u8 maj, u8 min) { struct sev_device *sev = psp_master->sev_data; @@ -214,6 +223,20 @@ static int __sev_platform_init_locked(int *error) if (sev->state == SEV_STATE_INIT) return 0; + if (sev_es_tmr) { + u64 tmr_pa; + + /* + * Do not include the encryption mask on the physical + * address of the TMR (firmware should clear it anyway). + */ + tmr_pa = __pa(sev_es_tmr); + + sev->init_cmd_buf.flags |= SEV_INIT_FLAGS_SEV_ES; + sev->init_cmd_buf.tmr_address = tmr_pa; + sev->init_cmd_buf.tmr_len = SEV_ES_TMR_SIZE; + } + rc = __sev_do_cmd_locked(SEV_CMD_INIT, &sev->init_cmd_buf, error); if (rc) return rc; @@ -1012,6 +1035,7 @@ EXPORT_SYMBOL_GPL(sev_issue_cmd_external_user); void sev_pci_init(void) { struct sev_device *sev = psp_master->sev_data; + struct page *tmr_page; int error, rc; if (!sev) @@ -1041,6 +1065,16 @@ void sev_pci_init(void) sev_update_firmware(sev->dev) == 0) sev_get_api_version(); + /* Obtain the TMR memory area for SEV-ES use */ + tmr_page = alloc_pages(GFP_KERNEL, get_order(SEV_ES_TMR_SIZE)); + if (tmr_page) { + sev_es_tmr = page_address(tmr_page); + } else { + sev_es_tmr = NULL; + dev_warn(sev->dev, + "SEV: TMR allocation failed, SEV-ES support unavailable\n"); + } + /* Initialize the platform */ rc = sev_platform_init(&error); if (rc && (error == SEV_RET_SECURE_DATA_INVALID)) { @@ -1075,4 +1109,13 @@ void sev_pci_exit(void) return; sev_platform_shutdown(NULL); + + if (sev_es_tmr) { + /* The TMR area was encrypted, flush it from the cache */ + wbinvd_on_all_cpus(); + + free_pages((unsigned long)sev_es_tmr, + get_order(SEV_ES_TMR_SIZE)); + sev_es_tmr = NULL; + } } diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 5167bf2bfc75..7fbc8679145c 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -100,6 +100,8 @@ struct sev_data_init { u32 tmr_len; /* In */ } __packed; +#define SEV_INIT_FLAGS_SEV_ES 0x01 + /** * struct sev_data_pek_csr - PEK_CSR command parameters * diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index 0549a5c622bf..91b4c63d5cbf 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -83,6 +83,8 @@ struct sev_user_data_status { __u32 guest_count; /* Out */ } __packed; +#define SEV_STATUS_FLAGS_CONFIG_ES 0x0100 + /** * struct sev_user_data_pek_csr - PEK_CSR command parameters * -- cgit v1.2.3 From 6e3a401fc8af01828bcdc92d713195d318b36e7e Mon Sep 17 00:00:00 2001 From: Dmitry Yakunin Date: Thu, 30 Apr 2020 18:51:14 +0300 Subject: inet_diag: add cgroup id attribute This patch adds cgroup v2 ID to common inet diag message attributes. Cgroup v2 ID is kernfs ID (ino or ino+gen). This attribute allows filter inet diag output by cgroup ID obtained by name_to_handle_at() syscall. When net_cls or net_prio cgroup is activated this ID is equal to 1 (root cgroup ID) for newly created sockets. Some notes about this ID: 1) gets initialized in socket() syscall 2) incoming socket gets ID from listening socket (not during accept() syscall) 3) not changed when process get moved to another cgroup 4) can point to deleted cgroup (refcounting) v2: - use CONFIG_SOCK_CGROUP_DATA instead if CONFIG_CGROUPS v3: - fix attr size by using nla_total_size_64bit() (Eric Dumazet) - more detailed commit message (Konstantin Khlebnikov) Signed-off-by: Dmitry Yakunin Reviewed-by: Konstantin Khlebnikov Acked-By: Tejun Heo Signed-off-by: David S. Miller --- include/linux/inet_diag.h | 6 +++++- include/uapi/linux/inet_diag.h | 1 + net/ipv4/inet_diag.c | 7 +++++++ 3 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index ce9ed1c0602f..0ef2d800fda7 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -71,7 +71,11 @@ static inline size_t inet_diag_msg_attrs_size(void) + nla_total_size(1) /* INET_DIAG_SKV6ONLY */ #endif + nla_total_size(4) /* INET_DIAG_MARK */ - + nla_total_size(4); /* INET_DIAG_CLASS_ID */ + + nla_total_size(4) /* INET_DIAG_CLASS_ID */ +#ifdef CONFIG_SOCK_CGROUP_DATA + + nla_total_size_64bit(sizeof(u64)) /* INET_DIAG_CGROUP_ID */ +#endif + ; } int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_msg *r, int ext, diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index 57cc429a9177..c9b1e551792c 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -157,6 +157,7 @@ enum { INET_DIAG_MD5SIG, INET_DIAG_ULP_INFO, INET_DIAG_SK_BPF_STORAGES, + INET_DIAG_CGROUP_ID, __INET_DIAG_MAX, }; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 5d50aad3cdbf..9c4c315cbc10 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -162,6 +162,13 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, goto errout; } +#ifdef CONFIG_SOCK_CGROUP_DATA + if (nla_put_u64_64bit(skb, INET_DIAG_CGROUP_ID, + cgroup_id(sock_cgroup_ptr(&sk->sk_cgrp_data)), + INET_DIAG_PAD)) + goto errout; +#endif + r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk); -- cgit v1.2.3 From b1f3e43dbfacfcd95296b0f80f84b186add9ef54 Mon Sep 17 00:00:00 2001 From: Dmitry Yakunin Date: Thu, 30 Apr 2020 18:51:15 +0300 Subject: inet_diag: add support for cgroup filter This patch adds ability to filter sockets based on cgroup v2 ID. Such filter is helpful in ss utility for filtering sockets by cgroup pathname. Signed-off-by: Dmitry Yakunin Reviewed-by: Konstantin Khlebnikov Signed-off-by: David S. Miller --- include/uapi/linux/inet_diag.h | 1 + net/ipv4/inet_diag.c | 31 +++++++++++++++++++++++++++++++ 2 files changed, 32 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index c9b1e551792c..e6f183ee8417 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -96,6 +96,7 @@ enum { INET_DIAG_BC_MARK_COND, INET_DIAG_BC_S_EQ, INET_DIAG_BC_D_EQ, + INET_DIAG_BC_CGROUP_COND, /* u64 cgroup v2 ID */ }; struct inet_diag_hostcond { diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 9c4c315cbc10..0034092358c3 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -43,6 +43,9 @@ struct inet_diag_entry { u16 userlocks; u32 ifindex; u32 mark; +#ifdef CONFIG_SOCK_CGROUP_DATA + u64 cgroup_id; +#endif }; static DEFINE_MUTEX(inet_diag_table_mutex); @@ -682,6 +685,16 @@ static int inet_diag_bc_run(const struct nlattr *_bc, yes = 0; break; } +#ifdef CONFIG_SOCK_CGROUP_DATA + case INET_DIAG_BC_CGROUP_COND: { + u64 cgroup_id; + + cgroup_id = get_unaligned((const u64 *)(op + 1)); + if (cgroup_id != entry->cgroup_id) + yes = 0; + break; + } +#endif } if (yes) { @@ -732,6 +745,9 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark; else entry.mark = 0; +#ifdef CONFIG_SOCK_CGROUP_DATA + entry.cgroup_id = cgroup_id(sock_cgroup_ptr(&sk->sk_cgrp_data)); +#endif return inet_diag_bc_run(bc, &entry); } @@ -821,6 +837,15 @@ static bool valid_markcond(const struct inet_diag_bc_op *op, int len, return len >= *min_len; } +#ifdef CONFIG_SOCK_CGROUP_DATA +static bool valid_cgroupcond(const struct inet_diag_bc_op *op, int len, + int *min_len) +{ + *min_len += sizeof(u64); + return len >= *min_len; +} +#endif + static int inet_diag_bc_audit(const struct nlattr *attr, const struct sk_buff *skb) { @@ -863,6 +888,12 @@ static int inet_diag_bc_audit(const struct nlattr *attr, if (!valid_markcond(bc, len, &min_len)) return -EINVAL; break; +#ifdef CONFIG_SOCK_CGROUP_DATA + case INET_DIAG_BC_CGROUP_COND: + if (!valid_cgroupcond(bc, len, &min_len)) + return -EINVAL; + break; +#endif case INET_DIAG_BC_AUTO: case INET_DIAG_BC_JMP: case INET_DIAG_BC_NOP: -- cgit v1.2.3 From 06bfa47e72c83550fefc93c62a1ace5fff72e212 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 30 Apr 2020 18:04:31 +0200 Subject: docs: networking: convert timestamping.txt to ReST - add SPDX header; - add a document title; - adjust titles and chapters, adding proper markups; - mark code blocks and literals as such; - adjust identation, whitespaces and blank lines where needed; - add to networking/index.rst. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: David S. Miller --- Documentation/networking/index.rst | 1 + Documentation/networking/packet_mmap.rst | 4 +- Documentation/networking/timestamping.rst | 591 ++++++++++++++++++++++++++++++ Documentation/networking/timestamping.txt | 571 ----------------------------- include/uapi/linux/errqueue.h | 2 +- 5 files changed, 595 insertions(+), 574 deletions(-) create mode 100644 Documentation/networking/timestamping.rst delete mode 100644 Documentation/networking/timestamping.txt (limited to 'include/uapi/linux') diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index be65ee509669..8f9a84b8e3f2 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -109,6 +109,7 @@ Contents: tc-actions-env-rules tcp-thin team + timestamping .. only:: subproject and html diff --git a/Documentation/networking/packet_mmap.rst b/Documentation/networking/packet_mmap.rst index 884c7222b9e9..6c009ceb1183 100644 --- a/Documentation/networking/packet_mmap.rst +++ b/Documentation/networking/packet_mmap.rst @@ -1030,7 +1030,7 @@ the packet meta information for mmap(2)ed RX_RING and TX_RINGs. If your NIC is capable of timestamping packets in hardware, you can request those hardware timestamps to be used. Note: you may need to enable the generation of hardware timestamps with SIOCSHWTSTAMP (see related information from -Documentation/networking/timestamping.txt). +Documentation/networking/timestamping.rst). PACKET_TIMESTAMP accepts the same integer bit field as SO_TIMESTAMPING:: @@ -1069,7 +1069,7 @@ TX_RING part only TP_STATUS_AVAILABLE is set, then the tp_sec and tp_{n,u}sec members do not contain a valid value. For TX_RINGs, by default no timestamp is generated! -See include/linux/net_tstamp.h and Documentation/networking/timestamping.txt +See include/linux/net_tstamp.h and Documentation/networking/timestamping.rst for more information on hardware timestamps. Miscellaneous bits diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst new file mode 100644 index 000000000000..1adead6a4527 --- /dev/null +++ b/Documentation/networking/timestamping.rst @@ -0,0 +1,591 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============ +Timestamping +============ + + +1. Control Interfaces +===================== + +The interfaces for receiving network packages timestamps are: + +SO_TIMESTAMP + Generates a timestamp for each incoming packet in (not necessarily + monotonic) system time. Reports the timestamp via recvmsg() in a + control message in usec resolution. + SO_TIMESTAMP is defined as SO_TIMESTAMP_NEW or SO_TIMESTAMP_OLD + based on the architecture type and time_t representation of libc. + Control message format is in struct __kernel_old_timeval for + SO_TIMESTAMP_OLD and in struct __kernel_sock_timeval for + SO_TIMESTAMP_NEW options respectively. + +SO_TIMESTAMPNS + Same timestamping mechanism as SO_TIMESTAMP, but reports the + timestamp as struct timespec in nsec resolution. + SO_TIMESTAMPNS is defined as SO_TIMESTAMPNS_NEW or SO_TIMESTAMPNS_OLD + based on the architecture type and time_t representation of libc. + Control message format is in struct timespec for SO_TIMESTAMPNS_OLD + and in struct __kernel_timespec for SO_TIMESTAMPNS_NEW options + respectively. + +IP_MULTICAST_LOOP + SO_TIMESTAMP[NS] + Only for multicast:approximate transmit timestamp obtained by + reading the looped packet receive timestamp. + +SO_TIMESTAMPING + Generates timestamps on reception, transmission or both. Supports + multiple timestamp sources, including hardware. Supports generating + timestamps for stream sockets. + + +1.1 SO_TIMESTAMP (also SO_TIMESTAMP_OLD and SO_TIMESTAMP_NEW) +------------------------------------------------------------- + +This socket option enables timestamping of datagrams on the reception +path. Because the destination socket, if any, is not known early in +the network stack, the feature has to be enabled for all packets. The +same is true for all early receive timestamp options. + +For interface details, see `man 7 socket`. + +Always use SO_TIMESTAMP_NEW timestamp to always get timestamp in +struct __kernel_sock_timeval format. + +SO_TIMESTAMP_OLD returns incorrect timestamps after the year 2038 +on 32 bit machines. + +1.2 SO_TIMESTAMPNS (also SO_TIMESTAMPNS_OLD and SO_TIMESTAMPNS_NEW): + +This option is identical to SO_TIMESTAMP except for the returned data type. +Its struct timespec allows for higher resolution (ns) timestamps than the +timeval of SO_TIMESTAMP (ms). + +Always use SO_TIMESTAMPNS_NEW timestamp to always get timestamp in +struct __kernel_timespec format. + +SO_TIMESTAMPNS_OLD returns incorrect timestamps after the year 2038 +on 32 bit machines. + +1.3 SO_TIMESTAMPING (also SO_TIMESTAMPING_OLD and SO_TIMESTAMPING_NEW) +---------------------------------------------------------------------- + +Supports multiple types of timestamp requests. As a result, this +socket option takes a bitmap of flags, not a boolean. In:: + + err = setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, &val, sizeof(val)); + +val is an integer with any of the following bits set. Setting other +bit returns EINVAL and does not change the current state. + +The socket option configures timestamp generation for individual +sk_buffs (1.3.1), timestamp reporting to the socket's error +queue (1.3.2) and options (1.3.3). Timestamp generation can also +be enabled for individual sendmsg calls using cmsg (1.3.4). + + +1.3.1 Timestamp Generation +^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Some bits are requests to the stack to try to generate timestamps. Any +combination of them is valid. Changes to these bits apply to newly +created packets, not to packets already in the stack. As a result, it +is possible to selectively request timestamps for a subset of packets +(e.g., for sampling) by embedding an send() call within two setsockopt +calls, one to enable timestamp generation and one to disable it. +Timestamps may also be generated for reasons other than being +requested by a particular socket, such as when receive timestamping is +enabled system wide, as explained earlier. + +SOF_TIMESTAMPING_RX_HARDWARE: + Request rx timestamps generated by the network adapter. + +SOF_TIMESTAMPING_RX_SOFTWARE: + Request rx timestamps when data enters the kernel. These timestamps + are generated just after a device driver hands a packet to the + kernel receive stack. + +SOF_TIMESTAMPING_TX_HARDWARE: + Request tx timestamps generated by the network adapter. This flag + can be enabled via both socket options and control messages. + +SOF_TIMESTAMPING_TX_SOFTWARE: + Request tx timestamps when data leaves the kernel. These timestamps + are generated in the device driver as close as possible, but always + prior to, passing the packet to the network interface. Hence, they + require driver support and may not be available for all devices. + This flag can be enabled via both socket options and control messages. + +SOF_TIMESTAMPING_TX_SCHED: + Request tx timestamps prior to entering the packet scheduler. Kernel + transmit latency is, if long, often dominated by queuing delay. The + difference between this timestamp and one taken at + SOF_TIMESTAMPING_TX_SOFTWARE will expose this latency independent + of protocol processing. The latency incurred in protocol + processing, if any, can be computed by subtracting a userspace + timestamp taken immediately before send() from this timestamp. On + machines with virtual devices where a transmitted packet travels + through multiple devices and, hence, multiple packet schedulers, + a timestamp is generated at each layer. This allows for fine + grained measurement of queuing delay. This flag can be enabled + via both socket options and control messages. + +SOF_TIMESTAMPING_TX_ACK: + Request tx timestamps when all data in the send buffer has been + acknowledged. This only makes sense for reliable protocols. It is + currently only implemented for TCP. For that protocol, it may + over-report measurement, because the timestamp is generated when all + data up to and including the buffer at send() was acknowledged: the + cumulative acknowledgment. The mechanism ignores SACK and FACK. + This flag can be enabled via both socket options and control messages. + + +1.3.2 Timestamp Reporting +^^^^^^^^^^^^^^^^^^^^^^^^^ + +The other three bits control which timestamps will be reported in a +generated control message. Changes to the bits take immediate +effect at the timestamp reporting locations in the stack. Timestamps +are only reported for packets that also have the relevant timestamp +generation request set. + +SOF_TIMESTAMPING_SOFTWARE: + Report any software timestamps when available. + +SOF_TIMESTAMPING_SYS_HARDWARE: + This option is deprecated and ignored. + +SOF_TIMESTAMPING_RAW_HARDWARE: + Report hardware timestamps as generated by + SOF_TIMESTAMPING_TX_HARDWARE when available. + + +1.3.3 Timestamp Options +^^^^^^^^^^^^^^^^^^^^^^^ + +The interface supports the options + +SOF_TIMESTAMPING_OPT_ID: + Generate a unique identifier along with each packet. A process can + have multiple concurrent timestamping requests outstanding. Packets + can be reordered in the transmit path, for instance in the packet + scheduler. In that case timestamps will be queued onto the error + queue out of order from the original send() calls. It is not always + possible to uniquely match timestamps to the original send() calls + based on timestamp order or payload inspection alone, then. + + This option associates each packet at send() with a unique + identifier and returns that along with the timestamp. The identifier + is derived from a per-socket u32 counter (that wraps). For datagram + sockets, the counter increments with each sent packet. For stream + sockets, it increments with every byte. + + The counter starts at zero. It is initialized the first time that + the socket option is enabled. It is reset each time the option is + enabled after having been disabled. Resetting the counter does not + change the identifiers of existing packets in the system. + + This option is implemented only for transmit timestamps. There, the + timestamp is always looped along with a struct sock_extended_err. + The option modifies field ee_data to pass an id that is unique + among all possibly concurrently outstanding timestamp requests for + that socket. + + +SOF_TIMESTAMPING_OPT_CMSG: + Support recv() cmsg for all timestamped packets. Control messages + are already supported unconditionally on all packets with receive + timestamps and on IPv6 packets with transmit timestamp. This option + extends them to IPv4 packets with transmit timestamp. One use case + is to correlate packets with their egress device, by enabling socket + option IP_PKTINFO simultaneously. + + +SOF_TIMESTAMPING_OPT_TSONLY: + Applies to transmit timestamps only. Makes the kernel return the + timestamp as a cmsg alongside an empty packet, as opposed to + alongside the original packet. This reduces the amount of memory + charged to the socket's receive budget (SO_RCVBUF) and delivers + the timestamp even if sysctl net.core.tstamp_allow_data is 0. + This option disables SOF_TIMESTAMPING_OPT_CMSG. + +SOF_TIMESTAMPING_OPT_STATS: + Optional stats that are obtained along with the transmit timestamps. + It must be used together with SOF_TIMESTAMPING_OPT_TSONLY. When the + transmit timestamp is available, the stats are available in a + separate control message of type SCM_TIMESTAMPING_OPT_STATS, as a + list of TLVs (struct nlattr) of types. These stats allow the + application to associate various transport layer stats with + the transmit timestamps, such as how long a certain block of + data was limited by peer's receiver window. + +SOF_TIMESTAMPING_OPT_PKTINFO: + Enable the SCM_TIMESTAMPING_PKTINFO control message for incoming + packets with hardware timestamps. The message contains struct + scm_ts_pktinfo, which supplies the index of the real interface which + received the packet and its length at layer 2. A valid (non-zero) + interface index will be returned only if CONFIG_NET_RX_BUSY_POLL is + enabled and the driver is using NAPI. The struct contains also two + other fields, but they are reserved and undefined. + +SOF_TIMESTAMPING_OPT_TX_SWHW: + Request both hardware and software timestamps for outgoing packets + when SOF_TIMESTAMPING_TX_HARDWARE and SOF_TIMESTAMPING_TX_SOFTWARE + are enabled at the same time. If both timestamps are generated, + two separate messages will be looped to the socket's error queue, + each containing just one timestamp. + +New applications are encouraged to pass SOF_TIMESTAMPING_OPT_ID to +disambiguate timestamps and SOF_TIMESTAMPING_OPT_TSONLY to operate +regardless of the setting of sysctl net.core.tstamp_allow_data. + +An exception is when a process needs additional cmsg data, for +instance SOL_IP/IP_PKTINFO to detect the egress network interface. +Then pass option SOF_TIMESTAMPING_OPT_CMSG. This option depends on +having access to the contents of the original packet, so cannot be +combined with SOF_TIMESTAMPING_OPT_TSONLY. + + +1.3.4. Enabling timestamps via control messages +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +In addition to socket options, timestamp generation can be requested +per write via cmsg, only for SOF_TIMESTAMPING_TX_* (see Section 1.3.1). +Using this feature, applications can sample timestamps per sendmsg() +without paying the overhead of enabling and disabling timestamps via +setsockopt:: + + struct msghdr *msg; + ... + cmsg = CMSG_FIRSTHDR(msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SO_TIMESTAMPING; + cmsg->cmsg_len = CMSG_LEN(sizeof(__u32)); + *((__u32 *) CMSG_DATA(cmsg)) = SOF_TIMESTAMPING_TX_SCHED | + SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_TX_ACK; + err = sendmsg(fd, msg, 0); + +The SOF_TIMESTAMPING_TX_* flags set via cmsg will override +the SOF_TIMESTAMPING_TX_* flags set via setsockopt. + +Moreover, applications must still enable timestamp reporting via +setsockopt to receive timestamps:: + + __u32 val = SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_OPT_ID /* or any other flag */; + err = setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, &val, sizeof(val)); + + +1.4 Bytestream Timestamps +------------------------- + +The SO_TIMESTAMPING interface supports timestamping of bytes in a +bytestream. Each request is interpreted as a request for when the +entire contents of the buffer has passed a timestamping point. That +is, for streams option SOF_TIMESTAMPING_TX_SOFTWARE will record +when all bytes have reached the device driver, regardless of how +many packets the data has been converted into. + +In general, bytestreams have no natural delimiters and therefore +correlating a timestamp with data is non-trivial. A range of bytes +may be split across segments, any segments may be merged (possibly +coalescing sections of previously segmented buffers associated with +independent send() calls). Segments can be reordered and the same +byte range can coexist in multiple segments for protocols that +implement retransmissions. + +It is essential that all timestamps implement the same semantics, +regardless of these possible transformations, as otherwise they are +incomparable. Handling "rare" corner cases differently from the +simple case (a 1:1 mapping from buffer to skb) is insufficient +because performance debugging often needs to focus on such outliers. + +In practice, timestamps can be correlated with segments of a +bytestream consistently, if both semantics of the timestamp and the +timing of measurement are chosen correctly. This challenge is no +different from deciding on a strategy for IP fragmentation. There, the +definition is that only the first fragment is timestamped. For +bytestreams, we chose that a timestamp is generated only when all +bytes have passed a point. SOF_TIMESTAMPING_TX_ACK as defined is easy to +implement and reason about. An implementation that has to take into +account SACK would be more complex due to possible transmission holes +and out of order arrival. + +On the host, TCP can also break the simple 1:1 mapping from buffer to +skbuff as a result of Nagle, cork, autocork, segmentation and GSO. The +implementation ensures correctness in all cases by tracking the +individual last byte passed to send(), even if it is no longer the +last byte after an skbuff extend or merge operation. It stores the +relevant sequence number in skb_shinfo(skb)->tskey. Because an skbuff +has only one such field, only one timestamp can be generated. + +In rare cases, a timestamp request can be missed if two requests are +collapsed onto the same skb. A process can detect this situation by +enabling SOF_TIMESTAMPING_OPT_ID and comparing the byte offset at +send time with the value returned for each timestamp. It can prevent +the situation by always flushing the TCP stack in between requests, +for instance by enabling TCP_NODELAY and disabling TCP_CORK and +autocork. + +These precautions ensure that the timestamp is generated only when all +bytes have passed a timestamp point, assuming that the network stack +itself does not reorder the segments. The stack indeed tries to avoid +reordering. The one exception is under administrator control: it is +possible to construct a packet scheduler configuration that delays +segments from the same stream differently. Such a setup would be +unusual. + + +2 Data Interfaces +================== + +Timestamps are read using the ancillary data feature of recvmsg(). +See `man 3 cmsg` for details of this interface. The socket manual +page (`man 7 socket`) describes how timestamps generated with +SO_TIMESTAMP and SO_TIMESTAMPNS records can be retrieved. + + +2.1 SCM_TIMESTAMPING records +---------------------------- + +These timestamps are returned in a control message with cmsg_level +SOL_SOCKET, cmsg_type SCM_TIMESTAMPING, and payload of type + +For SO_TIMESTAMPING_OLD:: + + struct scm_timestamping { + struct timespec ts[3]; + }; + +For SO_TIMESTAMPING_NEW:: + + struct scm_timestamping64 { + struct __kernel_timespec ts[3]; + +Always use SO_TIMESTAMPING_NEW timestamp to always get timestamp in +struct scm_timestamping64 format. + +SO_TIMESTAMPING_OLD returns incorrect timestamps after the year 2038 +on 32 bit machines. + +The structure can return up to three timestamps. This is a legacy +feature. At least one field is non-zero at any time. Most timestamps +are passed in ts[0]. Hardware timestamps are passed in ts[2]. + +ts[1] used to hold hardware timestamps converted to system time. +Instead, expose the hardware clock device on the NIC directly as +a HW PTP clock source, to allow time conversion in userspace and +optionally synchronize system time with a userspace PTP stack such +as linuxptp. For the PTP clock API, see Documentation/driver-api/ptp.rst. + +Note that if the SO_TIMESTAMP or SO_TIMESTAMPNS option is enabled +together with SO_TIMESTAMPING using SOF_TIMESTAMPING_SOFTWARE, a false +software timestamp will be generated in the recvmsg() call and passed +in ts[0] when a real software timestamp is missing. This happens also +on hardware transmit timestamps. + +2.1.1 Transmit timestamps with MSG_ERRQUEUE +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +For transmit timestamps the outgoing packet is looped back to the +socket's error queue with the send timestamp(s) attached. A process +receives the timestamps by calling recvmsg() with flag MSG_ERRQUEUE +set and with a msg_control buffer sufficiently large to receive the +relevant metadata structures. The recvmsg call returns the original +outgoing data packet with two ancillary messages attached. + +A message of cm_level SOL_IP(V6) and cm_type IP(V6)_RECVERR +embeds a struct sock_extended_err. This defines the error type. For +timestamps, the ee_errno field is ENOMSG. The other ancillary message +will have cm_level SOL_SOCKET and cm_type SCM_TIMESTAMPING. This +embeds the struct scm_timestamping. + + +2.1.1.2 Timestamp types +~~~~~~~~~~~~~~~~~~~~~~~ + +The semantics of the three struct timespec are defined by field +ee_info in the extended error structure. It contains a value of +type SCM_TSTAMP_* to define the actual timestamp passed in +scm_timestamping. + +The SCM_TSTAMP_* types are 1:1 matches to the SOF_TIMESTAMPING_* +control fields discussed previously, with one exception. For legacy +reasons, SCM_TSTAMP_SND is equal to zero and can be set for both +SOF_TIMESTAMPING_TX_HARDWARE and SOF_TIMESTAMPING_TX_SOFTWARE. It +is the first if ts[2] is non-zero, the second otherwise, in which +case the timestamp is stored in ts[0]. + + +2.1.1.3 Fragmentation +~~~~~~~~~~~~~~~~~~~~~ + +Fragmentation of outgoing datagrams is rare, but is possible, e.g., by +explicitly disabling PMTU discovery. If an outgoing packet is fragmented, +then only the first fragment is timestamped and returned to the sending +socket. + + +2.1.1.4 Packet Payload +~~~~~~~~~~~~~~~~~~~~~~ + +The calling application is often not interested in receiving the whole +packet payload that it passed to the stack originally: the socket +error queue mechanism is just a method to piggyback the timestamp on. +In this case, the application can choose to read datagrams with a +smaller buffer, possibly even of length 0. The payload is truncated +accordingly. Until the process calls recvmsg() on the error queue, +however, the full packet is queued, taking up budget from SO_RCVBUF. + + +2.1.1.5 Blocking Read +~~~~~~~~~~~~~~~~~~~~~ + +Reading from the error queue is always a non-blocking operation. To +block waiting on a timestamp, use poll or select. poll() will return +POLLERR in pollfd.revents if any data is ready on the error queue. +There is no need to pass this flag in pollfd.events. This flag is +ignored on request. See also `man 2 poll`. + + +2.1.2 Receive timestamps +^^^^^^^^^^^^^^^^^^^^^^^^ + +On reception, there is no reason to read from the socket error queue. +The SCM_TIMESTAMPING ancillary data is sent along with the packet data +on a normal recvmsg(). Since this is not a socket error, it is not +accompanied by a message SOL_IP(V6)/IP(V6)_RECVERROR. In this case, +the meaning of the three fields in struct scm_timestamping is +implicitly defined. ts[0] holds a software timestamp if set, ts[1] +is again deprecated and ts[2] holds a hardware timestamp if set. + + +3. Hardware Timestamping configuration: SIOCSHWTSTAMP and SIOCGHWTSTAMP +======================================================================= + +Hardware time stamping must also be initialized for each device driver +that is expected to do hardware time stamping. The parameter is defined in +include/uapi/linux/net_tstamp.h as:: + + struct hwtstamp_config { + int flags; /* no flags defined right now, must be zero */ + int tx_type; /* HWTSTAMP_TX_* */ + int rx_filter; /* HWTSTAMP_FILTER_* */ + }; + +Desired behavior is passed into the kernel and to a specific device by +calling ioctl(SIOCSHWTSTAMP) with a pointer to a struct ifreq whose +ifr_data points to a struct hwtstamp_config. The tx_type and +rx_filter are hints to the driver what it is expected to do. If +the requested fine-grained filtering for incoming packets is not +supported, the driver may time stamp more than just the requested types +of packets. + +Drivers are free to use a more permissive configuration than the requested +configuration. It is expected that drivers should only implement directly the +most generic mode that can be supported. For example if the hardware can +support HWTSTAMP_FILTER_V2_EVENT, then it should generally always upscale +HWTSTAMP_FILTER_V2_L2_SYNC_MESSAGE, and so forth, as HWTSTAMP_FILTER_V2_EVENT +is more generic (and more useful to applications). + +A driver which supports hardware time stamping shall update the struct +with the actual, possibly more permissive configuration. If the +requested packets cannot be time stamped, then nothing should be +changed and ERANGE shall be returned (in contrast to EINVAL, which +indicates that SIOCSHWTSTAMP is not supported at all). + +Only a processes with admin rights may change the configuration. User +space is responsible to ensure that multiple processes don't interfere +with each other and that the settings are reset. + +Any process can read the actual configuration by passing this +structure to ioctl(SIOCGHWTSTAMP) in the same way. However, this has +not been implemented in all drivers. + +:: + + /* possible values for hwtstamp_config->tx_type */ + enum { + /* + * no outgoing packet will need hardware time stamping; + * should a packet arrive which asks for it, no hardware + * time stamping will be done + */ + HWTSTAMP_TX_OFF, + + /* + * enables hardware time stamping for outgoing packets; + * the sender of the packet decides which are to be + * time stamped by setting SOF_TIMESTAMPING_TX_SOFTWARE + * before sending the packet + */ + HWTSTAMP_TX_ON, + }; + + /* possible values for hwtstamp_config->rx_filter */ + enum { + /* time stamp no incoming packet at all */ + HWTSTAMP_FILTER_NONE, + + /* time stamp any incoming packet */ + HWTSTAMP_FILTER_ALL, + + /* return value: time stamp all packets requested plus some others */ + HWTSTAMP_FILTER_SOME, + + /* PTP v1, UDP, any kind of event packet */ + HWTSTAMP_FILTER_PTP_V1_L4_EVENT, + + /* for the complete list of values, please check + * the include file include/uapi/linux/net_tstamp.h + */ + }; + +3.1 Hardware Timestamping Implementation: Device Drivers +-------------------------------------------------------- + +A driver which supports hardware time stamping must support the +SIOCSHWTSTAMP ioctl and update the supplied struct hwtstamp_config with +the actual values as described in the section on SIOCSHWTSTAMP. It +should also support SIOCGHWTSTAMP. + +Time stamps for received packets must be stored in the skb. To get a pointer +to the shared time stamp structure of the skb call skb_hwtstamps(). Then +set the time stamps in the structure:: + + struct skb_shared_hwtstamps { + /* hardware time stamp transformed into duration + * since arbitrary point in time + */ + ktime_t hwtstamp; + }; + +Time stamps for outgoing packets are to be generated as follows: + +- In hard_start_xmit(), check if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) + is set no-zero. If yes, then the driver is expected to do hardware time + stamping. +- If this is possible for the skb and requested, then declare + that the driver is doing the time stamping by setting the flag + SKBTX_IN_PROGRESS in skb_shinfo(skb)->tx_flags , e.g. with:: + + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + + You might want to keep a pointer to the associated skb for the next step + and not free the skb. A driver not supporting hardware time stamping doesn't + do that. A driver must never touch sk_buff::tstamp! It is used to store + software generated time stamps by the network subsystem. +- Driver should call skb_tx_timestamp() as close to passing sk_buff to hardware + as possible. skb_tx_timestamp() provides a software time stamp if requested + and hardware timestamping is not possible (SKBTX_IN_PROGRESS not set). +- As soon as the driver has sent the packet and/or obtained a + hardware time stamp for it, it passes the time stamp back by + calling skb_hwtstamp_tx() with the original skb, the raw + hardware time stamp. skb_hwtstamp_tx() clones the original skb and + adds the timestamps, therefore the original skb has to be freed now. + If obtaining the hardware time stamp somehow fails, then the driver + should not fall back to software time stamping. The rationale is that + this would occur at a later time in the processing pipeline than other + software time stamping and therefore could lead to unexpected deltas + between time stamps. diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt deleted file mode 100644 index 8dd6333c3270..000000000000 --- a/Documentation/networking/timestamping.txt +++ /dev/null @@ -1,571 +0,0 @@ - -1. Control Interfaces - -The interfaces for receiving network packages timestamps are: - -* SO_TIMESTAMP - Generates a timestamp for each incoming packet in (not necessarily - monotonic) system time. Reports the timestamp via recvmsg() in a - control message in usec resolution. - SO_TIMESTAMP is defined as SO_TIMESTAMP_NEW or SO_TIMESTAMP_OLD - based on the architecture type and time_t representation of libc. - Control message format is in struct __kernel_old_timeval for - SO_TIMESTAMP_OLD and in struct __kernel_sock_timeval for - SO_TIMESTAMP_NEW options respectively. - -* SO_TIMESTAMPNS - Same timestamping mechanism as SO_TIMESTAMP, but reports the - timestamp as struct timespec in nsec resolution. - SO_TIMESTAMPNS is defined as SO_TIMESTAMPNS_NEW or SO_TIMESTAMPNS_OLD - based on the architecture type and time_t representation of libc. - Control message format is in struct timespec for SO_TIMESTAMPNS_OLD - and in struct __kernel_timespec for SO_TIMESTAMPNS_NEW options - respectively. - -* IP_MULTICAST_LOOP + SO_TIMESTAMP[NS] - Only for multicast:approximate transmit timestamp obtained by - reading the looped packet receive timestamp. - -* SO_TIMESTAMPING - Generates timestamps on reception, transmission or both. Supports - multiple timestamp sources, including hardware. Supports generating - timestamps for stream sockets. - - -1.1 SO_TIMESTAMP (also SO_TIMESTAMP_OLD and SO_TIMESTAMP_NEW): - -This socket option enables timestamping of datagrams on the reception -path. Because the destination socket, if any, is not known early in -the network stack, the feature has to be enabled for all packets. The -same is true for all early receive timestamp options. - -For interface details, see `man 7 socket`. - -Always use SO_TIMESTAMP_NEW timestamp to always get timestamp in -struct __kernel_sock_timeval format. - -SO_TIMESTAMP_OLD returns incorrect timestamps after the year 2038 -on 32 bit machines. - -1.2 SO_TIMESTAMPNS (also SO_TIMESTAMPNS_OLD and SO_TIMESTAMPNS_NEW): - -This option is identical to SO_TIMESTAMP except for the returned data type. -Its struct timespec allows for higher resolution (ns) timestamps than the -timeval of SO_TIMESTAMP (ms). - -Always use SO_TIMESTAMPNS_NEW timestamp to always get timestamp in -struct __kernel_timespec format. - -SO_TIMESTAMPNS_OLD returns incorrect timestamps after the year 2038 -on 32 bit machines. - -1.3 SO_TIMESTAMPING (also SO_TIMESTAMPING_OLD and SO_TIMESTAMPING_NEW): - -Supports multiple types of timestamp requests. As a result, this -socket option takes a bitmap of flags, not a boolean. In - - err = setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, &val, sizeof(val)); - -val is an integer with any of the following bits set. Setting other -bit returns EINVAL and does not change the current state. - -The socket option configures timestamp generation for individual -sk_buffs (1.3.1), timestamp reporting to the socket's error -queue (1.3.2) and options (1.3.3). Timestamp generation can also -be enabled for individual sendmsg calls using cmsg (1.3.4). - - -1.3.1 Timestamp Generation - -Some bits are requests to the stack to try to generate timestamps. Any -combination of them is valid. Changes to these bits apply to newly -created packets, not to packets already in the stack. As a result, it -is possible to selectively request timestamps for a subset of packets -(e.g., for sampling) by embedding an send() call within two setsockopt -calls, one to enable timestamp generation and one to disable it. -Timestamps may also be generated for reasons other than being -requested by a particular socket, such as when receive timestamping is -enabled system wide, as explained earlier. - -SOF_TIMESTAMPING_RX_HARDWARE: - Request rx timestamps generated by the network adapter. - -SOF_TIMESTAMPING_RX_SOFTWARE: - Request rx timestamps when data enters the kernel. These timestamps - are generated just after a device driver hands a packet to the - kernel receive stack. - -SOF_TIMESTAMPING_TX_HARDWARE: - Request tx timestamps generated by the network adapter. This flag - can be enabled via both socket options and control messages. - -SOF_TIMESTAMPING_TX_SOFTWARE: - Request tx timestamps when data leaves the kernel. These timestamps - are generated in the device driver as close as possible, but always - prior to, passing the packet to the network interface. Hence, they - require driver support and may not be available for all devices. - This flag can be enabled via both socket options and control messages. - - -SOF_TIMESTAMPING_TX_SCHED: - Request tx timestamps prior to entering the packet scheduler. Kernel - transmit latency is, if long, often dominated by queuing delay. The - difference between this timestamp and one taken at - SOF_TIMESTAMPING_TX_SOFTWARE will expose this latency independent - of protocol processing. The latency incurred in protocol - processing, if any, can be computed by subtracting a userspace - timestamp taken immediately before send() from this timestamp. On - machines with virtual devices where a transmitted packet travels - through multiple devices and, hence, multiple packet schedulers, - a timestamp is generated at each layer. This allows for fine - grained measurement of queuing delay. This flag can be enabled - via both socket options and control messages. - -SOF_TIMESTAMPING_TX_ACK: - Request tx timestamps when all data in the send buffer has been - acknowledged. This only makes sense for reliable protocols. It is - currently only implemented for TCP. For that protocol, it may - over-report measurement, because the timestamp is generated when all - data up to and including the buffer at send() was acknowledged: the - cumulative acknowledgment. The mechanism ignores SACK and FACK. - This flag can be enabled via both socket options and control messages. - - -1.3.2 Timestamp Reporting - -The other three bits control which timestamps will be reported in a -generated control message. Changes to the bits take immediate -effect at the timestamp reporting locations in the stack. Timestamps -are only reported for packets that also have the relevant timestamp -generation request set. - -SOF_TIMESTAMPING_SOFTWARE: - Report any software timestamps when available. - -SOF_TIMESTAMPING_SYS_HARDWARE: - This option is deprecated and ignored. - -SOF_TIMESTAMPING_RAW_HARDWARE: - Report hardware timestamps as generated by - SOF_TIMESTAMPING_TX_HARDWARE when available. - - -1.3.3 Timestamp Options - -The interface supports the options - -SOF_TIMESTAMPING_OPT_ID: - - Generate a unique identifier along with each packet. A process can - have multiple concurrent timestamping requests outstanding. Packets - can be reordered in the transmit path, for instance in the packet - scheduler. In that case timestamps will be queued onto the error - queue out of order from the original send() calls. It is not always - possible to uniquely match timestamps to the original send() calls - based on timestamp order or payload inspection alone, then. - - This option associates each packet at send() with a unique - identifier and returns that along with the timestamp. The identifier - is derived from a per-socket u32 counter (that wraps). For datagram - sockets, the counter increments with each sent packet. For stream - sockets, it increments with every byte. - - The counter starts at zero. It is initialized the first time that - the socket option is enabled. It is reset each time the option is - enabled after having been disabled. Resetting the counter does not - change the identifiers of existing packets in the system. - - This option is implemented only for transmit timestamps. There, the - timestamp is always looped along with a struct sock_extended_err. - The option modifies field ee_data to pass an id that is unique - among all possibly concurrently outstanding timestamp requests for - that socket. - - -SOF_TIMESTAMPING_OPT_CMSG: - - Support recv() cmsg for all timestamped packets. Control messages - are already supported unconditionally on all packets with receive - timestamps and on IPv6 packets with transmit timestamp. This option - extends them to IPv4 packets with transmit timestamp. One use case - is to correlate packets with their egress device, by enabling socket - option IP_PKTINFO simultaneously. - - -SOF_TIMESTAMPING_OPT_TSONLY: - - Applies to transmit timestamps only. Makes the kernel return the - timestamp as a cmsg alongside an empty packet, as opposed to - alongside the original packet. This reduces the amount of memory - charged to the socket's receive budget (SO_RCVBUF) and delivers - the timestamp even if sysctl net.core.tstamp_allow_data is 0. - This option disables SOF_TIMESTAMPING_OPT_CMSG. - -SOF_TIMESTAMPING_OPT_STATS: - - Optional stats that are obtained along with the transmit timestamps. - It must be used together with SOF_TIMESTAMPING_OPT_TSONLY. When the - transmit timestamp is available, the stats are available in a - separate control message of type SCM_TIMESTAMPING_OPT_STATS, as a - list of TLVs (struct nlattr) of types. These stats allow the - application to associate various transport layer stats with - the transmit timestamps, such as how long a certain block of - data was limited by peer's receiver window. - -SOF_TIMESTAMPING_OPT_PKTINFO: - - Enable the SCM_TIMESTAMPING_PKTINFO control message for incoming - packets with hardware timestamps. The message contains struct - scm_ts_pktinfo, which supplies the index of the real interface which - received the packet and its length at layer 2. A valid (non-zero) - interface index will be returned only if CONFIG_NET_RX_BUSY_POLL is - enabled and the driver is using NAPI. The struct contains also two - other fields, but they are reserved and undefined. - -SOF_TIMESTAMPING_OPT_TX_SWHW: - - Request both hardware and software timestamps for outgoing packets - when SOF_TIMESTAMPING_TX_HARDWARE and SOF_TIMESTAMPING_TX_SOFTWARE - are enabled at the same time. If both timestamps are generated, - two separate messages will be looped to the socket's error queue, - each containing just one timestamp. - -New applications are encouraged to pass SOF_TIMESTAMPING_OPT_ID to -disambiguate timestamps and SOF_TIMESTAMPING_OPT_TSONLY to operate -regardless of the setting of sysctl net.core.tstamp_allow_data. - -An exception is when a process needs additional cmsg data, for -instance SOL_IP/IP_PKTINFO to detect the egress network interface. -Then pass option SOF_TIMESTAMPING_OPT_CMSG. This option depends on -having access to the contents of the original packet, so cannot be -combined with SOF_TIMESTAMPING_OPT_TSONLY. - - -1.3.4. Enabling timestamps via control messages - -In addition to socket options, timestamp generation can be requested -per write via cmsg, only for SOF_TIMESTAMPING_TX_* (see Section 1.3.1). -Using this feature, applications can sample timestamps per sendmsg() -without paying the overhead of enabling and disabling timestamps via -setsockopt: - - struct msghdr *msg; - ... - cmsg = CMSG_FIRSTHDR(msg); - cmsg->cmsg_level = SOL_SOCKET; - cmsg->cmsg_type = SO_TIMESTAMPING; - cmsg->cmsg_len = CMSG_LEN(sizeof(__u32)); - *((__u32 *) CMSG_DATA(cmsg)) = SOF_TIMESTAMPING_TX_SCHED | - SOF_TIMESTAMPING_TX_SOFTWARE | - SOF_TIMESTAMPING_TX_ACK; - err = sendmsg(fd, msg, 0); - -The SOF_TIMESTAMPING_TX_* flags set via cmsg will override -the SOF_TIMESTAMPING_TX_* flags set via setsockopt. - -Moreover, applications must still enable timestamp reporting via -setsockopt to receive timestamps: - - __u32 val = SOF_TIMESTAMPING_SOFTWARE | - SOF_TIMESTAMPING_OPT_ID /* or any other flag */; - err = setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, &val, sizeof(val)); - - -1.4 Bytestream Timestamps - -The SO_TIMESTAMPING interface supports timestamping of bytes in a -bytestream. Each request is interpreted as a request for when the -entire contents of the buffer has passed a timestamping point. That -is, for streams option SOF_TIMESTAMPING_TX_SOFTWARE will record -when all bytes have reached the device driver, regardless of how -many packets the data has been converted into. - -In general, bytestreams have no natural delimiters and therefore -correlating a timestamp with data is non-trivial. A range of bytes -may be split across segments, any segments may be merged (possibly -coalescing sections of previously segmented buffers associated with -independent send() calls). Segments can be reordered and the same -byte range can coexist in multiple segments for protocols that -implement retransmissions. - -It is essential that all timestamps implement the same semantics, -regardless of these possible transformations, as otherwise they are -incomparable. Handling "rare" corner cases differently from the -simple case (a 1:1 mapping from buffer to skb) is insufficient -because performance debugging often needs to focus on such outliers. - -In practice, timestamps can be correlated with segments of a -bytestream consistently, if both semantics of the timestamp and the -timing of measurement are chosen correctly. This challenge is no -different from deciding on a strategy for IP fragmentation. There, the -definition is that only the first fragment is timestamped. For -bytestreams, we chose that a timestamp is generated only when all -bytes have passed a point. SOF_TIMESTAMPING_TX_ACK as defined is easy to -implement and reason about. An implementation that has to take into -account SACK would be more complex due to possible transmission holes -and out of order arrival. - -On the host, TCP can also break the simple 1:1 mapping from buffer to -skbuff as a result of Nagle, cork, autocork, segmentation and GSO. The -implementation ensures correctness in all cases by tracking the -individual last byte passed to send(), even if it is no longer the -last byte after an skbuff extend or merge operation. It stores the -relevant sequence number in skb_shinfo(skb)->tskey. Because an skbuff -has only one such field, only one timestamp can be generated. - -In rare cases, a timestamp request can be missed if two requests are -collapsed onto the same skb. A process can detect this situation by -enabling SOF_TIMESTAMPING_OPT_ID and comparing the byte offset at -send time with the value returned for each timestamp. It can prevent -the situation by always flushing the TCP stack in between requests, -for instance by enabling TCP_NODELAY and disabling TCP_CORK and -autocork. - -These precautions ensure that the timestamp is generated only when all -bytes have passed a timestamp point, assuming that the network stack -itself does not reorder the segments. The stack indeed tries to avoid -reordering. The one exception is under administrator control: it is -possible to construct a packet scheduler configuration that delays -segments from the same stream differently. Such a setup would be -unusual. - - -2 Data Interfaces - -Timestamps are read using the ancillary data feature of recvmsg(). -See `man 3 cmsg` for details of this interface. The socket manual -page (`man 7 socket`) describes how timestamps generated with -SO_TIMESTAMP and SO_TIMESTAMPNS records can be retrieved. - - -2.1 SCM_TIMESTAMPING records - -These timestamps are returned in a control message with cmsg_level -SOL_SOCKET, cmsg_type SCM_TIMESTAMPING, and payload of type - -For SO_TIMESTAMPING_OLD: - -struct scm_timestamping { - struct timespec ts[3]; -}; - -For SO_TIMESTAMPING_NEW: - -struct scm_timestamping64 { - struct __kernel_timespec ts[3]; - -Always use SO_TIMESTAMPING_NEW timestamp to always get timestamp in -struct scm_timestamping64 format. - -SO_TIMESTAMPING_OLD returns incorrect timestamps after the year 2038 -on 32 bit machines. - -The structure can return up to three timestamps. This is a legacy -feature. At least one field is non-zero at any time. Most timestamps -are passed in ts[0]. Hardware timestamps are passed in ts[2]. - -ts[1] used to hold hardware timestamps converted to system time. -Instead, expose the hardware clock device on the NIC directly as -a HW PTP clock source, to allow time conversion in userspace and -optionally synchronize system time with a userspace PTP stack such -as linuxptp. For the PTP clock API, see Documentation/driver-api/ptp.rst. - -Note that if the SO_TIMESTAMP or SO_TIMESTAMPNS option is enabled -together with SO_TIMESTAMPING using SOF_TIMESTAMPING_SOFTWARE, a false -software timestamp will be generated in the recvmsg() call and passed -in ts[0] when a real software timestamp is missing. This happens also -on hardware transmit timestamps. - -2.1.1 Transmit timestamps with MSG_ERRQUEUE - -For transmit timestamps the outgoing packet is looped back to the -socket's error queue with the send timestamp(s) attached. A process -receives the timestamps by calling recvmsg() with flag MSG_ERRQUEUE -set and with a msg_control buffer sufficiently large to receive the -relevant metadata structures. The recvmsg call returns the original -outgoing data packet with two ancillary messages attached. - -A message of cm_level SOL_IP(V6) and cm_type IP(V6)_RECVERR -embeds a struct sock_extended_err. This defines the error type. For -timestamps, the ee_errno field is ENOMSG. The other ancillary message -will have cm_level SOL_SOCKET and cm_type SCM_TIMESTAMPING. This -embeds the struct scm_timestamping. - - -2.1.1.2 Timestamp types - -The semantics of the three struct timespec are defined by field -ee_info in the extended error structure. It contains a value of -type SCM_TSTAMP_* to define the actual timestamp passed in -scm_timestamping. - -The SCM_TSTAMP_* types are 1:1 matches to the SOF_TIMESTAMPING_* -control fields discussed previously, with one exception. For legacy -reasons, SCM_TSTAMP_SND is equal to zero and can be set for both -SOF_TIMESTAMPING_TX_HARDWARE and SOF_TIMESTAMPING_TX_SOFTWARE. It -is the first if ts[2] is non-zero, the second otherwise, in which -case the timestamp is stored in ts[0]. - - -2.1.1.3 Fragmentation - -Fragmentation of outgoing datagrams is rare, but is possible, e.g., by -explicitly disabling PMTU discovery. If an outgoing packet is fragmented, -then only the first fragment is timestamped and returned to the sending -socket. - - -2.1.1.4 Packet Payload - -The calling application is often not interested in receiving the whole -packet payload that it passed to the stack originally: the socket -error queue mechanism is just a method to piggyback the timestamp on. -In this case, the application can choose to read datagrams with a -smaller buffer, possibly even of length 0. The payload is truncated -accordingly. Until the process calls recvmsg() on the error queue, -however, the full packet is queued, taking up budget from SO_RCVBUF. - - -2.1.1.5 Blocking Read - -Reading from the error queue is always a non-blocking operation. To -block waiting on a timestamp, use poll or select. poll() will return -POLLERR in pollfd.revents if any data is ready on the error queue. -There is no need to pass this flag in pollfd.events. This flag is -ignored on request. See also `man 2 poll`. - - -2.1.2 Receive timestamps - -On reception, there is no reason to read from the socket error queue. -The SCM_TIMESTAMPING ancillary data is sent along with the packet data -on a normal recvmsg(). Since this is not a socket error, it is not -accompanied by a message SOL_IP(V6)/IP(V6)_RECVERROR. In this case, -the meaning of the three fields in struct scm_timestamping is -implicitly defined. ts[0] holds a software timestamp if set, ts[1] -is again deprecated and ts[2] holds a hardware timestamp if set. - - -3. Hardware Timestamping configuration: SIOCSHWTSTAMP and SIOCGHWTSTAMP - -Hardware time stamping must also be initialized for each device driver -that is expected to do hardware time stamping. The parameter is defined in -include/uapi/linux/net_tstamp.h as: - -struct hwtstamp_config { - int flags; /* no flags defined right now, must be zero */ - int tx_type; /* HWTSTAMP_TX_* */ - int rx_filter; /* HWTSTAMP_FILTER_* */ -}; - -Desired behavior is passed into the kernel and to a specific device by -calling ioctl(SIOCSHWTSTAMP) with a pointer to a struct ifreq whose -ifr_data points to a struct hwtstamp_config. The tx_type and -rx_filter are hints to the driver what it is expected to do. If -the requested fine-grained filtering for incoming packets is not -supported, the driver may time stamp more than just the requested types -of packets. - -Drivers are free to use a more permissive configuration than the requested -configuration. It is expected that drivers should only implement directly the -most generic mode that can be supported. For example if the hardware can -support HWTSTAMP_FILTER_V2_EVENT, then it should generally always upscale -HWTSTAMP_FILTER_V2_L2_SYNC_MESSAGE, and so forth, as HWTSTAMP_FILTER_V2_EVENT -is more generic (and more useful to applications). - -A driver which supports hardware time stamping shall update the struct -with the actual, possibly more permissive configuration. If the -requested packets cannot be time stamped, then nothing should be -changed and ERANGE shall be returned (in contrast to EINVAL, which -indicates that SIOCSHWTSTAMP is not supported at all). - -Only a processes with admin rights may change the configuration. User -space is responsible to ensure that multiple processes don't interfere -with each other and that the settings are reset. - -Any process can read the actual configuration by passing this -structure to ioctl(SIOCGHWTSTAMP) in the same way. However, this has -not been implemented in all drivers. - -/* possible values for hwtstamp_config->tx_type */ -enum { - /* - * no outgoing packet will need hardware time stamping; - * should a packet arrive which asks for it, no hardware - * time stamping will be done - */ - HWTSTAMP_TX_OFF, - - /* - * enables hardware time stamping for outgoing packets; - * the sender of the packet decides which are to be - * time stamped by setting SOF_TIMESTAMPING_TX_SOFTWARE - * before sending the packet - */ - HWTSTAMP_TX_ON, -}; - -/* possible values for hwtstamp_config->rx_filter */ -enum { - /* time stamp no incoming packet at all */ - HWTSTAMP_FILTER_NONE, - - /* time stamp any incoming packet */ - HWTSTAMP_FILTER_ALL, - - /* return value: time stamp all packets requested plus some others */ - HWTSTAMP_FILTER_SOME, - - /* PTP v1, UDP, any kind of event packet */ - HWTSTAMP_FILTER_PTP_V1_L4_EVENT, - - /* for the complete list of values, please check - * the include file include/uapi/linux/net_tstamp.h - */ -}; - -3.1 Hardware Timestamping Implementation: Device Drivers - -A driver which supports hardware time stamping must support the -SIOCSHWTSTAMP ioctl and update the supplied struct hwtstamp_config with -the actual values as described in the section on SIOCSHWTSTAMP. It -should also support SIOCGHWTSTAMP. - -Time stamps for received packets must be stored in the skb. To get a pointer -to the shared time stamp structure of the skb call skb_hwtstamps(). Then -set the time stamps in the structure: - -struct skb_shared_hwtstamps { - /* hardware time stamp transformed into duration - * since arbitrary point in time - */ - ktime_t hwtstamp; -}; - -Time stamps for outgoing packets are to be generated as follows: -- In hard_start_xmit(), check if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) - is set no-zero. If yes, then the driver is expected to do hardware time - stamping. -- If this is possible for the skb and requested, then declare - that the driver is doing the time stamping by setting the flag - SKBTX_IN_PROGRESS in skb_shinfo(skb)->tx_flags , e.g. with - - skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - - You might want to keep a pointer to the associated skb for the next step - and not free the skb. A driver not supporting hardware time stamping doesn't - do that. A driver must never touch sk_buff::tstamp! It is used to store - software generated time stamps by the network subsystem. -- Driver should call skb_tx_timestamp() as close to passing sk_buff to hardware - as possible. skb_tx_timestamp() provides a software time stamp if requested - and hardware timestamping is not possible (SKBTX_IN_PROGRESS not set). -- As soon as the driver has sent the packet and/or obtained a - hardware time stamp for it, it passes the time stamp back by - calling skb_hwtstamp_tx() with the original skb, the raw - hardware time stamp. skb_hwtstamp_tx() clones the original skb and - adds the timestamps, therefore the original skb has to be freed now. - If obtaining the hardware time stamp somehow fails, then the driver - should not fall back to software time stamping. The rationale is that - this would occur at a later time in the processing pipeline than other - software time stamping and therefore could lead to unexpected deltas - between time stamps. diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h index 0cca19670fd2..ca5cb3e3c6df 100644 --- a/include/uapi/linux/errqueue.h +++ b/include/uapi/linux/errqueue.h @@ -36,7 +36,7 @@ struct sock_extended_err { * * The timestamping interfaces SO_TIMESTAMPING, MSG_TSTAMP_* * communicate network timestamps by passing this struct in a cmsg with - * recvmsg(). See Documentation/networking/timestamping.txt for details. + * recvmsg(). See Documentation/networking/timestamping.rst for details. * User space sees a timespec definition that matches either * __kernel_timespec or __kernel_old_timespec, in the kernel we * require two structure definitions to provide both. -- cgit v1.2.3 From d07dcf9aadd6b2842b439e8668ff7ea2873f28d7 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 30 Apr 2020 22:13:12 +0200 Subject: netlink: add infrastructure to expose policies to userspace Add, and use in generic netlink, helpers to dump out a netlink policy to userspace, including all the range validation data, nested policies etc. This lets userspace discover what the kernel understands. For families/commands other than generic netlink, the helpers need to be used directly in an appropriate command, or we can add some infrastructure (a new netlink family) that those can register their policies with for introspection. I'm not that familiar with non-generic netlink, so that's left out for now. The data exposed to userspace also includes min and max length for binary/string data, I've done that instead of letting the userspace tools figure out whether min/max is intended based on the type so that we can extend this later in the kernel, we might want to just use the range data for example. Because of this, I opted to not directly expose the NLA_* values, even if some of them are already exposed via BPF, as with min/max length we don't need to have different types here for NLA_BINARY/NLA_MIN_LEN/NLA_EXACT_LEN, we just make them all NL_ATTR_TYPE_BINARY with min/max length optionally set. Similarly, we don't really need NLA_MSECS, and perhaps can remove it in the future - but not if we encode it into the userspace API now. It gets mapped to NL_ATTR_TYPE_U64 here. Note that the exposing here corresponds to the strict policy interpretation, and NLA_UNSPEC items are omitted entirely. To get those, change them to NLA_MIN_LEN which behaves in exactly the same way, but is exposed. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/net/netlink.h | 6 + include/uapi/linux/genetlink.h | 2 + include/uapi/linux/netlink.h | 103 ++++++++++++++ net/netlink/Makefile | 2 +- net/netlink/genetlink.c | 78 +++++++++++ net/netlink/policy.c | 308 +++++++++++++++++++++++++++++++++++++++++ 6 files changed, 498 insertions(+), 1 deletion(-) create mode 100644 net/netlink/policy.c (limited to 'include/uapi/linux') diff --git a/include/net/netlink.h b/include/net/netlink.h index 557b67f1db99..c0411f14fb53 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1933,4 +1933,10 @@ void nla_get_range_unsigned(const struct nla_policy *pt, void nla_get_range_signed(const struct nla_policy *pt, struct netlink_range_validation_signed *range); +int netlink_policy_dump_start(const struct nla_policy *policy, + unsigned int maxtype, + unsigned long *state); +bool netlink_policy_dump_loop(unsigned long *state); +int netlink_policy_dump_write(struct sk_buff *skb, unsigned long state); + #endif diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h index 877f7fa95466..9c0636ec2286 100644 --- a/include/uapi/linux/genetlink.h +++ b/include/uapi/linux/genetlink.h @@ -48,6 +48,7 @@ enum { CTRL_CMD_NEWMCAST_GRP, CTRL_CMD_DELMCAST_GRP, CTRL_CMD_GETMCAST_GRP, /* unused */ + CTRL_CMD_GETPOLICY, __CTRL_CMD_MAX, }; @@ -62,6 +63,7 @@ enum { CTRL_ATTR_MAXATTR, CTRL_ATTR_OPS, CTRL_ATTR_MCAST_GROUPS, + CTRL_ATTR_POLICY, __CTRL_ATTR_MAX, }; diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 0a4d73317759..eac8a6a648ea 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -249,4 +249,107 @@ struct nla_bitfield32 { __u32 selector; }; +/* + * policy descriptions - it's specific to each family how this is used + * Normally, it should be retrieved via a dump inside another attribute + * specifying where it applies. + */ + +/** + * enum netlink_attribute_type - type of an attribute + * @NL_ATTR_TYPE_INVALID: unused + * @NL_ATTR_TYPE_FLAG: flag attribute (present/not present) + * @NL_ATTR_TYPE_U8: 8-bit unsigned attribute + * @NL_ATTR_TYPE_U16: 16-bit unsigned attribute + * @NL_ATTR_TYPE_U32: 32-bit unsigned attribute + * @NL_ATTR_TYPE_U64: 64-bit unsigned attribute + * @NL_ATTR_TYPE_S8: 8-bit signed attribute + * @NL_ATTR_TYPE_S16: 16-bit signed attribute + * @NL_ATTR_TYPE_S32: 32-bit signed attribute + * @NL_ATTR_TYPE_S64: 64-bit signed attribute + * @NL_ATTR_TYPE_BINARY: binary data, min/max length may be specified + * @NL_ATTR_TYPE_STRING: string, min/max length may be specified + * @NL_ATTR_TYPE_NUL_STRING: NUL-terminated string, + * min/max length may be specified + * @NL_ATTR_TYPE_NESTED: nested, i.e. the content of this attribute + * consists of sub-attributes. The nested policy and maxtype + * inside may be specified. + * @NL_ATTR_TYPE_NESTED_ARRAY: nested array, i.e. the content of this + * attribute contains sub-attributes whose type is irrelevant + * (just used to separate the array entries) and each such array + * entry has attributes again, the policy for those inner ones + * and the corresponding maxtype may be specified. + * @NL_ATTR_TYPE_BITFIELD32: &struct nla_bitfield32 attribute + */ +enum netlink_attribute_type { + NL_ATTR_TYPE_INVALID, + + NL_ATTR_TYPE_FLAG, + + NL_ATTR_TYPE_U8, + NL_ATTR_TYPE_U16, + NL_ATTR_TYPE_U32, + NL_ATTR_TYPE_U64, + + NL_ATTR_TYPE_S8, + NL_ATTR_TYPE_S16, + NL_ATTR_TYPE_S32, + NL_ATTR_TYPE_S64, + + NL_ATTR_TYPE_BINARY, + NL_ATTR_TYPE_STRING, + NL_ATTR_TYPE_NUL_STRING, + + NL_ATTR_TYPE_NESTED, + NL_ATTR_TYPE_NESTED_ARRAY, + + NL_ATTR_TYPE_BITFIELD32, +}; + +/** + * enum netlink_policy_type_attr - policy type attributes + * @NL_POLICY_TYPE_ATTR_UNSPEC: unused + * @NL_POLICY_TYPE_ATTR_TYPE: type of the attribute, + * &enum netlink_attribute_type (U32) + * @NL_POLICY_TYPE_ATTR_MIN_VALUE_S: minimum value for signed + * integers (S64) + * @NL_POLICY_TYPE_ATTR_MAX_VALUE_S: maximum value for signed + * integers (S64) + * @NL_POLICY_TYPE_ATTR_MIN_VALUE_U: minimum value for unsigned + * integers (U64) + * @NL_POLICY_TYPE_ATTR_MAX_VALUE_U: maximum value for unsigned + * integers (U64) + * @NL_POLICY_TYPE_ATTR_MIN_LENGTH: minimum length for binary + * attributes, no minimum if not given (U32) + * @NL_POLICY_TYPE_ATTR_MAX_LENGTH: maximum length for binary + * attributes, no maximum if not given (U32) + * @NL_POLICY_TYPE_ATTR_POLICY_IDX: sub policy for nested and + * nested array types (U32) + * @NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE: maximum sub policy + * attribute for nested and nested array types, this can + * in theory be < the size of the policy pointed to by + * the index, if limited inside the nesting (U32) + * @NL_POLICY_TYPE_ATTR_BITFIELD32_MASK: valid mask for the + * bitfield32 type (U32) + * @NL_POLICY_TYPE_ATTR_PAD: pad attribute for 64-bit alignment + */ +enum netlink_policy_type_attr { + NL_POLICY_TYPE_ATTR_UNSPEC, + NL_POLICY_TYPE_ATTR_TYPE, + NL_POLICY_TYPE_ATTR_MIN_VALUE_S, + NL_POLICY_TYPE_ATTR_MAX_VALUE_S, + NL_POLICY_TYPE_ATTR_MIN_VALUE_U, + NL_POLICY_TYPE_ATTR_MAX_VALUE_U, + NL_POLICY_TYPE_ATTR_MIN_LENGTH, + NL_POLICY_TYPE_ATTR_MAX_LENGTH, + NL_POLICY_TYPE_ATTR_POLICY_IDX, + NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE, + NL_POLICY_TYPE_ATTR_BITFIELD32_MASK, + NL_POLICY_TYPE_ATTR_PAD, + + /* keep last */ + __NL_POLICY_TYPE_ATTR_MAX, + NL_POLICY_TYPE_ATTR_MAX = __NL_POLICY_TYPE_ATTR_MAX - 1 +}; + #endif /* _UAPI__LINUX_NETLINK_H */ diff --git a/net/netlink/Makefile b/net/netlink/Makefile index de42df7f0068..e05202708c90 100644 --- a/net/netlink/Makefile +++ b/net/netlink/Makefile @@ -3,7 +3,7 @@ # Makefile for the netlink driver. # -obj-y := af_netlink.o genetlink.o +obj-y := af_netlink.o genetlink.o policy.o obj-$(CONFIG_NETLINK_DIAG) += netlink_diag.o netlink_diag-y := diag.o diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 9f357aa22b94..2f049692e012 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1043,6 +1043,80 @@ static int genl_ctrl_event(int event, const struct genl_family *family, return 0; } +static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct genl_family *rt; + unsigned int fam_id = cb->args[0]; + int err; + + if (!fam_id) { + struct nlattr *tb[CTRL_ATTR_MAX + 1]; + + err = genlmsg_parse(cb->nlh, &genl_ctrl, tb, + genl_ctrl.maxattr, + genl_ctrl.policy, cb->extack); + if (err) + return err; + + if (!tb[CTRL_ATTR_FAMILY_ID] && !tb[CTRL_ATTR_FAMILY_NAME]) + return -EINVAL; + + if (tb[CTRL_ATTR_FAMILY_ID]) { + fam_id = nla_get_u16(tb[CTRL_ATTR_FAMILY_ID]); + } else { + rt = genl_family_find_byname( + nla_data(tb[CTRL_ATTR_FAMILY_NAME])); + if (!rt) + return -ENOENT; + fam_id = rt->id; + } + } + + rt = genl_family_find_byid(fam_id); + if (!rt) + return -ENOENT; + + if (!rt->policy) + return -ENODATA; + + err = netlink_policy_dump_start(rt->policy, rt->maxattr, &cb->args[1]); + if (err) + return err; + + while (netlink_policy_dump_loop(&cb->args[1])) { + void *hdr; + struct nlattr *nest; + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &genl_ctrl, + NLM_F_MULTI, CTRL_CMD_GETPOLICY); + if (!hdr) + goto nla_put_failure; + + if (nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, rt->id)) + goto nla_put_failure; + + nest = nla_nest_start(skb, CTRL_ATTR_POLICY); + if (!nest) + goto nla_put_failure; + + if (netlink_policy_dump_write(skb, cb->args[1])) + goto nla_put_failure; + + nla_nest_end(skb, nest); + + genlmsg_end(skb, hdr); + continue; + +nla_put_failure: + genlmsg_cancel(skb, hdr); + break; + } + + cb->args[0] = fam_id; + return skb->len; +} + static const struct genl_ops genl_ctrl_ops[] = { { .cmd = CTRL_CMD_GETFAMILY, @@ -1050,6 +1124,10 @@ static const struct genl_ops genl_ctrl_ops[] = { .doit = ctrl_getfamily, .dumpit = ctrl_dumpfamily, }, + { + .cmd = CTRL_CMD_GETPOLICY, + .dumpit = ctrl_dumppolicy, + }, }; static const struct genl_multicast_group genl_ctrl_groups[] = { diff --git a/net/netlink/policy.c b/net/netlink/policy.c new file mode 100644 index 000000000000..f6491853c797 --- /dev/null +++ b/net/netlink/policy.c @@ -0,0 +1,308 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NETLINK Policy advertisement to userspace + * + * Authors: Johannes Berg + * + * Copyright 2019 Intel Corporation + */ + +#include +#include +#include +#include + +#define INITIAL_POLICIES_ALLOC 10 + +struct nl_policy_dump { + unsigned int policy_idx; + unsigned int attr_idx; + unsigned int n_alloc; + struct { + const struct nla_policy *policy; + unsigned int maxtype; + } policies[]; +}; + +static int add_policy(struct nl_policy_dump **statep, + const struct nla_policy *policy, + unsigned int maxtype) +{ + struct nl_policy_dump *state = *statep; + unsigned int n_alloc, i; + + if (!policy || !maxtype) + return 0; + + for (i = 0; i < state->n_alloc; i++) { + if (state->policies[i].policy == policy) + return 0; + + if (!state->policies[i].policy) { + state->policies[i].policy = policy; + state->policies[i].maxtype = maxtype; + return 0; + } + } + + n_alloc = state->n_alloc + INITIAL_POLICIES_ALLOC; + state = krealloc(state, struct_size(state, policies, n_alloc), + GFP_KERNEL); + if (!state) + return -ENOMEM; + + state->policies[state->n_alloc].policy = policy; + state->policies[state->n_alloc].maxtype = maxtype; + state->n_alloc = n_alloc; + *statep = state; + + return 0; +} + +static unsigned int get_policy_idx(struct nl_policy_dump *state, + const struct nla_policy *policy) +{ + unsigned int i; + + for (i = 0; i < state->n_alloc; i++) { + if (state->policies[i].policy == policy) + return i; + } + + WARN_ON_ONCE(1); + return -1; +} + +int netlink_policy_dump_start(const struct nla_policy *policy, + unsigned int maxtype, + unsigned long *_state) +{ + struct nl_policy_dump *state; + unsigned int policy_idx; + int err; + + /* also returns 0 if "*_state" is our ERR_PTR() end marker */ + if (*_state) + return 0; + + /* + * walk the policies and nested ones first, and build + * a linear list of them. + */ + + state = kzalloc(struct_size(state, policies, INITIAL_POLICIES_ALLOC), + GFP_KERNEL); + if (!state) + return -ENOMEM; + state->n_alloc = INITIAL_POLICIES_ALLOC; + + err = add_policy(&state, policy, maxtype); + if (err) + return err; + + for (policy_idx = 0; + policy_idx < state->n_alloc && state->policies[policy_idx].policy; + policy_idx++) { + const struct nla_policy *policy; + unsigned int type; + + policy = state->policies[policy_idx].policy; + + for (type = 0; + type <= state->policies[policy_idx].maxtype; + type++) { + switch (policy[type].type) { + case NLA_NESTED: + case NLA_NESTED_ARRAY: + err = add_policy(&state, + policy[type].nested_policy, + policy[type].len); + if (err) + return err; + break; + default: + break; + } + } + } + + *_state = (unsigned long)state; + + return 0; +} + +static bool netlink_policy_dump_finished(struct nl_policy_dump *state) +{ + return state->policy_idx >= state->n_alloc || + !state->policies[state->policy_idx].policy; +} + +bool netlink_policy_dump_loop(unsigned long *_state) +{ + struct nl_policy_dump *state = (void *)*_state; + + if (IS_ERR(state)) + return false; + + if (netlink_policy_dump_finished(state)) { + kfree(state); + /* store end marker instead of freed state */ + *_state = (unsigned long)ERR_PTR(-ENOENT); + return false; + } + + return true; +} + +int netlink_policy_dump_write(struct sk_buff *skb, unsigned long _state) +{ + struct nl_policy_dump *state = (void *)_state; + const struct nla_policy *pt; + struct nlattr *policy, *attr; + enum netlink_attribute_type type; + bool again; + +send_attribute: + again = false; + + pt = &state->policies[state->policy_idx].policy[state->attr_idx]; + + policy = nla_nest_start(skb, state->policy_idx); + if (!policy) + return -ENOBUFS; + + attr = nla_nest_start(skb, state->attr_idx); + if (!attr) + goto nla_put_failure; + + switch (pt->type) { + default: + case NLA_UNSPEC: + case NLA_REJECT: + /* skip - use NLA_MIN_LEN to advertise such */ + nla_nest_cancel(skb, policy); + again = true; + goto next; + case NLA_NESTED: + type = NL_ATTR_TYPE_NESTED; + /* fall through */ + case NLA_NESTED_ARRAY: + if (pt->type == NLA_NESTED_ARRAY) + type = NL_ATTR_TYPE_NESTED_ARRAY; + if (pt->nested_policy && pt->len && + (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_POLICY_IDX, + get_policy_idx(state, pt->nested_policy)) || + nla_put_u32(skb, NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE, + pt->len))) + goto nla_put_failure; + break; + case NLA_U8: + case NLA_U16: + case NLA_U32: + case NLA_U64: + case NLA_MSECS: { + struct netlink_range_validation range; + + if (pt->type == NLA_U8) + type = NL_ATTR_TYPE_U8; + else if (pt->type == NLA_U16) + type = NL_ATTR_TYPE_U16; + else if (pt->type == NLA_U32) + type = NL_ATTR_TYPE_U32; + else + type = NL_ATTR_TYPE_U64; + + nla_get_range_unsigned(pt, &range); + + if (nla_put_u64_64bit(skb, NL_POLICY_TYPE_ATTR_MIN_VALUE_U, + range.min, NL_POLICY_TYPE_ATTR_PAD) || + nla_put_u64_64bit(skb, NL_POLICY_TYPE_ATTR_MAX_VALUE_U, + range.max, NL_POLICY_TYPE_ATTR_PAD)) + goto nla_put_failure; + break; + } + case NLA_S8: + case NLA_S16: + case NLA_S32: + case NLA_S64: { + struct netlink_range_validation_signed range; + + if (pt->type == NLA_S8) + type = NL_ATTR_TYPE_S8; + else if (pt->type == NLA_S16) + type = NL_ATTR_TYPE_S16; + else if (pt->type == NLA_S32) + type = NL_ATTR_TYPE_S32; + else + type = NL_ATTR_TYPE_S64; + + nla_get_range_signed(pt, &range); + + if (nla_put_s64(skb, NL_POLICY_TYPE_ATTR_MIN_VALUE_S, + range.min, NL_POLICY_TYPE_ATTR_PAD) || + nla_put_s64(skb, NL_POLICY_TYPE_ATTR_MAX_VALUE_S, + range.max, NL_POLICY_TYPE_ATTR_PAD)) + goto nla_put_failure; + break; + } + case NLA_BITFIELD32: + type = NL_ATTR_TYPE_BITFIELD32; + if (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_BITFIELD32_MASK, + pt->bitfield32_valid)) + goto nla_put_failure; + break; + case NLA_EXACT_LEN: + type = NL_ATTR_TYPE_BINARY; + if (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MIN_LENGTH, pt->len) || + nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH, pt->len)) + goto nla_put_failure; + break; + case NLA_STRING: + case NLA_NUL_STRING: + case NLA_BINARY: + if (pt->type == NLA_STRING) + type = NL_ATTR_TYPE_STRING; + else if (pt->type == NLA_NUL_STRING) + type = NL_ATTR_TYPE_NUL_STRING; + else + type = NL_ATTR_TYPE_BINARY; + if (pt->len && nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH, + pt->len)) + goto nla_put_failure; + break; + case NLA_MIN_LEN: + type = NL_ATTR_TYPE_BINARY; + if (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MIN_LENGTH, pt->len)) + goto nla_put_failure; + break; + case NLA_FLAG: + type = NL_ATTR_TYPE_FLAG; + break; + } + + if (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_TYPE, type)) + goto nla_put_failure; + + /* finish and move state to next attribute */ + nla_nest_end(skb, attr); + nla_nest_end(skb, policy); + +next: + state->attr_idx += 1; + if (state->attr_idx > state->policies[state->policy_idx].maxtype) { + state->attr_idx = 0; + state->policy_idx++; + } + + if (again) { + if (netlink_policy_dump_finished(state)) + return -ENODATA; + goto send_attribute; + } + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, policy); + return -ENOBUFS; +} -- cgit v1.2.3 From 0aeaaf64e6d06e353de15dcf9973312ae0672ca1 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Wed, 29 Apr 2020 19:36:06 -0400 Subject: drm/amdkfd: Fix comment formatting Corrected two function names. Added a missing space. Signed-off-by: Felix Kuehling Reviewed-by: Kent Russell Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_process.c | 4 ++-- include/uapi/linux/kfd_ioctl.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 598296034b43..d27221ddcdeb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1122,7 +1122,7 @@ struct kfd_process *kfd_lookup_process_by_mm(const struct mm_struct *mm) return p; } -/* process_evict_queues - Evict all user queues of a process +/* kfd_process_evict_queues - Evict all user queues of a process * * Eviction is reference-counted per process-device. This means multiple * evictions from different sources can be nested safely. @@ -1162,7 +1162,7 @@ fail: return r; } -/* process_restore_queues - Restore all user queues of a process */ +/* kfd_process_restore_queues - Restore all user queues of a process */ int kfd_process_restore_queues(struct kfd_process *p) { struct kfd_process_device *pdd; diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 4f6676428c5c..b6be62356d34 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -251,7 +251,7 @@ struct kfd_memory_exception_failure { __u32 imprecise; /* Can't determine the exact fault address */ }; -/* memory exception data*/ +/* memory exception data */ struct kfd_hsa_memory_exception_data { struct kfd_memory_exception_failure failure; __u64 va; -- cgit v1.2.3 From d46edd671a147032e22cfeb271a5734703093649 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 30 Apr 2020 00:15:04 -0700 Subject: bpf: Sharing bpf runtime stats with BPF_ENABLE_STATS Currently, sysctl kernel.bpf_stats_enabled controls BPF runtime stats. Typical userspace tools use kernel.bpf_stats_enabled as follows: 1. Enable kernel.bpf_stats_enabled; 2. Check program run_time_ns; 3. Sleep for the monitoring period; 4. Check program run_time_ns again, calculate the difference; 5. Disable kernel.bpf_stats_enabled. The problem with this approach is that only one userspace tool can toggle this sysctl. If multiple tools toggle the sysctl at the same time, the measurement may be inaccurate. To fix this problem while keep backward compatibility, introduce a new bpf command BPF_ENABLE_STATS. On success, this command enables stats and returns a valid fd. BPF_ENABLE_STATS takes argument "type". Currently, only one type, BPF_STATS_RUN_TIME, is supported. We can extend the command to support other types of stats in the future. With BPF_ENABLE_STATS, user space tool would have the following flow: 1. Get a fd with BPF_ENABLE_STATS, and make sure it is valid; 2. Check program run_time_ns; 3. Sleep for the monitoring period; 4. Check program run_time_ns again, calculate the difference; 5. Close the fd. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200430071506.1408910-2-songliubraving@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 11 ++++++++ kernel/bpf/syscall.c | 57 ++++++++++++++++++++++++++++++++++++++++++ kernel/sysctl.c | 36 +++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 11 ++++++++ 5 files changed, 115 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c07b1d2f3824..1262ec460ab3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -987,6 +987,7 @@ _out: \ #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); +extern struct mutex bpf_stats_enabled_mutex; /* * Block execution of BPF programs attached to instrumentation (perf, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0eccafae55bb..705e4822f997 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -115,6 +115,7 @@ enum bpf_cmd { BPF_LINK_UPDATE, BPF_LINK_GET_FD_BY_ID, BPF_LINK_GET_NEXT_ID, + BPF_ENABLE_STATS, }; enum bpf_map_type { @@ -390,6 +391,12 @@ enum { */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) +/* type for BPF_ENABLE_STATS */ +enum bpf_stats_type { + /* enabled run_time_ns and run_cnt */ + BPF_STATS_RUN_TIME = 0, +}; + enum bpf_stack_build_id_status { /* user space need an empty entry to identify end of a trace */ BPF_STACK_BUILD_ID_EMPTY = 0, @@ -601,6 +608,10 @@ union bpf_attr { __u32 old_prog_fd; } link_update; + struct { /* struct used by BPF_ENABLE_STATS command */ + __u32 type; + } enable_stats; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c75b2dd2459c..4f34eecec9ce 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3872,6 +3872,60 @@ static int bpf_link_get_fd_by_id(const union bpf_attr *attr) return fd; } +DEFINE_MUTEX(bpf_stats_enabled_mutex); + +static int bpf_stats_release(struct inode *inode, struct file *file) +{ + mutex_lock(&bpf_stats_enabled_mutex); + static_key_slow_dec(&bpf_stats_enabled_key.key); + mutex_unlock(&bpf_stats_enabled_mutex); + return 0; +} + +static const struct file_operations bpf_stats_fops = { + .release = bpf_stats_release, +}; + +static int bpf_enable_runtime_stats(void) +{ + int fd; + + mutex_lock(&bpf_stats_enabled_mutex); + + /* Set a very high limit to avoid overflow */ + if (static_key_count(&bpf_stats_enabled_key.key) > INT_MAX / 2) { + mutex_unlock(&bpf_stats_enabled_mutex); + return -EBUSY; + } + + fd = anon_inode_getfd("bpf-stats", &bpf_stats_fops, NULL, O_CLOEXEC); + if (fd >= 0) + static_key_slow_inc(&bpf_stats_enabled_key.key); + + mutex_unlock(&bpf_stats_enabled_mutex); + return fd; +} + +#define BPF_ENABLE_STATS_LAST_FIELD enable_stats.type + +static int bpf_enable_stats(union bpf_attr *attr) +{ + + if (CHECK_ATTR(BPF_ENABLE_STATS)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + switch (attr->enable_stats.type) { + case BPF_STATS_RUN_TIME: + return bpf_enable_runtime_stats(); + default: + break; + } + return -EINVAL; +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr; @@ -3996,6 +4050,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_obj_get_next_id(&attr, uattr, &link_idr, &link_idr_lock); break; + case BPF_ENABLE_STATS: + err = bpf_enable_stats(&attr); + break; default: err = -EINVAL; break; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index e961286d0e14..7adfe5dbce9d 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -201,6 +201,40 @@ static int max_extfrag_threshold = 1000; #endif /* CONFIG_SYSCTL */ +#ifdef CONFIG_BPF_SYSCALL +static int bpf_stats_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct static_key *key = (struct static_key *)table->data; + static int saved_val; + int val, ret; + struct ctl_table tmp = { + .data = &val, + .maxlen = sizeof(val), + .mode = table->mode, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + mutex_lock(&bpf_stats_enabled_mutex); + val = saved_val; + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + if (write && !ret && val != saved_val) { + if (val) + static_key_slow_inc(key); + else + static_key_slow_dec(key); + saved_val = val; + } + mutex_unlock(&bpf_stats_enabled_mutex); + return ret; +} +#endif + /* * /proc/sys support */ @@ -2549,7 +2583,7 @@ static struct ctl_table kern_table[] = { .data = &bpf_stats_enabled_key.key, .maxlen = sizeof(bpf_stats_enabled_key), .mode = 0644, - .proc_handler = proc_do_static_key, + .proc_handler = bpf_stats_handler, }, #endif #if defined(CONFIG_TREE_RCU) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 0eccafae55bb..705e4822f997 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -115,6 +115,7 @@ enum bpf_cmd { BPF_LINK_UPDATE, BPF_LINK_GET_FD_BY_ID, BPF_LINK_GET_NEXT_ID, + BPF_ENABLE_STATS, }; enum bpf_map_type { @@ -390,6 +391,12 @@ enum { */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) +/* type for BPF_ENABLE_STATS */ +enum bpf_stats_type { + /* enabled run_time_ns and run_cnt */ + BPF_STATS_RUN_TIME = 0, +}; + enum bpf_stack_build_id_status { /* user space need an empty entry to identify end of a trace */ BPF_STACK_BUILD_ID_EMPTY = 0, @@ -601,6 +608,10 @@ union bpf_attr { __u32 old_prog_fd; } link_update; + struct { /* struct used by BPF_ENABLE_STATS command */ + __u32 type; + } enable_stats; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF -- cgit v1.2.3 From 883780af72090daf9ab53779a3085a6ddfc468ca Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 1 May 2020 16:44:27 +0200 Subject: docs: networking: convert x25-iface.txt to ReST Not much to be done here: - add SPDX header; - adjust title markup; - remove a tail whitespace; - add to networking/index.rst. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: David S. Miller --- Documentation/networking/index.rst | 1 + Documentation/networking/x25-iface.rst | 129 +++++++++++++++++++++++++++++++++ Documentation/networking/x25-iface.txt | 123 ------------------------------- include/uapi/linux/if_x25.h | 2 +- net/x25/Kconfig | 2 +- 5 files changed, 132 insertions(+), 125 deletions(-) create mode 100644 Documentation/networking/x25-iface.rst delete mode 100644 Documentation/networking/x25-iface.txt (limited to 'include/uapi/linux') diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index a72fdfb391b6..7a4bdbc111b0 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -115,6 +115,7 @@ Contents: udplite vrf vxlan + x25-iface .. only:: subproject and html diff --git a/Documentation/networking/x25-iface.rst b/Documentation/networking/x25-iface.rst new file mode 100644 index 000000000000..df401891dce6 --- /dev/null +++ b/Documentation/networking/x25-iface.rst @@ -0,0 +1,129 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================- +X.25 Device Driver Interface +============================- + +Version 1.1 + + Jonathan Naylor 26.12.96 + +This is a description of the messages to be passed between the X.25 Packet +Layer and the X.25 device driver. They are designed to allow for the easy +setting of the LAPB mode from within the Packet Layer. + +The X.25 device driver will be coded normally as per the Linux device driver +standards. Most X.25 device drivers will be moderately similar to the +already existing Ethernet device drivers. However unlike those drivers, the +X.25 device driver has a state associated with it, and this information +needs to be passed to and from the Packet Layer for proper operation. + +All messages are held in sk_buff's just like real data to be transmitted +over the LAPB link. The first byte of the skbuff indicates the meaning of +the rest of the skbuff, if any more information does exist. + + +Packet Layer to Device Driver +----------------------------- + +First Byte = 0x00 (X25_IFACE_DATA) + +This indicates that the rest of the skbuff contains data to be transmitted +over the LAPB link. The LAPB link should already exist before any data is +passed down. + +First Byte = 0x01 (X25_IFACE_CONNECT) + +Establish the LAPB link. If the link is already established then the connect +confirmation message should be returned as soon as possible. + +First Byte = 0x02 (X25_IFACE_DISCONNECT) + +Terminate the LAPB link. If it is already disconnected then the disconnect +confirmation message should be returned as soon as possible. + +First Byte = 0x03 (X25_IFACE_PARAMS) + +LAPB parameters. To be defined. + + +Device Driver to Packet Layer +----------------------------- + +First Byte = 0x00 (X25_IFACE_DATA) + +This indicates that the rest of the skbuff contains data that has been +received over the LAPB link. + +First Byte = 0x01 (X25_IFACE_CONNECT) + +LAPB link has been established. The same message is used for both a LAPB +link connect_confirmation and a connect_indication. + +First Byte = 0x02 (X25_IFACE_DISCONNECT) + +LAPB link has been terminated. This same message is used for both a LAPB +link disconnect_confirmation and a disconnect_indication. + +First Byte = 0x03 (X25_IFACE_PARAMS) + +LAPB parameters. To be defined. + + + +Possible Problems +================= + +(Henner Eisen, 2000-10-28) + +The X.25 packet layer protocol depends on a reliable datalink service. +The LAPB protocol provides such reliable service. But this reliability +is not preserved by the Linux network device driver interface: + +- With Linux 2.4.x (and above) SMP kernels, packet ordering is not + preserved. Even if a device driver calls netif_rx(skb1) and later + netif_rx(skb2), skb2 might be delivered to the network layer + earlier that skb1. +- Data passed upstream by means of netif_rx() might be dropped by the + kernel if the backlog queue is congested. + +The X.25 packet layer protocol will detect this and reset the virtual +call in question. But many upper layer protocols are not designed to +handle such N-Reset events gracefully. And frequent N-Reset events +will always degrade performance. + +Thus, driver authors should make netif_rx() as reliable as possible: + +SMP re-ordering will not occur if the driver's interrupt handler is +always executed on the same CPU. Thus, + +- Driver authors should use irq affinity for the interrupt handler. + +The probability of packet loss due to backlog congestion can be +reduced by the following measures or a combination thereof: + +(1) Drivers for kernel versions 2.4.x and above should always check the + return value of netif_rx(). If it returns NET_RX_DROP, the + driver's LAPB protocol must not confirm reception of the frame + to the peer. + This will reliably suppress packet loss. The LAPB protocol will + automatically cause the peer to re-transmit the dropped packet + later. + The lapb module interface was modified to support this. Its + data_indication() method should now transparently pass the + netif_rx() return value to the (lapb module) caller. +(2) Drivers for kernel versions 2.2.x should always check the global + variable netdev_dropping when a new frame is received. The driver + should only call netif_rx() if netdev_dropping is zero. Otherwise + the driver should not confirm delivery of the frame and drop it. + Alternatively, the driver can queue the frame internally and call + netif_rx() later when netif_dropping is 0 again. In that case, delivery + confirmation should also be deferred such that the internal queue + cannot grow to much. + This will not reliably avoid packet loss, but the probability + of packet loss in netif_rx() path will be significantly reduced. +(3) Additionally, driver authors might consider to support + CONFIG_NET_HW_FLOWCONTROL. This allows the driver to be woken up + when a previously congested backlog queue becomes empty again. + The driver could uses this for flow-controlling the peer by means + of the LAPB protocol's flow-control service. diff --git a/Documentation/networking/x25-iface.txt b/Documentation/networking/x25-iface.txt deleted file mode 100644 index 7f213b556e85..000000000000 --- a/Documentation/networking/x25-iface.txt +++ /dev/null @@ -1,123 +0,0 @@ - X.25 Device Driver Interface 1.1 - - Jonathan Naylor 26.12.96 - -This is a description of the messages to be passed between the X.25 Packet -Layer and the X.25 device driver. They are designed to allow for the easy -setting of the LAPB mode from within the Packet Layer. - -The X.25 device driver will be coded normally as per the Linux device driver -standards. Most X.25 device drivers will be moderately similar to the -already existing Ethernet device drivers. However unlike those drivers, the -X.25 device driver has a state associated with it, and this information -needs to be passed to and from the Packet Layer for proper operation. - -All messages are held in sk_buff's just like real data to be transmitted -over the LAPB link. The first byte of the skbuff indicates the meaning of -the rest of the skbuff, if any more information does exist. - - -Packet Layer to Device Driver ------------------------------ - -First Byte = 0x00 (X25_IFACE_DATA) - -This indicates that the rest of the skbuff contains data to be transmitted -over the LAPB link. The LAPB link should already exist before any data is -passed down. - -First Byte = 0x01 (X25_IFACE_CONNECT) - -Establish the LAPB link. If the link is already established then the connect -confirmation message should be returned as soon as possible. - -First Byte = 0x02 (X25_IFACE_DISCONNECT) - -Terminate the LAPB link. If it is already disconnected then the disconnect -confirmation message should be returned as soon as possible. - -First Byte = 0x03 (X25_IFACE_PARAMS) - -LAPB parameters. To be defined. - - -Device Driver to Packet Layer ------------------------------ - -First Byte = 0x00 (X25_IFACE_DATA) - -This indicates that the rest of the skbuff contains data that has been -received over the LAPB link. - -First Byte = 0x01 (X25_IFACE_CONNECT) - -LAPB link has been established. The same message is used for both a LAPB -link connect_confirmation and a connect_indication. - -First Byte = 0x02 (X25_IFACE_DISCONNECT) - -LAPB link has been terminated. This same message is used for both a LAPB -link disconnect_confirmation and a disconnect_indication. - -First Byte = 0x03 (X25_IFACE_PARAMS) - -LAPB parameters. To be defined. - - - -Possible Problems -================= - -(Henner Eisen, 2000-10-28) - -The X.25 packet layer protocol depends on a reliable datalink service. -The LAPB protocol provides such reliable service. But this reliability -is not preserved by the Linux network device driver interface: - -- With Linux 2.4.x (and above) SMP kernels, packet ordering is not - preserved. Even if a device driver calls netif_rx(skb1) and later - netif_rx(skb2), skb2 might be delivered to the network layer - earlier that skb1. -- Data passed upstream by means of netif_rx() might be dropped by the - kernel if the backlog queue is congested. - -The X.25 packet layer protocol will detect this and reset the virtual -call in question. But many upper layer protocols are not designed to -handle such N-Reset events gracefully. And frequent N-Reset events -will always degrade performance. - -Thus, driver authors should make netif_rx() as reliable as possible: - -SMP re-ordering will not occur if the driver's interrupt handler is -always executed on the same CPU. Thus, - -- Driver authors should use irq affinity for the interrupt handler. - -The probability of packet loss due to backlog congestion can be -reduced by the following measures or a combination thereof: - -(1) Drivers for kernel versions 2.4.x and above should always check the - return value of netif_rx(). If it returns NET_RX_DROP, the - driver's LAPB protocol must not confirm reception of the frame - to the peer. - This will reliably suppress packet loss. The LAPB protocol will - automatically cause the peer to re-transmit the dropped packet - later. - The lapb module interface was modified to support this. Its - data_indication() method should now transparently pass the - netif_rx() return value to the (lapb module) caller. -(2) Drivers for kernel versions 2.2.x should always check the global - variable netdev_dropping when a new frame is received. The driver - should only call netif_rx() if netdev_dropping is zero. Otherwise - the driver should not confirm delivery of the frame and drop it. - Alternatively, the driver can queue the frame internally and call - netif_rx() later when netif_dropping is 0 again. In that case, delivery - confirmation should also be deferred such that the internal queue - cannot grow to much. - This will not reliably avoid packet loss, but the probability - of packet loss in netif_rx() path will be significantly reduced. -(3) Additionally, driver authors might consider to support - CONFIG_NET_HW_FLOWCONTROL. This allows the driver to be woken up - when a previously congested backlog queue becomes empty again. - The driver could uses this for flow-controlling the peer by means - of the LAPB protocol's flow-control service. diff --git a/include/uapi/linux/if_x25.h b/include/uapi/linux/if_x25.h index 5d962448345f..3a5938e38370 100644 --- a/include/uapi/linux/if_x25.h +++ b/include/uapi/linux/if_x25.h @@ -18,7 +18,7 @@ #include -/* Documentation/networking/x25-iface.txt */ +/* Documentation/networking/x25-iface.rst */ #define X25_IFACE_DATA 0x00 #define X25_IFACE_CONNECT 0x01 #define X25_IFACE_DISCONNECT 0x02 diff --git a/net/x25/Kconfig b/net/x25/Kconfig index 2ecb2e5e241e..a328f79885d1 100644 --- a/net/x25/Kconfig +++ b/net/x25/Kconfig @@ -21,7 +21,7 @@ config X25 . Information about X.25 for Linux is contained in the files and - . + . One connects to an X.25 network either with a dedicated network card using the X.21 protocol (not yet supported by Linux) or one can do -- cgit v1.2.3 From beecf11bc2188067824591612151c4dc6ec383c7 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Thu, 30 Apr 2020 16:31:52 -0700 Subject: bpf: Bpf_{g,s}etsockopt for struct bpf_sock_addr Currently, bpf_getsockopt and bpf_setsockopt helpers operate on the 'struct bpf_sock_ops' context in BPF_PROG_TYPE_SOCK_OPS program. Let's generalize them and make them available for 'struct bpf_sock_addr'. That way, in the future, we can allow those helpers in more places. As an example, let's expose those 'struct bpf_sock_addr' based helpers to BPF_CGROUP_INET{4,6}_CONNECT hooks. That way we can override CC before the connection is made. v3: * Expose custom helpers for bpf_sock_addr context instead of doing generic bpf_sock argument (as suggested by Daniel). Even with try_socket_lock that doesn't sleep we have a problem where context sk is already locked and socket lock is non-nestable. v2: * s/BPF_PROG_TYPE_CGROUP_SOCKOPT/BPF_PROG_TYPE_SOCK_OPS/ Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200430233152.199403-1-sdf@google.com --- include/uapi/linux/bpf.h | 14 ++- net/core/filter.c | 118 +++++++++++++++++----- tools/include/uapi/linux/bpf.h | 14 ++- tools/testing/selftests/bpf/config | 1 + tools/testing/selftests/bpf/progs/connect4_prog.c | 46 +++++++++ 5 files changed, 166 insertions(+), 27 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 705e4822f997..b3643e27e264 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1587,7 +1587,7 @@ union bpf_attr { * Return * 0 * - * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) + * int bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) * Description * Emulate a call to **setsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1595,6 +1595,11 @@ union bpf_attr { * must be specified, see **setsockopt(2)** for more information. * The option value of length *optlen* is pointed by *optval*. * + * *bpf_socket* should be one of the following: + * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** + * and **BPF_CGROUP_INET6_CONNECT**. + * * This helper actually implements a subset of **setsockopt()**. * It supports the following *level*\ s: * @@ -1789,7 +1794,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) + * int bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) * Description * Emulate a call to **getsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1798,6 +1803,11 @@ union bpf_attr { * The retrieved value is stored in the structure pointed by * *opval* and of length *optlen*. * + * *bpf_socket* should be one of the following: + * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** + * and **BPF_CGROUP_INET6_CONNECT**. + * * This helper actually implements a subset of **getsockopt()**. * It supports the following *level*\ s: * diff --git a/net/core/filter.c b/net/core/filter.c index 70b32723e6be..dfaf5df13722 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4194,16 +4194,19 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; -BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, - int, level, int, optname, char *, optval, int, optlen) +#define SOCKOPT_CC_REINIT (1 << 0) + +static int _bpf_setsockopt(struct sock *sk, int level, int optname, + char *optval, int optlen, u32 flags) { - struct sock *sk = bpf_sock->sk; int ret = 0; int val; if (!sk_fullsock(sk)) return -EINVAL; + sock_owned_by_me(sk); + if (level == SOL_SOCKET) { if (optlen != sizeof(int)) return -EINVAL; @@ -4298,7 +4301,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, sk->sk_prot->setsockopt == tcp_setsockopt) { if (optname == TCP_CONGESTION) { char name[TCP_CA_NAME_MAX]; - bool reinit = bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN; + bool reinit = flags & SOCKOPT_CC_REINIT; strncpy(name, optval, min_t(long, optlen, TCP_CA_NAME_MAX-1)); @@ -4345,24 +4348,14 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, return ret; } -static const struct bpf_func_proto bpf_setsockopt_proto = { - .func = bpf_setsockopt, - .gpl_only = false, - .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, - .arg5_type = ARG_CONST_SIZE, -}; - -BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, - int, level, int, optname, char *, optval, int, optlen) +static int _bpf_getsockopt(struct sock *sk, int level, int optname, + char *optval, int optlen) { - struct sock *sk = bpf_sock->sk; - if (!sk_fullsock(sk)) goto err_clear; + + sock_owned_by_me(sk); + #ifdef CONFIG_INET if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) { struct inet_connection_sock *icsk; @@ -4428,8 +4421,71 @@ err_clear: return -EINVAL; } -static const struct bpf_func_proto bpf_getsockopt_proto = { - .func = bpf_getsockopt, +BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx, + int, level, int, optname, char *, optval, int, optlen) +{ + u32 flags = 0; + return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen, + flags); +} + +static const struct bpf_func_proto bpf_sock_addr_setsockopt_proto = { + .func = bpf_sock_addr_setsockopt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_MEM, + .arg5_type = ARG_CONST_SIZE, +}; + +BPF_CALL_5(bpf_sock_addr_getsockopt, struct bpf_sock_addr_kern *, ctx, + int, level, int, optname, char *, optval, int, optlen) +{ + return _bpf_getsockopt(ctx->sk, level, optname, optval, optlen); +} + +static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = { + .func = bpf_sock_addr_getsockopt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_UNINIT_MEM, + .arg5_type = ARG_CONST_SIZE, +}; + +BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, + int, level, int, optname, char *, optval, int, optlen) +{ + u32 flags = 0; + if (bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN) + flags |= SOCKOPT_CC_REINIT; + return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen, + flags); +} + +static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = { + .func = bpf_sock_ops_setsockopt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_MEM, + .arg5_type = ARG_CONST_SIZE, +}; + +BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, + int, level, int, optname, char *, optval, int, optlen) +{ + return _bpf_getsockopt(bpf_sock->sk, level, optname, optval, optlen); +} + +static const struct bpf_func_proto bpf_sock_ops_getsockopt_proto = { + .func = bpf_sock_ops_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, @@ -6043,6 +6099,22 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; + case BPF_FUNC_setsockopt: + switch (prog->expected_attach_type) { + case BPF_CGROUP_INET4_CONNECT: + case BPF_CGROUP_INET6_CONNECT: + return &bpf_sock_addr_setsockopt_proto; + default: + return NULL; + } + case BPF_FUNC_getsockopt: + switch (prog->expected_attach_type) { + case BPF_CGROUP_INET4_CONNECT: + case BPF_CGROUP_INET6_CONNECT: + return &bpf_sock_addr_getsockopt_proto; + default: + return NULL; + } default: return bpf_base_func_proto(func_id); } @@ -6261,9 +6333,9 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_setsockopt: - return &bpf_setsockopt_proto; + return &bpf_sock_ops_setsockopt_proto; case BPF_FUNC_getsockopt: - return &bpf_getsockopt_proto; + return &bpf_sock_ops_getsockopt_proto; case BPF_FUNC_sock_ops_cb_flags_set: return &bpf_sock_ops_cb_flags_set_proto; case BPF_FUNC_sock_map_update: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 705e4822f997..b3643e27e264 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1587,7 +1587,7 @@ union bpf_attr { * Return * 0 * - * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) + * int bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) * Description * Emulate a call to **setsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1595,6 +1595,11 @@ union bpf_attr { * must be specified, see **setsockopt(2)** for more information. * The option value of length *optlen* is pointed by *optval*. * + * *bpf_socket* should be one of the following: + * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** + * and **BPF_CGROUP_INET6_CONNECT**. + * * This helper actually implements a subset of **setsockopt()**. * It supports the following *level*\ s: * @@ -1789,7 +1794,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) + * int bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) * Description * Emulate a call to **getsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1798,6 +1803,11 @@ union bpf_attr { * The retrieved value is stored in the structure pointed by * *opval* and of length *optlen*. * + * *bpf_socket* should be one of the following: + * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** + * and **BPF_CGROUP_INET6_CONNECT**. + * * This helper actually implements a subset of **getsockopt()**. * It supports the following *level*\ s: * diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 60e3ae5d4e48..6e5b94c036ca 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -37,3 +37,4 @@ CONFIG_IPV6_SIT=m CONFIG_BPF_JIT=y CONFIG_BPF_LSM=y CONFIG_SECURITY=y +CONFIG_TCP_CONG_DCTCP=y diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c index ad3c498a8150..972918cd2d7f 100644 --- a/tools/testing/selftests/bpf/progs/connect4_prog.c +++ b/tools/testing/selftests/bpf/progs/connect4_prog.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -16,6 +17,10 @@ #define DST_REWRITE_IP4 0x7f000001U #define DST_REWRITE_PORT4 4444 +#ifndef TCP_CA_NAME_MAX +#define TCP_CA_NAME_MAX 16 +#endif + int _version SEC("version") = 1; __attribute__ ((noinline)) @@ -33,6 +38,43 @@ int do_bind(struct bpf_sock_addr *ctx) return 1; } +static __inline int verify_cc(struct bpf_sock_addr *ctx, + char expected[TCP_CA_NAME_MAX]) +{ + char buf[TCP_CA_NAME_MAX]; + int i; + + if (bpf_getsockopt(ctx, SOL_TCP, TCP_CONGESTION, &buf, sizeof(buf))) + return 1; + + for (i = 0; i < TCP_CA_NAME_MAX; i++) { + if (buf[i] != expected[i]) + return 1; + if (buf[i] == 0) + break; + } + + return 0; +} + +static __inline int set_cc(struct bpf_sock_addr *ctx) +{ + char dctcp[TCP_CA_NAME_MAX] = "dctcp"; + char cubic[TCP_CA_NAME_MAX] = "cubic"; + + if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &dctcp, sizeof(dctcp))) + return 1; + if (verify_cc(ctx, dctcp)) + return 1; + + if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &cubic, sizeof(cubic))) + return 1; + if (verify_cc(ctx, cubic)) + return 1; + + return 0; +} + SEC("cgroup/connect4") int connect_v4_prog(struct bpf_sock_addr *ctx) { @@ -66,6 +108,10 @@ int connect_v4_prog(struct bpf_sock_addr *ctx) bpf_sk_release(sk); + /* Rewrite congestion control. */ + if (ctx->type == SOCK_STREAM && set_cc(ctx)) + return 0; + /* Rewrite destination. */ ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4); ctx->user_port = bpf_htons(DST_REWRITE_PORT4); -- cgit v1.2.3 From a51c328df3106663879645680609eb49b3ff6444 Mon Sep 17 00:00:00 2001 From: Po Liu Date: Fri, 1 May 2020 08:53:15 +0800 Subject: net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu Signed-off-by: David S. Miller --- include/net/tc_act/tc_gate.h | 47 +++ include/uapi/linux/pkt_cls.h | 1 + include/uapi/linux/tc_act/tc_gate.h | 47 +++ net/sched/Kconfig | 12 + net/sched/Makefile | 1 + net/sched/act_gate.c | 636 ++++++++++++++++++++++++++++++++++++ 6 files changed, 744 insertions(+) create mode 100644 include/net/tc_act/tc_gate.h create mode 100644 include/uapi/linux/tc_act/tc_gate.h create mode 100644 net/sched/act_gate.c (limited to 'include/uapi/linux') diff --git a/include/net/tc_act/tc_gate.h b/include/net/tc_act/tc_gate.h new file mode 100644 index 000000000000..330ad8b02495 --- /dev/null +++ b/include/net/tc_act/tc_gate.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright 2020 NXP */ + +#ifndef __NET_TC_GATE_H +#define __NET_TC_GATE_H + +#include +#include + +struct tcfg_gate_entry { + int index; + u8 gate_state; + u32 interval; + s32 ipv; + s32 maxoctets; + struct list_head list; +}; + +struct tcf_gate_params { + s32 tcfg_priority; + u64 tcfg_basetime; + u64 tcfg_cycletime; + u64 tcfg_cycletime_ext; + u32 tcfg_flags; + s32 tcfg_clockid; + size_t num_entries; + struct list_head entries; +}; + +#define GATE_ACT_GATE_OPEN BIT(0) +#define GATE_ACT_PENDING BIT(1) + +struct tcf_gate { + struct tc_action common; + struct tcf_gate_params param; + u8 current_gate_status; + ktime_t current_close_time; + u32 current_entry_octets; + s32 current_max_octets; + struct tcfg_gate_entry *next_entry; + struct hrtimer hitimer; + enum tk_offsets tk_offset; +}; + +#define to_gate(a) ((struct tcf_gate *)a) + +#endif diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 9f06d29cab70..fc672b232437 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -134,6 +134,7 @@ enum tca_id { TCA_ID_CTINFO, TCA_ID_MPLS, TCA_ID_CT, + TCA_ID_GATE, /* other actions go here */ __TCA_ID_MAX = 255 }; diff --git a/include/uapi/linux/tc_act/tc_gate.h b/include/uapi/linux/tc_act/tc_gate.h new file mode 100644 index 000000000000..f214b3a6d44f --- /dev/null +++ b/include/uapi/linux/tc_act/tc_gate.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* Copyright 2020 NXP */ + +#ifndef __LINUX_TC_GATE_H +#define __LINUX_TC_GATE_H + +#include + +struct tc_gate { + tc_gen; +}; + +enum { + TCA_GATE_ENTRY_UNSPEC, + TCA_GATE_ENTRY_INDEX, + TCA_GATE_ENTRY_GATE, + TCA_GATE_ENTRY_INTERVAL, + TCA_GATE_ENTRY_IPV, + TCA_GATE_ENTRY_MAX_OCTETS, + __TCA_GATE_ENTRY_MAX, +}; +#define TCA_GATE_ENTRY_MAX (__TCA_GATE_ENTRY_MAX - 1) + +enum { + TCA_GATE_ONE_ENTRY_UNSPEC, + TCA_GATE_ONE_ENTRY, + __TCA_GATE_ONE_ENTRY_MAX, +}; +#define TCA_GATE_ONE_ENTRY_MAX (__TCA_GATE_ONE_ENTRY_MAX - 1) + +enum { + TCA_GATE_UNSPEC, + TCA_GATE_TM, + TCA_GATE_PARMS, + TCA_GATE_PAD, + TCA_GATE_PRIORITY, + TCA_GATE_ENTRY_LIST, + TCA_GATE_BASE_TIME, + TCA_GATE_CYCLE_TIME, + TCA_GATE_CYCLE_TIME_EXT, + TCA_GATE_FLAGS, + TCA_GATE_CLOCKID, + __TCA_GATE_MAX, +}; +#define TCA_GATE_MAX (__TCA_GATE_MAX - 1) + +#endif diff --git a/net/sched/Kconfig b/net/sched/Kconfig index bfbefb7bff9d..2f20073f4f84 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -981,6 +981,18 @@ config NET_ACT_CT To compile this code as a module, choose M here: the module will be called act_ct. +config NET_ACT_GATE + tristate "Frame gate entry list control tc action" + depends on NET_CLS_ACT + help + Say Y here to allow to control the ingress flow to be passed at + specific time slot and be dropped at other specific time slot by + the gate entry list. + + If unsure, say N. + To compile this code as a module, choose M here: the + module will be called act_gate. + config NET_IFE_SKBMARK tristate "Support to encoding decoding skb mark on IFE action" depends on NET_ACT_IFE diff --git a/net/sched/Makefile b/net/sched/Makefile index 31c367a6cd09..66bbf9a98f9e 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -30,6 +30,7 @@ obj-$(CONFIG_NET_IFE_SKBPRIO) += act_meta_skbprio.o obj-$(CONFIG_NET_IFE_SKBTCINDEX) += act_meta_skbtcindex.o obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o obj-$(CONFIG_NET_ACT_CT) += act_ct.o +obj-$(CONFIG_NET_ACT_GATE) += act_gate.o obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c new file mode 100644 index 000000000000..35fc48795541 --- /dev/null +++ b/net/sched/act_gate.c @@ -0,0 +1,636 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Copyright 2020 NXP */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static unsigned int gate_net_id; +static struct tc_action_ops act_gate_ops; + +static ktime_t gate_get_time(struct tcf_gate *gact) +{ + ktime_t mono = ktime_get(); + + switch (gact->tk_offset) { + case TK_OFFS_MAX: + return mono; + default: + return ktime_mono_to_any(mono, gact->tk_offset); + } + + return KTIME_MAX; +} + +static int gate_get_start_time(struct tcf_gate *gact, ktime_t *start) +{ + struct tcf_gate_params *param = &gact->param; + ktime_t now, base, cycle; + u64 n; + + base = ns_to_ktime(param->tcfg_basetime); + now = gate_get_time(gact); + + if (ktime_after(base, now)) { + *start = base; + return 0; + } + + cycle = param->tcfg_cycletime; + + /* cycle time should not be zero */ + if (!cycle) + return -EFAULT; + + n = div64_u64(ktime_sub_ns(now, base), cycle); + *start = ktime_add_ns(base, (n + 1) * cycle); + return 0; +} + +static void gate_start_timer(struct tcf_gate *gact, ktime_t start) +{ + ktime_t expires; + + expires = hrtimer_get_expires(&gact->hitimer); + if (expires == 0) + expires = KTIME_MAX; + + start = min_t(ktime_t, start, expires); + + hrtimer_start(&gact->hitimer, start, HRTIMER_MODE_ABS_SOFT); +} + +static enum hrtimer_restart gate_timer_func(struct hrtimer *timer) +{ + struct tcf_gate *gact = container_of(timer, struct tcf_gate, + hitimer); + struct tcf_gate_params *p = &gact->param; + struct tcfg_gate_entry *next; + ktime_t close_time, now; + + spin_lock(&gact->tcf_lock); + + next = gact->next_entry; + + /* cycle start, clear pending bit, clear total octets */ + gact->current_gate_status = next->gate_state ? GATE_ACT_GATE_OPEN : 0; + gact->current_entry_octets = 0; + gact->current_max_octets = next->maxoctets; + + gact->current_close_time = ktime_add_ns(gact->current_close_time, + next->interval); + + close_time = gact->current_close_time; + + if (list_is_last(&next->list, &p->entries)) + next = list_first_entry(&p->entries, + struct tcfg_gate_entry, list); + else + next = list_next_entry(next, list); + + now = gate_get_time(gact); + + if (ktime_after(now, close_time)) { + ktime_t cycle, base; + u64 n; + + cycle = p->tcfg_cycletime; + base = ns_to_ktime(p->tcfg_basetime); + n = div64_u64(ktime_sub_ns(now, base), cycle); + close_time = ktime_add_ns(base, (n + 1) * cycle); + } + + gact->next_entry = next; + + hrtimer_set_expires(&gact->hitimer, close_time); + + spin_unlock(&gact->tcf_lock); + + return HRTIMER_RESTART; +} + +static int tcf_gate_act(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_gate *gact = to_gate(a); + + spin_lock(&gact->tcf_lock); + + tcf_lastuse_update(&gact->tcf_tm); + bstats_update(&gact->tcf_bstats, skb); + + if (unlikely(gact->current_gate_status & GATE_ACT_PENDING)) { + spin_unlock(&gact->tcf_lock); + return gact->tcf_action; + } + + if (!(gact->current_gate_status & GATE_ACT_GATE_OPEN)) + goto drop; + + if (gact->current_max_octets >= 0) { + gact->current_entry_octets += qdisc_pkt_len(skb); + if (gact->current_entry_octets > gact->current_max_octets) { + gact->tcf_qstats.overlimits++; + goto drop; + } + } + + spin_unlock(&gact->tcf_lock); + + return gact->tcf_action; +drop: + gact->tcf_qstats.drops++; + spin_unlock(&gact->tcf_lock); + + return TC_ACT_SHOT; +} + +static const struct nla_policy entry_policy[TCA_GATE_ENTRY_MAX + 1] = { + [TCA_GATE_ENTRY_INDEX] = { .type = NLA_U32 }, + [TCA_GATE_ENTRY_GATE] = { .type = NLA_FLAG }, + [TCA_GATE_ENTRY_INTERVAL] = { .type = NLA_U32 }, + [TCA_GATE_ENTRY_IPV] = { .type = NLA_S32 }, + [TCA_GATE_ENTRY_MAX_OCTETS] = { .type = NLA_S32 }, +}; + +static const struct nla_policy gate_policy[TCA_GATE_MAX + 1] = { + [TCA_GATE_PARMS] = { .len = sizeof(struct tc_gate), + .type = NLA_EXACT_LEN }, + [TCA_GATE_PRIORITY] = { .type = NLA_S32 }, + [TCA_GATE_ENTRY_LIST] = { .type = NLA_NESTED }, + [TCA_GATE_BASE_TIME] = { .type = NLA_U64 }, + [TCA_GATE_CYCLE_TIME] = { .type = NLA_U64 }, + [TCA_GATE_CYCLE_TIME_EXT] = { .type = NLA_U64 }, + [TCA_GATE_FLAGS] = { .type = NLA_U32 }, + [TCA_GATE_CLOCKID] = { .type = NLA_S32 }, +}; + +static int fill_gate_entry(struct nlattr **tb, struct tcfg_gate_entry *entry, + struct netlink_ext_ack *extack) +{ + u32 interval = 0; + + entry->gate_state = nla_get_flag(tb[TCA_GATE_ENTRY_GATE]); + + if (tb[TCA_GATE_ENTRY_INTERVAL]) + interval = nla_get_u32(tb[TCA_GATE_ENTRY_INTERVAL]); + + if (interval == 0) { + NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry"); + return -EINVAL; + } + + entry->interval = interval; + + if (tb[TCA_GATE_ENTRY_IPV]) + entry->ipv = nla_get_s32(tb[TCA_GATE_ENTRY_IPV]); + else + entry->ipv = -1; + + if (tb[TCA_GATE_ENTRY_MAX_OCTETS]) + entry->maxoctets = nla_get_s32(tb[TCA_GATE_ENTRY_MAX_OCTETS]); + else + entry->maxoctets = -1; + + return 0; +} + +static int parse_gate_entry(struct nlattr *n, struct tcfg_gate_entry *entry, + int index, struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_GATE_ENTRY_MAX + 1] = { }; + int err; + + err = nla_parse_nested(tb, TCA_GATE_ENTRY_MAX, n, entry_policy, extack); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Could not parse nested entry"); + return -EINVAL; + } + + entry->index = index; + + return fill_gate_entry(tb, entry, extack); +} + +static void release_entry_list(struct list_head *entries) +{ + struct tcfg_gate_entry *entry, *e; + + list_for_each_entry_safe(entry, e, entries, list) { + list_del(&entry->list); + kfree(entry); + } +} + +static int parse_gate_list(struct nlattr *list_attr, + struct tcf_gate_params *sched, + struct netlink_ext_ack *extack) +{ + struct tcfg_gate_entry *entry; + struct nlattr *n; + int err, rem; + int i = 0; + + if (!list_attr) + return -EINVAL; + + nla_for_each_nested(n, list_attr, rem) { + if (nla_type(n) != TCA_GATE_ONE_ENTRY) { + NL_SET_ERR_MSG(extack, "Attribute isn't type 'entry'"); + continue; + } + + entry = kzalloc(sizeof(*entry), GFP_ATOMIC); + if (!entry) { + NL_SET_ERR_MSG(extack, "Not enough memory for entry"); + err = -ENOMEM; + goto release_list; + } + + err = parse_gate_entry(n, entry, i, extack); + if (err < 0) { + kfree(entry); + goto release_list; + } + + list_add_tail(&entry->list, &sched->entries); + i++; + } + + sched->num_entries = i; + + return i; + +release_list: + release_entry_list(&sched->entries); + + return err; +} + +static int tcf_gate_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action **a, + int ovr, int bind, bool rtnl_held, + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) +{ + struct tc_action_net *tn = net_generic(net, gate_net_id); + enum tk_offsets tk_offset = TK_OFFS_TAI; + struct nlattr *tb[TCA_GATE_MAX + 1]; + struct tcf_chain *goto_ch = NULL; + struct tcf_gate_params *p; + s32 clockid = CLOCK_TAI; + struct tcf_gate *gact; + struct tc_gate *parm; + int ret = 0, err; + u64 basetime = 0; + u32 gflags = 0; + s32 prio = -1; + ktime_t start; + u32 index; + + if (!nla) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_GATE_MAX, nla, gate_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_GATE_PARMS]) + return -EINVAL; + + parm = nla_data(tb[TCA_GATE_PARMS]); + index = parm->index; + + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) + return err; + + if (err && bind) + return 0; + + if (!err) { + ret = tcf_idr_create(tn, index, est, a, + &act_gate_ops, bind, false, 0); + if (ret) { + tcf_idr_cleanup(tn, index); + return ret; + } + + ret = ACT_P_CREATED; + } else if (!ovr) { + tcf_idr_release(*a, bind); + return -EEXIST; + } + + if (tb[TCA_GATE_PRIORITY]) + prio = nla_get_s32(tb[TCA_GATE_PRIORITY]); + + if (tb[TCA_GATE_BASE_TIME]) + basetime = nla_get_u64(tb[TCA_GATE_BASE_TIME]); + + if (tb[TCA_GATE_FLAGS]) + gflags = nla_get_u32(tb[TCA_GATE_FLAGS]); + + if (tb[TCA_GATE_CLOCKID]) { + clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]); + switch (clockid) { + case CLOCK_REALTIME: + tk_offset = TK_OFFS_REAL; + break; + case CLOCK_MONOTONIC: + tk_offset = TK_OFFS_MAX; + break; + case CLOCK_BOOTTIME: + tk_offset = TK_OFFS_BOOT; + break; + case CLOCK_TAI: + tk_offset = TK_OFFS_TAI; + break; + default: + NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); + goto release_idr; + } + } + + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + + gact = to_gate(*a); + + spin_lock_bh(&gact->tcf_lock); + p = &gact->param; + + if (tb[TCA_GATE_CYCLE_TIME]) { + p->tcfg_cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); + if (!p->tcfg_cycletime_ext) + goto chain_put; + } + + INIT_LIST_HEAD(&p->entries); + if (tb[TCA_GATE_ENTRY_LIST]) { + err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack); + if (err < 0) + goto chain_put; + } + + if (!p->tcfg_cycletime) { + struct tcfg_gate_entry *entry; + ktime_t cycle = 0; + + list_for_each_entry(entry, &p->entries, list) + cycle = ktime_add_ns(cycle, entry->interval); + p->tcfg_cycletime = cycle; + } + + if (tb[TCA_GATE_CYCLE_TIME_EXT]) + p->tcfg_cycletime_ext = + nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]); + + p->tcfg_priority = prio; + p->tcfg_basetime = basetime; + p->tcfg_clockid = clockid; + p->tcfg_flags = gflags; + + gact->tk_offset = tk_offset; + hrtimer_init(&gact->hitimer, clockid, HRTIMER_MODE_ABS_SOFT); + gact->hitimer.function = gate_timer_func; + + err = gate_get_start_time(gact, &start); + if (err < 0) { + NL_SET_ERR_MSG(extack, + "Internal error: failed get start time"); + release_entry_list(&p->entries); + goto chain_put; + } + + gact->current_close_time = start; + gact->current_gate_status = GATE_ACT_GATE_OPEN | GATE_ACT_PENDING; + + gact->next_entry = list_first_entry(&p->entries, + struct tcfg_gate_entry, list); + + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + + gate_start_timer(gact, start); + + spin_unlock_bh(&gact->tcf_lock); + + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + + if (ret == ACT_P_CREATED) + tcf_idr_insert(tn, *a); + + return ret; + +chain_put: + spin_unlock_bh(&gact->tcf_lock); + + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; +} + +static void tcf_gate_cleanup(struct tc_action *a) +{ + struct tcf_gate *gact = to_gate(a); + struct tcf_gate_params *p; + + hrtimer_cancel(&gact->hitimer); + + p = &gact->param; + + release_entry_list(&p->entries); +} + +static int dumping_entry(struct sk_buff *skb, + struct tcfg_gate_entry *entry) +{ + struct nlattr *item; + + item = nla_nest_start_noflag(skb, TCA_GATE_ONE_ENTRY); + if (!item) + return -ENOSPC; + + if (nla_put_u32(skb, TCA_GATE_ENTRY_INDEX, entry->index)) + goto nla_put_failure; + + if (entry->gate_state && nla_put_flag(skb, TCA_GATE_ENTRY_GATE)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_GATE_ENTRY_INTERVAL, entry->interval)) + goto nla_put_failure; + + if (nla_put_s32(skb, TCA_GATE_ENTRY_MAX_OCTETS, entry->maxoctets)) + goto nla_put_failure; + + if (nla_put_s32(skb, TCA_GATE_ENTRY_IPV, entry->ipv)) + goto nla_put_failure; + + return nla_nest_end(skb, item); + +nla_put_failure: + nla_nest_cancel(skb, item); + return -1; +} + +static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) +{ + unsigned char *b = skb_tail_pointer(skb); + struct tcf_gate *gact = to_gate(a); + struct tc_gate opt = { + .index = gact->tcf_index, + .refcnt = refcount_read(&gact->tcf_refcnt) - ref, + .bindcnt = atomic_read(&gact->tcf_bindcnt) - bind, + }; + struct tcfg_gate_entry *entry; + struct tcf_gate_params *p; + struct nlattr *entry_list; + struct tcf_t t; + + spin_lock_bh(&gact->tcf_lock); + opt.action = gact->tcf_action; + + p = &gact->param; + + if (nla_put(skb, TCA_GATE_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, TCA_GATE_BASE_TIME, + p->tcfg_basetime, TCA_GATE_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, TCA_GATE_CYCLE_TIME, + p->tcfg_cycletime, TCA_GATE_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, TCA_GATE_CYCLE_TIME_EXT, + p->tcfg_cycletime_ext, TCA_GATE_PAD)) + goto nla_put_failure; + + if (nla_put_s32(skb, TCA_GATE_CLOCKID, p->tcfg_clockid)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_GATE_FLAGS, p->tcfg_flags)) + goto nla_put_failure; + + if (nla_put_s32(skb, TCA_GATE_PRIORITY, p->tcfg_priority)) + goto nla_put_failure; + + entry_list = nla_nest_start_noflag(skb, TCA_GATE_ENTRY_LIST); + if (!entry_list) + goto nla_put_failure; + + list_for_each_entry(entry, &p->entries, list) { + if (dumping_entry(skb, entry) < 0) + goto nla_put_failure; + } + + nla_nest_end(skb, entry_list); + + tcf_tm_dump(&t, &gact->tcf_tm); + if (nla_put_64bit(skb, TCA_GATE_TM, sizeof(t), &t, TCA_GATE_PAD)) + goto nla_put_failure; + spin_unlock_bh(&gact->tcf_lock); + + return skb->len; + +nla_put_failure: + spin_unlock_bh(&gact->tcf_lock); + nlmsg_trim(skb, b); + return -1; +} + +static int tcf_gate_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) +{ + struct tc_action_net *tn = net_generic(net, gate_net_id); + + return tcf_generic_walker(tn, skb, cb, type, ops, extack); +} + +static void tcf_gate_stats_update(struct tc_action *a, u64 bytes, u32 packets, + u64 lastuse, bool hw) +{ + struct tcf_gate *gact = to_gate(a); + struct tcf_t *tm = &gact->tcf_tm; + + tcf_action_update_stats(a, bytes, packets, false, hw); + tm->lastuse = max_t(u64, tm->lastuse, lastuse); +} + +static int tcf_gate_search(struct net *net, struct tc_action **a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, gate_net_id); + + return tcf_idr_search(tn, a, index); +} + +static size_t tcf_gate_get_fill_size(const struct tc_action *act) +{ + return nla_total_size(sizeof(struct tc_gate)); +} + +static struct tc_action_ops act_gate_ops = { + .kind = "gate", + .id = TCA_ID_GATE, + .owner = THIS_MODULE, + .act = tcf_gate_act, + .dump = tcf_gate_dump, + .init = tcf_gate_init, + .cleanup = tcf_gate_cleanup, + .walk = tcf_gate_walker, + .stats_update = tcf_gate_stats_update, + .get_fill_size = tcf_gate_get_fill_size, + .lookup = tcf_gate_search, + .size = sizeof(struct tcf_gate), +}; + +static __net_init int gate_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, gate_net_id); + + return tc_action_net_init(net, tn, &act_gate_ops); +} + +static void __net_exit gate_exit_net(struct list_head *net_list) +{ + tc_action_net_exit(net_list, gate_net_id); +} + +static struct pernet_operations gate_net_ops = { + .init = gate_init_net, + .exit_batch = gate_exit_net, + .id = &gate_net_id, + .size = sizeof(struct tc_action_net), +}; + +static int __init gate_init_module(void) +{ + return tcf_register_action(&act_gate_ops, &gate_net_ops); +} + +static void __exit gate_cleanup_module(void) +{ + tcf_unregister_action(&act_gate_ops, &gate_net_ops); +} + +module_init(gate_init_module); +module_exit(gate_cleanup_module); +MODULE_LICENSE("GPL v2"); -- cgit v1.2.3 From d3f1cbd29fa63f1bb608603a6cd54ca7af56a68b Mon Sep 17 00:00:00 2001 From: Vincent Cheng Date: Fri, 1 May 2020 23:35:37 -0400 Subject: ptp: Add adjust_phase to ptp_clock_caps capability. Add adjust_phase to ptp_clock_caps capability to allow user to query if a PHC driver supports adjust phase with ioctl PTP_CLOCK_GETCAPS command. Signed-off-by: Vincent Cheng Reviewed-by: Richard Cochran Signed-off-by: David S. Miller --- drivers/ptp/ptp_chardev.c | 1 + include/uapi/linux/ptp_clock.h | 4 +++- tools/testing/selftests/ptp/testptp.c | 6 ++++-- 3 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index 93d574faf1fe..375cd6e4aade 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -136,6 +136,7 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg) caps.pps = ptp->info->pps; caps.n_pins = ptp->info->n_pins; caps.cross_timestamping = ptp->info->getcrosststamp != NULL; + caps.adjust_phase = ptp->info->adjphase != NULL; if (copy_to_user((void __user *)arg, &caps, sizeof(caps))) err = -EFAULT; break; diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h index 9dc9d0079e98..ff070aa64278 100644 --- a/include/uapi/linux/ptp_clock.h +++ b/include/uapi/linux/ptp_clock.h @@ -89,7 +89,9 @@ struct ptp_clock_caps { int n_pins; /* Number of input/output pins. */ /* Whether the clock supports precise system-device cross timestamps */ int cross_timestamping; - int rsv[13]; /* Reserved for future use. */ + /* Whether the clock supports adjust phase */ + int adjust_phase; + int rsv[12]; /* Reserved for future use. */ }; struct ptp_extts_request { diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index c0dd10257df5..da7a9dda9490 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -269,14 +269,16 @@ int main(int argc, char *argv[]) " %d programmable periodic signals\n" " %d pulse per second\n" " %d programmable pins\n" - " %d cross timestamping\n", + " %d cross timestamping\n" + " %d adjust_phase\n", caps.max_adj, caps.n_alarm, caps.n_ext_ts, caps.n_per_out, caps.pps, caps.n_pins, - caps.cross_timestamping); + caps.cross_timestamping, + caps.adjust_phase); } } -- cgit v1.2.3 From 712b2698e4c024b561694cbcc1abba13eb0fd9ce Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 30 Apr 2020 07:41:34 -0700 Subject: fs/stat: Define DAX statx attribute In order for users to determine if a file is currently operating in DAX state (effective DAX). Define a statx attribute value and set that attribute if the effective DAX flag is set. To go along with this we propose the following addition to the statx man page: STATX_ATTR_DAX The file is in the DAX (cpu direct access) state. DAX state attempts to minimize software cache effects for both I/O and memory mappings of this file. It requires a file system which has been configured to support DAX. DAX generally assumes all accesses are via cpu load / store instructions which can minimize overhead for small accesses, but may adversely affect cpu utilization for large transfers. File I/O is done directly to/from user-space buffers and memory mapped I/O may be performed with direct memory mappings that bypass kernel page cache. While the DAX property tends to result in data being transferred synchronously, it does not give the same guarantees of O_SYNC where data and the necessary metadata are transferred together. A DAX file may support being mapped with the MAP_SYNC flag, which enables a program to use CPU cache flush instructions to persist CPU store operations without an explicit fsync(2). See mmap(2) for more information. Reviewed-by: Dave Chinner Reviewed-by: Jan Kara Reviewed-by: Darrick J. Wong Signed-off-by: Ira Weiny Signed-off-by: Darrick J. Wong --- fs/stat.c | 3 +++ include/uapi/linux/stat.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/stat.c b/fs/stat.c index 030008796479..894699c74dde 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -79,6 +79,9 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, if (IS_AUTOMOUNT(inode)) stat->attributes |= STATX_ATTR_AUTOMOUNT; + if (IS_DAX(inode)) + stat->attributes |= STATX_ATTR_DAX; + if (inode->i_op->getattr) return inode->i_op->getattr(path, stat, request_mask, query_flags); diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index ad80a5c885d5..e5f9d5517f6b 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -169,6 +169,7 @@ struct statx { #define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */ #define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ +#define STATX_ATTR_DAX 0x00002000 /* [I] File is DAX */ #endif /* _UAPI_LINUX_STAT_H */ -- cgit v1.2.3 From 1e6e9d0f4859ec698d55381ea26f4136eff3afe1 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 24 Apr 2020 10:50:00 -0500 Subject: uapi: revert flexible-array conversions These structures can get embedded in other structures in user-space and cause all sorts of warnings and problems. So, we better don't take any chances and keep the zero-length arrays in place for now. Signed-off-by: Gustavo A. R. Silva --- include/uapi/linux/bpf.h | 2 +- include/uapi/linux/dlm_device.h | 4 ++-- include/uapi/linux/fiemap.h | 2 +- include/uapi/linux/if_arcnet.h | 6 +++--- include/uapi/linux/mmc/ioctl.h | 2 +- include/uapi/linux/net_dropmon.h | 4 ++-- include/uapi/linux/netfilter_bridge/ebt_among.h | 2 +- include/uapi/scsi/scsi_bsg_fc.h | 2 +- 8 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7bbf1b65be10..f9b7fdd951e4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -73,7 +73,7 @@ struct bpf_insn { /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ struct bpf_lpm_trie_key { __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ - __u8 data[]; /* Arbitrary size */ + __u8 data[0]; /* Arbitrary size */ }; struct bpf_cgroup_storage_key { diff --git a/include/uapi/linux/dlm_device.h b/include/uapi/linux/dlm_device.h index e83954c69fff..f880d2831160 100644 --- a/include/uapi/linux/dlm_device.h +++ b/include/uapi/linux/dlm_device.h @@ -45,13 +45,13 @@ struct dlm_lock_params { void __user *bastaddr; struct dlm_lksb __user *lksb; char lvb[DLM_USER_LVB_LEN]; - char name[]; + char name[0]; }; struct dlm_lspace_params { __u32 flags; __u32 minor; - char name[]; + char name[0]; }; struct dlm_purge_params { diff --git a/include/uapi/linux/fiemap.h b/include/uapi/linux/fiemap.h index 7a900b2377b6..8c0bc24d5d95 100644 --- a/include/uapi/linux/fiemap.h +++ b/include/uapi/linux/fiemap.h @@ -34,7 +34,7 @@ struct fiemap { __u32 fm_mapped_extents;/* number of extents that were mapped (out) */ __u32 fm_extent_count; /* size of fm_extents array (in) */ __u32 fm_reserved; - struct fiemap_extent fm_extents[]; /* array of mapped extents (out) */ + struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */ }; #define FIEMAP_MAX_OFFSET (~0ULL) diff --git a/include/uapi/linux/if_arcnet.h b/include/uapi/linux/if_arcnet.h index b122cfac7128..683878036d76 100644 --- a/include/uapi/linux/if_arcnet.h +++ b/include/uapi/linux/if_arcnet.h @@ -60,7 +60,7 @@ struct arc_rfc1201 { __u8 proto; /* protocol ID field - varies */ __u8 split_flag; /* for use with split packets */ __be16 sequence; /* sequence number */ - __u8 payload[]; /* space remaining in packet (504 bytes)*/ + __u8 payload[0]; /* space remaining in packet (504 bytes)*/ }; #define RFC1201_HDR_SIZE 4 @@ -69,7 +69,7 @@ struct arc_rfc1201 { */ struct arc_rfc1051 { __u8 proto; /* ARC_P_RFC1051_ARP/RFC1051_IP */ - __u8 payload[]; /* 507 bytes */ + __u8 payload[0]; /* 507 bytes */ }; #define RFC1051_HDR_SIZE 1 @@ -80,7 +80,7 @@ struct arc_rfc1051 { struct arc_eth_encap { __u8 proto; /* Always ARC_P_ETHER */ struct ethhdr eth; /* standard ethernet header (yuck!) */ - __u8 payload[]; /* 493 bytes */ + __u8 payload[0]; /* 493 bytes */ }; #define ETH_ENCAP_HDR_SIZE 14 diff --git a/include/uapi/linux/mmc/ioctl.h b/include/uapi/linux/mmc/ioctl.h index 98e29e7f54ac..00c08120f3ba 100644 --- a/include/uapi/linux/mmc/ioctl.h +++ b/include/uapi/linux/mmc/ioctl.h @@ -57,7 +57,7 @@ struct mmc_ioc_cmd { */ struct mmc_ioc_multi_cmd { __u64 num_of_cmds; - struct mmc_ioc_cmd cmds[]; + struct mmc_ioc_cmd cmds[0]; }; #define MMC_IOC_CMD _IOWR(MMC_BLOCK_MAJOR, 0, struct mmc_ioc_cmd) diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h index 67e31f329190..66048cc5d7b3 100644 --- a/include/uapi/linux/net_dropmon.h +++ b/include/uapi/linux/net_dropmon.h @@ -29,12 +29,12 @@ struct net_dm_config_entry { struct net_dm_config_msg { __u32 entries; - struct net_dm_config_entry options[]; + struct net_dm_config_entry options[0]; }; struct net_dm_alert_msg { __u32 entries; - struct net_dm_drop_point points[]; + struct net_dm_drop_point points[0]; }; struct net_dm_user_msg { diff --git a/include/uapi/linux/netfilter_bridge/ebt_among.h b/include/uapi/linux/netfilter_bridge/ebt_among.h index 73b26a280c4f..9acf757bc1f7 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_among.h +++ b/include/uapi/linux/netfilter_bridge/ebt_among.h @@ -40,7 +40,7 @@ struct ebt_mac_wormhash_tuple { struct ebt_mac_wormhash { int table[257]; int poolsize; - struct ebt_mac_wormhash_tuple pool[]; + struct ebt_mac_wormhash_tuple pool[0]; }; #define ebt_mac_wormhash_size(x) ((x) ? sizeof(struct ebt_mac_wormhash) \ diff --git a/include/uapi/scsi/scsi_bsg_fc.h b/include/uapi/scsi/scsi_bsg_fc.h index 7f5930801f72..3ae65e93235c 100644 --- a/include/uapi/scsi/scsi_bsg_fc.h +++ b/include/uapi/scsi/scsi_bsg_fc.h @@ -209,7 +209,7 @@ struct fc_bsg_host_vendor { __u64 vendor_id; /* start of vendor command area */ - __u32 vendor_cmd[]; + __u32 vendor_cmd[0]; }; /* Response: -- cgit v1.2.3 From 39d010504e6b4485d7ceee167743620dd33f4417 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 1 May 2020 07:07:41 -0700 Subject: net_sched: sch_fq: add horizon attribute QUIC servers would like to use SO_TXTIME, without having CAP_NET_ADMIN, to efficiently pace UDP packets. As far as sch_fq is concerned, we need to add safety checks, so that a buggy application does not fill the qdisc with packets having delivery time far in the future. This patch adds a configurable horizon (default: 10 seconds), and a configurable policy when a packet is beyond the horizon at enqueue() time: - either drop the packet (default policy) - or cap its delivery time to the horizon. $ tc -s -d qd sh dev eth0 qdisc fq 8022: root refcnt 257 limit 10000p flow_limit 100p buckets 1024 orphan_mask 1023 quantum 10Kb initial_quantum 51160b low_rate_threshold 550Kbit refill_delay 40.0ms timer_slack 10.000us horizon 10.000s Sent 1234215879 bytes 837099 pkt (dropped 21, overlimits 0 requeues 6) backlog 0b 0p requeues 6 flows 1191 (inactive 1177 throttled 0) gc 0 highprio 0 throttled 692 latency 11.480us pkts_too_long 0 alloc_errors 0 horizon_drops 21 horizon_caps 0 v2: fixed an overflow on 32bit kernels in fq_init(), reported by kbuild test robot Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 6 +++++ net/sched/sch_fq.c | 59 ++++++++++++++++++++++++++++++++++++++---- 2 files changed, 60 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 0c02737c8f47..a95f3ae7ab37 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -913,6 +913,10 @@ enum { TCA_FQ_TIMER_SLACK, /* timer slack */ + TCA_FQ_HORIZON, /* time horizon in us */ + + TCA_FQ_HORIZON_DROP, /* drop packets beyond horizon, or cap their EDT */ + __TCA_FQ_MAX }; @@ -932,6 +936,8 @@ struct tc_fq_qd_stats { __u32 throttled_flows; __u32 unthrottle_latency_ns; __u64 ce_mark; /* packets above ce_threshold */ + __u64 horizon_drops; + __u64 horizon_caps; }; /* Heavy-Hitter Filter */ diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 4f0104243cc2..8f06a808c59a 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -100,6 +100,7 @@ struct fq_sched_data { struct rb_root delayed; /* for rate limited flows */ u64 time_next_delayed_flow; + u64 ktime_cache; /* copy of last ktime_get_ns() */ unsigned long unthrottle_latency_ns; struct fq_flow internal; /* for non classified or high prio packets */ @@ -109,12 +110,13 @@ struct fq_sched_data { u32 flow_plimit; /* max packets per flow */ unsigned long flow_max_rate; /* optional max rate per flow */ u64 ce_threshold; + u64 horizon; /* horizon in ns */ u32 orphan_mask; /* mask for orphaned skb */ u32 low_rate_threshold; struct rb_root *fq_root; u8 rate_enable; u8 fq_trees_log; - + u8 horizon_drop; u32 flows; u32 inactive_flows; u32 throttled_flows; @@ -123,6 +125,8 @@ struct fq_sched_data { u64 stat_internal_packets; u64 stat_throttled; u64 stat_ce_mark; + u64 stat_horizon_drops; + u64 stat_horizon_caps; u64 stat_flows_plimit; u64 stat_pkts_too_long; u64 stat_allocation_errors; @@ -402,8 +406,6 @@ static void flow_queue_add(struct fq_flow *flow, struct sk_buff *skb) struct rb_node **p, *parent; struct sk_buff *head, *aux; - fq_skb_cb(skb)->time_to_send = skb->tstamp ?: ktime_get_ns(); - head = flow->head; if (!head || fq_skb_cb(skb)->time_to_send >= fq_skb_cb(flow->tail)->time_to_send) { @@ -431,6 +433,12 @@ static void flow_queue_add(struct fq_flow *flow, struct sk_buff *skb) rb_insert_color(&skb->rbnode, &flow->t_root); } +static bool fq_packet_beyond_horizon(const struct sk_buff *skb, + const struct fq_sched_data *q) +{ + return unlikely((s64)skb->tstamp > (s64)(q->ktime_cache + q->horizon)); +} + static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { @@ -440,6 +448,28 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (unlikely(sch->q.qlen >= sch->limit)) return qdisc_drop(skb, sch, to_free); + if (!skb->tstamp) { + fq_skb_cb(skb)->time_to_send = q->ktime_cache = ktime_get_ns(); + } else { + /* Check if packet timestamp is too far in the future. + * Try first if our cached value, to avoid ktime_get_ns() + * cost in most cases. + */ + if (fq_packet_beyond_horizon(skb, q)) { + /* Refresh our cache and check another time */ + q->ktime_cache = ktime_get_ns(); + if (fq_packet_beyond_horizon(skb, q)) { + if (q->horizon_drop) { + q->stat_horizon_drops++; + return qdisc_drop(skb, sch, to_free); + } + q->stat_horizon_caps++; + skb->tstamp = q->ktime_cache + q->horizon; + } + } + fq_skb_cb(skb)->time_to_send = skb->tstamp; + } + f = fq_classify(skb, q); if (unlikely(f->qlen >= q->flow_plimit && f != &q->internal)) { q->stat_flows_plimit++; @@ -512,7 +542,7 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch) goto out; } - now = ktime_get_ns(); + q->ktime_cache = now = ktime_get_ns(); fq_check_throttled(q, now); begin: head = &q->new_flows; @@ -765,6 +795,8 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { [TCA_FQ_LOW_RATE_THRESHOLD] = { .type = NLA_U32 }, [TCA_FQ_CE_THRESHOLD] = { .type = NLA_U32 }, [TCA_FQ_TIMER_SLACK] = { .type = NLA_U32 }, + [TCA_FQ_HORIZON] = { .type = NLA_U32 }, + [TCA_FQ_HORIZON_DROP] = { .type = NLA_U8 }, }; static int fq_change(struct Qdisc *sch, struct nlattr *opt, @@ -854,7 +886,15 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_FQ_TIMER_SLACK]) q->timer_slack = nla_get_u32(tb[TCA_FQ_TIMER_SLACK]); + if (tb[TCA_FQ_HORIZON]) + q->horizon = (u64)NSEC_PER_USEC * + nla_get_u32(tb[TCA_FQ_HORIZON]); + + if (tb[TCA_FQ_HORIZON_DROP]) + q->horizon_drop = nla_get_u8(tb[TCA_FQ_HORIZON_DROP]); + if (!err) { + sch_tree_unlock(sch); err = fq_resize(sch, fq_log); sch_tree_lock(sch); @@ -907,6 +947,9 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt, q->timer_slack = 10 * NSEC_PER_USEC; /* 10 usec of hrtimer slack */ + q->horizon = 10ULL * NSEC_PER_SEC; /* 10 seconds */ + q->horizon_drop = 1; /* by default, drop packets beyond horizon */ + /* Default ce_threshold of 4294 seconds */ q->ce_threshold = (u64)NSEC_PER_USEC * ~0U; @@ -924,6 +967,7 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) { struct fq_sched_data *q = qdisc_priv(sch); u64 ce_threshold = q->ce_threshold; + u64 horizon = q->horizon; struct nlattr *opts; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); @@ -933,6 +977,7 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) /* TCA_FQ_FLOW_DEFAULT_RATE is not used anymore */ do_div(ce_threshold, NSEC_PER_USEC); + do_div(horizon, NSEC_PER_USEC); if (nla_put_u32(skb, TCA_FQ_PLIMIT, sch->limit) || nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT, q->flow_plimit) || @@ -948,7 +993,9 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) q->low_rate_threshold) || nla_put_u32(skb, TCA_FQ_CE_THRESHOLD, (u32)ce_threshold) || nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log) || - nla_put_u32(skb, TCA_FQ_TIMER_SLACK, q->timer_slack)) + nla_put_u32(skb, TCA_FQ_TIMER_SLACK, q->timer_slack) || + nla_put_u32(skb, TCA_FQ_HORIZON, (u32)horizon) || + nla_put_u8(skb, TCA_FQ_HORIZON_DROP, q->horizon_drop)) goto nla_put_failure; return nla_nest_end(skb, opts); @@ -979,6 +1026,8 @@ static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) st.unthrottle_latency_ns = min_t(unsigned long, q->unthrottle_latency_ns, ~0U); st.ce_mark = q->stat_ce_mark; + st.horizon_drops = q->stat_horizon_drops; + st.horizon_caps = q->stat_horizon_caps; sch_tree_unlock(sch); return gnet_stats_copy_app(d, &st, sizeof(st)); -- cgit v1.2.3 From f645e6256bd1b12523b759fcc610861fb21c24c7 Mon Sep 17 00:00:00 2001 From: Niklas Söderlund Date: Tue, 21 Apr 2020 15:57:38 +0200 Subject: media: v4l2-dev/ioctl: Add V4L2_CAP_IO_MC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a video device capability flag to indicate that its inputs and/or outputs are controlled by the Media Controller instead of the V4L2 API. When this flag is set, ioctl for enum inputs and outputs are automatically enabled and programmed to call a helper function. Suggested-by: Hans Verkuil Signed-off-by: Helen Koike Signed-off-by: Niklas Söderlund Reviewed-by: Laurent Pinchart Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- .../userspace-api/media/v4l/vidioc-querycap.rst | 6 +++ .../userspace-api/media/videodev2.h.rst.exceptions | 1 + drivers/media/v4l2-core/v4l2-dev.c | 25 +++++++--- drivers/media/v4l2-core/v4l2-ioctl.c | 57 ++++++++++++++++++++-- include/uapi/linux/videodev2.h | 2 + 5 files changed, 81 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/vidioc-querycap.rst b/Documentation/userspace-api/media/v4l/vidioc-querycap.rst index 28e1f766128c..666ac4d42051 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-querycap.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-querycap.rst @@ -264,6 +264,12 @@ specification the ioctl returns an ``EINVAL`` error code. * - ``V4L2_CAP_TOUCH`` - 0x10000000 - This is a touch device. + * - ``V4L2_CAP_IO_MC`` + - 0x20000000 + - There is only one input and/or output seen from userspace. The whole + video topology configuration, including which I/O entity is routed to + the input/output, is configured by userspace via the Media Controller. + See :ref:`media_controller`. * - ``V4L2_CAP_DEVICE_CAPS`` - 0x80000000 - The driver fills the ``device_caps`` field. This capability can diff --git a/Documentation/userspace-api/media/videodev2.h.rst.exceptions b/Documentation/userspace-api/media/videodev2.h.rst.exceptions index cb6ccf91776e..a625fb90e3a9 100644 --- a/Documentation/userspace-api/media/videodev2.h.rst.exceptions +++ b/Documentation/userspace-api/media/videodev2.h.rst.exceptions @@ -176,6 +176,7 @@ replace define V4L2_CAP_STREAMING device-capabilities replace define V4L2_CAP_META_OUTPUT device-capabilities replace define V4L2_CAP_DEVICE_CAPS device-capabilities replace define V4L2_CAP_TOUCH device-capabilities +replace define V4L2_CAP_IO_MC device-capabilities # V4L2 pix flags replace define V4L2_PIX_FMT_PRIV_MAGIC :c:type:`v4l2_pix_format` diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c index 97b6a3af1361..a593ea0598b5 100644 --- a/drivers/media/v4l2-core/v4l2-dev.c +++ b/drivers/media/v4l2-core/v4l2-dev.c @@ -552,6 +552,7 @@ static void determine_valid_ioctls(struct video_device *vdev) (vdev->device_caps & meta_caps); bool is_rx = vdev->vfl_dir != VFL_DIR_TX; bool is_tx = vdev->vfl_dir != VFL_DIR_RX; + bool is_io_mc = vdev->device_caps & V4L2_CAP_IO_MC; bitmap_zero(valid_ioctls, BASE_VIDIOC_PRIVATE); @@ -725,9 +726,15 @@ static void determine_valid_ioctls(struct video_device *vdev) SET_VALID_IOCTL(ops, VIDIOC_G_STD, vidioc_g_std); if (is_rx) { SET_VALID_IOCTL(ops, VIDIOC_QUERYSTD, vidioc_querystd); - SET_VALID_IOCTL(ops, VIDIOC_ENUMINPUT, vidioc_enum_input); - SET_VALID_IOCTL(ops, VIDIOC_G_INPUT, vidioc_g_input); - SET_VALID_IOCTL(ops, VIDIOC_S_INPUT, vidioc_s_input); + if (is_io_mc) { + set_bit(_IOC_NR(VIDIOC_ENUMINPUT), valid_ioctls); + set_bit(_IOC_NR(VIDIOC_G_INPUT), valid_ioctls); + set_bit(_IOC_NR(VIDIOC_S_INPUT), valid_ioctls); + } else { + SET_VALID_IOCTL(ops, VIDIOC_ENUMINPUT, vidioc_enum_input); + SET_VALID_IOCTL(ops, VIDIOC_G_INPUT, vidioc_g_input); + SET_VALID_IOCTL(ops, VIDIOC_S_INPUT, vidioc_s_input); + } SET_VALID_IOCTL(ops, VIDIOC_ENUMAUDIO, vidioc_enumaudio); SET_VALID_IOCTL(ops, VIDIOC_G_AUDIO, vidioc_g_audio); SET_VALID_IOCTL(ops, VIDIOC_S_AUDIO, vidioc_s_audio); @@ -735,9 +742,15 @@ static void determine_valid_ioctls(struct video_device *vdev) SET_VALID_IOCTL(ops, VIDIOC_S_EDID, vidioc_s_edid); } if (is_tx) { - SET_VALID_IOCTL(ops, VIDIOC_ENUMOUTPUT, vidioc_enum_output); - SET_VALID_IOCTL(ops, VIDIOC_G_OUTPUT, vidioc_g_output); - SET_VALID_IOCTL(ops, VIDIOC_S_OUTPUT, vidioc_s_output); + if (is_io_mc) { + set_bit(_IOC_NR(VIDIOC_ENUMOUTPUT), valid_ioctls); + set_bit(_IOC_NR(VIDIOC_G_OUTPUT), valid_ioctls); + set_bit(_IOC_NR(VIDIOC_S_OUTPUT), valid_ioctls); + } else { + SET_VALID_IOCTL(ops, VIDIOC_ENUMOUTPUT, vidioc_enum_output); + SET_VALID_IOCTL(ops, VIDIOC_G_OUTPUT, vidioc_g_output); + SET_VALID_IOCTL(ops, VIDIOC_S_OUTPUT, vidioc_s_output); + } SET_VALID_IOCTL(ops, VIDIOC_ENUMAUDOUT, vidioc_enumaudout); SET_VALID_IOCTL(ops, VIDIOC_G_AUDOUT, vidioc_g_audout); SET_VALID_IOCTL(ops, VIDIOC_S_AUDOUT, vidioc_s_audout); diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 833e79a2cb98..665b2bc7b732 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1085,6 +1085,32 @@ static int v4l_querycap(const struct v4l2_ioctl_ops *ops, return ret; } +static int v4l_g_input(const struct v4l2_ioctl_ops *ops, + struct file *file, void *fh, void *arg) +{ + struct video_device *vfd = video_devdata(file); + + if (vfd->device_caps & V4L2_CAP_IO_MC) { + *(int *)arg = 0; + return 0; + } + + return ops->vidioc_g_input(file, fh, arg); +} + +static int v4l_g_output(const struct v4l2_ioctl_ops *ops, + struct file *file, void *fh, void *arg) +{ + struct video_device *vfd = video_devdata(file); + + if (vfd->device_caps & V4L2_CAP_IO_MC) { + *(int *)arg = 0; + return 0; + } + + return ops->vidioc_g_output(file, fh, arg); +} + static int v4l_s_input(const struct v4l2_ioctl_ops *ops, struct file *file, void *fh, void *arg) { @@ -1094,12 +1120,21 @@ static int v4l_s_input(const struct v4l2_ioctl_ops *ops, ret = v4l_enable_media_source(vfd); if (ret) return ret; + + if (vfd->device_caps & V4L2_CAP_IO_MC) + return *(int *)arg ? -EINVAL : 0; + return ops->vidioc_s_input(file, fh, *(unsigned int *)arg); } static int v4l_s_output(const struct v4l2_ioctl_ops *ops, struct file *file, void *fh, void *arg) { + struct video_device *vfd = video_devdata(file); + + if (vfd->device_caps & V4L2_CAP_IO_MC) + return *(int *)arg ? -EINVAL : 0; + return ops->vidioc_s_output(file, fh, *(unsigned int *)arg); } @@ -1143,6 +1178,14 @@ static int v4l_enuminput(const struct v4l2_ioctl_ops *ops, if (is_valid_ioctl(vfd, VIDIOC_S_STD)) p->capabilities |= V4L2_IN_CAP_STD; + if (vfd->device_caps & V4L2_CAP_IO_MC) { + if (p->index) + return -EINVAL; + strscpy(p->name, vfd->name, sizeof(p->name)); + p->type = V4L2_INPUT_TYPE_CAMERA; + return 0; + } + return ops->vidioc_enum_input(file, fh, p); } @@ -1161,6 +1204,14 @@ static int v4l_enumoutput(const struct v4l2_ioctl_ops *ops, if (is_valid_ioctl(vfd, VIDIOC_S_STD)) p->capabilities |= V4L2_OUT_CAP_STD; + if (vfd->device_caps & V4L2_CAP_IO_MC) { + if (p->index) + return -EINVAL; + strscpy(p->name, vfd->name, sizeof(p->name)); + p->type = V4L2_OUTPUT_TYPE_ANALOG; + return 0; + } + return ops->vidioc_enum_output(file, fh, p); } @@ -2683,10 +2734,8 @@ DEFINE_V4L_STUB_FUNC(expbuf) DEFINE_V4L_STUB_FUNC(g_std) DEFINE_V4L_STUB_FUNC(g_audio) DEFINE_V4L_STUB_FUNC(s_audio) -DEFINE_V4L_STUB_FUNC(g_input) DEFINE_V4L_STUB_FUNC(g_edid) DEFINE_V4L_STUB_FUNC(s_edid) -DEFINE_V4L_STUB_FUNC(g_output) DEFINE_V4L_STUB_FUNC(g_audout) DEFINE_V4L_STUB_FUNC(s_audout) DEFINE_V4L_STUB_FUNC(g_jpegcomp) @@ -2735,11 +2784,11 @@ static const struct v4l2_ioctl_info v4l2_ioctls[] = { IOCTL_INFO(VIDIOC_S_AUDIO, v4l_stub_s_audio, v4l_print_audio, INFO_FL_PRIO), IOCTL_INFO(VIDIOC_QUERYCTRL, v4l_queryctrl, v4l_print_queryctrl, INFO_FL_CTRL | INFO_FL_CLEAR(v4l2_queryctrl, id)), IOCTL_INFO(VIDIOC_QUERYMENU, v4l_querymenu, v4l_print_querymenu, INFO_FL_CTRL | INFO_FL_CLEAR(v4l2_querymenu, index)), - IOCTL_INFO(VIDIOC_G_INPUT, v4l_stub_g_input, v4l_print_u32, 0), + IOCTL_INFO(VIDIOC_G_INPUT, v4l_g_input, v4l_print_u32, 0), IOCTL_INFO(VIDIOC_S_INPUT, v4l_s_input, v4l_print_u32, INFO_FL_PRIO), IOCTL_INFO(VIDIOC_G_EDID, v4l_stub_g_edid, v4l_print_edid, INFO_FL_ALWAYS_COPY), IOCTL_INFO(VIDIOC_S_EDID, v4l_stub_s_edid, v4l_print_edid, INFO_FL_PRIO | INFO_FL_ALWAYS_COPY), - IOCTL_INFO(VIDIOC_G_OUTPUT, v4l_stub_g_output, v4l_print_u32, 0), + IOCTL_INFO(VIDIOC_G_OUTPUT, v4l_g_output, v4l_print_u32, 0), IOCTL_INFO(VIDIOC_S_OUTPUT, v4l_s_output, v4l_print_u32, INFO_FL_PRIO), IOCTL_INFO(VIDIOC_ENUMOUTPUT, v4l_enumoutput, v4l_print_enumoutput, INFO_FL_CLEAR(v4l2_output, index)), IOCTL_INFO(VIDIOC_G_AUDOUT, v4l_stub_g_audout, v4l_print_audioout, 0), diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 9817b7e2c968..b18f3f7cde31 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -487,6 +487,8 @@ struct v4l2_capability { #define V4L2_CAP_TOUCH 0x10000000 /* Is a touch device */ +#define V4L2_CAP_IO_MC 0x20000000 /* Is input/output controlled by the media controller */ + #define V4L2_CAP_DEVICE_CAPS 0x80000000 /* sets device capabilities field */ /* -- cgit v1.2.3 From e5b6b07a1b45dd9d19bec1fa1d60750b0fcf2fb0 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 24 Apr 2020 15:43:31 +0200 Subject: media: v4l2: Extend VIDIOC_ENUM_FMT to support MC-centric devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The VIDIOC_ENUM_FMT ioctl enumerates all formats supported by a video node. For MC-centric devices, its behaviour has always been ill-defined, with drivers implementing one of the following behaviours: - No support for VIDIOC_ENUM_FMT at all - Enumerating all formats supported by the video node, regardless of the configuration of the pipeline - Enumerating formats supported by the video node for the active configuration of the connected subdevice The first behaviour is obviously useless for applications. The second behaviour provides the most information, but doesn't offer a way to find what formats are compatible with a given pipeline configuration. The third behaviour fixes that, but with the drawback that applications can't enumerate all supported formats anymore, and have to modify the active configuration of the pipeline to enumerate formats. The situation is messy as none of the implemented behaviours are ideal, and userspace can't predict what will happen as the behaviour is driver-specific. To fix this, let's extend the VIDIOC_ENUM_FMT with a missing capability: enumerating pixel formats for a given media bus code. The media bus code is passed through the v4l2_fmtdesc structure in a new mbus_code field (repurposed from the reserved fields). With this capability in place, applications can enumerate pixel formats for a given media bus code without modifying the active configuration of the device. The current behaviour of the ioctl is preserved when the new mbus_code field is set to 0, ensuring compatibility with existing userspace. The API extension is documented as mandatory for MC-centric devices (as advertised through the V4L2_CAP_IO_MC capability), allowing applications and compliance tools to easily determine the availability of the VIDIOC_ENUM_FMT extension. Signed-off-by: Laurent Pinchart Acked-by: Sakari Ailus Signed-off-by: Niklas Söderlund Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- .../userspace-api/media/v4l/vidioc-enum-fmt.rst | 27 ++++++++++++++++++---- drivers/media/v4l2-core/v4l2-ioctl.c | 13 +++++++++-- include/uapi/linux/videodev2.h | 3 ++- 3 files changed, 35 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/vidioc-enum-fmt.rst b/Documentation/userspace-api/media/v4l/vidioc-enum-fmt.rst index 7e3142e11d77..9694111772a2 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-enum-fmt.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-enum-fmt.rst @@ -48,10 +48,21 @@ one until ``EINVAL`` is returned. If applicable, drivers shall return formats in preference order, where preferred formats are returned before (that is, with lower ``index`` value) less-preferred formats. -.. note:: - - After switching input or output the list of enumerated image - formats may be different. +If the driver doesn't advertise the ``V4L2_CAP_IO_MC`` :ref:`capability +`, applications shall initialize the ``mbus_code`` field +to zero and drivers shall ignore the value of the field. Drivers shall +enumerate all image formats. The enumerated formats may depend on the active +input or output of the device. + +If the driver advertises the ``V4L2_CAP_IO_MC`` :ref:`capability +`, applications may initialize the ``mbus_code`` field to +a valid :ref:`media bus format code `. If the +``mbus_code`` field is not zero, drivers shall restrict enumeration to only the +image formats that can produce (for video output devices) or be produced from +(for video capture devices) that media bus code. Regardless of the value of +the ``mbus_code`` field, the enumerated image formats shall not depend on the +active configuration of the video device or device pipeline. Enumeration shall +otherwise operate as previously described. .. tabularcolumns:: |p{4.4cm}|p{4.4cm}|p{8.7cm}| @@ -106,7 +117,13 @@ formats in preference order, where preferred formats are returned before These codes are not the same as those used in the Windows world. * - __u32 - - ``reserved``\ [4] + - ``mbus_code`` + - Media bus code restricting the enumerated formats, set by the + application. Only applicable to drivers that advertise the + ``V4L2_CAP_IO_MC`` :ref:`capability `, shall be 0 + otherwise. + * - __u32 + - ``reserved``\ [3] - Reserved for future extensions. Drivers must set the array to zero. diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 665b2bc7b732..2322f08a98be 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -264,12 +264,13 @@ static void v4l_print_fmtdesc(const void *arg, bool write_only) { const struct v4l2_fmtdesc *p = arg; - pr_cont("index=%u, type=%s, flags=0x%x, pixelformat=%c%c%c%c, description='%.*s'\n", + pr_cont("index=%u, type=%s, flags=0x%x, pixelformat=%c%c%c%c, mbus_code=0x%04x, description='%.*s'\n", p->index, prt_names(p->type, v4l2_type_names), p->flags, (p->pixelformat & 0xff), (p->pixelformat >> 8) & 0xff, (p->pixelformat >> 16) & 0xff, (p->pixelformat >> 24) & 0xff, + p->mbus_code, (int)sizeof(p->description), p->description); } @@ -1472,12 +1473,20 @@ static int v4l_enum_fmt(const struct v4l2_ioctl_ops *ops, struct video_device *vdev = video_devdata(file); struct v4l2_fmtdesc *p = arg; int ret = check_fmt(file, p->type); + u32 mbus_code; u32 cap_mask; if (ret) return ret; ret = -EINVAL; + if (!(vdev->device_caps & V4L2_CAP_IO_MC)) + p->mbus_code = 0; + + mbus_code = p->mbus_code; + CLEAR_AFTER_FIELD(p, type); + p->mbus_code = mbus_code; + switch (p->type) { case V4L2_BUF_TYPE_VIDEO_CAPTURE: case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE: @@ -2757,7 +2766,7 @@ DEFINE_V4L_STUB_FUNC(dv_timings_cap) static const struct v4l2_ioctl_info v4l2_ioctls[] = { IOCTL_INFO(VIDIOC_QUERYCAP, v4l_querycap, v4l_print_querycap, 0), - IOCTL_INFO(VIDIOC_ENUM_FMT, v4l_enum_fmt, v4l_print_fmtdesc, INFO_FL_CLEAR(v4l2_fmtdesc, type)), + IOCTL_INFO(VIDIOC_ENUM_FMT, v4l_enum_fmt, v4l_print_fmtdesc, 0), IOCTL_INFO(VIDIOC_G_FMT, v4l_g_fmt, v4l_print_format, 0), IOCTL_INFO(VIDIOC_S_FMT, v4l_s_fmt, v4l_print_format, INFO_FL_PRIO), IOCTL_INFO(VIDIOC_REQBUFS, v4l_reqbufs, v4l_print_requestbuffers, INFO_FL_PRIO | INFO_FL_QUEUE), diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index b18f3f7cde31..c3a1cf1c507f 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -784,7 +784,8 @@ struct v4l2_fmtdesc { __u32 flags; __u8 description[32]; /* Description string */ __u32 pixelformat; /* Format fourcc */ - __u32 reserved[4]; + __u32 mbus_code; /* Media bus code */ + __u32 reserved[3]; }; #define V4L2_FMT_FLAG_COMPRESSED 0x0001 -- cgit v1.2.3 From bdbdac7649fac05f88c9f7ab18121a17fb591687 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 5 May 2020 08:35:05 +0200 Subject: ethtool: provide UAPI for PHY master/slave configuration. This UAPI is needed for BroadR-Reach 100BASE-T1 devices. Due to lack of auto-negotiation support, we needed to be able to configure the MASTER-SLAVE role of the port manually or from an application in user space. The same UAPI can be used for 1000BASE-T or MultiGBASE-T devices to force MASTER or SLAVE role. See IEEE 802.3-2018: 22.2.4.3.7 MASTER-SLAVE control register (Register 9) 22.2.4.3.8 MASTER-SLAVE status register (Register 10) 40.5.2 MASTER-SLAVE configuration resolution 45.2.1.185.1 MASTER-SLAVE config value (1.2100.14) 45.2.7.10 MultiGBASE-T AN control 1 register (Register 7.32) The MASTER-SLAVE role affects the clock configuration: ------------------------------------------------------------------------------- When the PHY is configured as MASTER, the PMA Transmit function shall source TX_TCLK from a local clock source. When configured as SLAVE, the PMA Transmit function shall source TX_TCLK from the clock recovered from data stream provided by MASTER. iMX6Q KSZ9031 XXX ------\ /-----------\ /------------\ | | | | | MAC |<----RGMII----->| PHY Slave |<------>| PHY Master | |<--- 125 MHz ---+-<------/ | | \ | ------/ \-----------/ \------------/ ^ \-TX_TCLK ------------------------------------------------------------------------------- Since some clock or link related issues are only reproducible in a specific MASTER-SLAVE-role, MAC and PHY configuration, it is beneficial to provide generic (not 100BASE-T1 specific) interface to the user space for configuration flexibility and trouble shooting. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 35 ++++++----- drivers/net/phy/phy.c | 4 +- drivers/net/phy/phy_device.c | 94 ++++++++++++++++++++++++++++ include/linux/phy.h | 3 + include/uapi/linux/ethtool.h | 16 ++++- include/uapi/linux/ethtool_netlink.h | 2 + include/uapi/linux/mii.h | 2 + net/ethtool/ioctl.c | 6 ++ net/ethtool/linkmodes.c | 53 ++++++++++++++++ 9 files changed, 197 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 567326491f80..8f5cefc539cf 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -392,14 +392,16 @@ Request contents: Kernel response contents: - ==================================== ====== ========================== - ``ETHTOOL_A_LINKMODES_HEADER`` nested reply header - ``ETHTOOL_A_LINKMODES_AUTONEG`` u8 autonegotiation status - ``ETHTOOL_A_LINKMODES_OURS`` bitset advertised link modes - ``ETHTOOL_A_LINKMODES_PEER`` bitset partner link modes - ``ETHTOOL_A_LINKMODES_SPEED`` u32 link speed (Mb/s) - ``ETHTOOL_A_LINKMODES_DUPLEX`` u8 duplex mode - ==================================== ====== ========================== + ========================================== ====== ========================== + ``ETHTOOL_A_LINKMODES_HEADER`` nested reply header + ``ETHTOOL_A_LINKMODES_AUTONEG`` u8 autonegotiation status + ``ETHTOOL_A_LINKMODES_OURS`` bitset advertised link modes + ``ETHTOOL_A_LINKMODES_PEER`` bitset partner link modes + ``ETHTOOL_A_LINKMODES_SPEED`` u32 link speed (Mb/s) + ``ETHTOOL_A_LINKMODES_DUPLEX`` u8 duplex mode + ``ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG`` u8 Master/slave port mode + ``ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE`` u8 Master/slave port state + ========================================== ====== ========================== For ``ETHTOOL_A_LINKMODES_OURS``, value represents advertised modes and mask represents supported modes. ``ETHTOOL_A_LINKMODES_PEER`` in the reply is a bit @@ -414,14 +416,15 @@ LINKMODES_SET Request contents: - ==================================== ====== ========================== - ``ETHTOOL_A_LINKMODES_HEADER`` nested request header - ``ETHTOOL_A_LINKMODES_AUTONEG`` u8 autonegotiation status - ``ETHTOOL_A_LINKMODES_OURS`` bitset advertised link modes - ``ETHTOOL_A_LINKMODES_PEER`` bitset partner link modes - ``ETHTOOL_A_LINKMODES_SPEED`` u32 link speed (Mb/s) - ``ETHTOOL_A_LINKMODES_DUPLEX`` u8 duplex mode - ==================================== ====== ========================== + ========================================== ====== ========================== + ``ETHTOOL_A_LINKMODES_HEADER`` nested request header + ``ETHTOOL_A_LINKMODES_AUTONEG`` u8 autonegotiation status + ``ETHTOOL_A_LINKMODES_OURS`` bitset advertised link modes + ``ETHTOOL_A_LINKMODES_PEER`` bitset partner link modes + ``ETHTOOL_A_LINKMODES_SPEED`` u32 link speed (Mb/s) + ``ETHTOOL_A_LINKMODES_DUPLEX`` u8 duplex mode + ``ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG`` u8 Master/slave port mode + ========================================== ====== ========================== ``ETHTOOL_A_LINKMODES_OURS`` bit set allows setting advertised link modes. If autonegotiation is on (either set now or kept from before), advertised modes diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 72c69a9c8a98..8c22d02b4218 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -295,7 +295,7 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev, phydev->advertising, autoneg == AUTONEG_ENABLE); phydev->duplex = duplex; - + phydev->master_slave_set = cmd->base.master_slave_cfg; phydev->mdix_ctrl = cmd->base.eth_tp_mdix_ctrl; /* Restart the PHY */ @@ -314,6 +314,8 @@ void phy_ethtool_ksettings_get(struct phy_device *phydev, cmd->base.speed = phydev->speed; cmd->base.duplex = phydev->duplex; + cmd->base.master_slave_cfg = phydev->master_slave_get; + cmd->base.master_slave_state = phydev->master_slave_state; if (phydev->interface == PHY_INTERFACE_MODE_MOCA) cmd->base.port = PORT_BNC; else diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index b1c5e4503bc4..83fc8e1b5793 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1913,6 +1913,90 @@ int genphy_setup_forced(struct phy_device *phydev) } EXPORT_SYMBOL(genphy_setup_forced); +static int genphy_setup_master_slave(struct phy_device *phydev) +{ + u16 ctl = 0; + + if (!phydev->is_gigabit_capable) + return 0; + + switch (phydev->master_slave_set) { + case MASTER_SLAVE_CFG_MASTER_PREFERRED: + ctl |= CTL1000_PREFER_MASTER; + break; + case MASTER_SLAVE_CFG_SLAVE_PREFERRED: + break; + case MASTER_SLAVE_CFG_MASTER_FORCE: + ctl |= CTL1000_AS_MASTER; + /* fallthrough */ + case MASTER_SLAVE_CFG_SLAVE_FORCE: + ctl |= CTL1000_ENABLE_MASTER; + break; + case MASTER_SLAVE_CFG_UNKNOWN: + case MASTER_SLAVE_CFG_UNSUPPORTED: + return 0; + default: + phydev_warn(phydev, "Unsupported Master/Slave mode\n"); + return -EOPNOTSUPP; + } + + return phy_modify_changed(phydev, MII_CTRL1000, + (CTL1000_ENABLE_MASTER | CTL1000_AS_MASTER | + CTL1000_PREFER_MASTER), ctl); +} + +static int genphy_read_master_slave(struct phy_device *phydev) +{ + int cfg, state; + u16 val; + + if (!phydev->is_gigabit_capable) { + phydev->master_slave_get = MASTER_SLAVE_CFG_UNSUPPORTED; + phydev->master_slave_state = MASTER_SLAVE_STATE_UNSUPPORTED; + return 0; + } + + phydev->master_slave_get = MASTER_SLAVE_CFG_UNKNOWN; + phydev->master_slave_state = MASTER_SLAVE_STATE_UNKNOWN; + + val = phy_read(phydev, MII_CTRL1000); + if (val < 0) + return val; + + if (val & CTL1000_ENABLE_MASTER) { + if (val & CTL1000_AS_MASTER) + cfg = MASTER_SLAVE_CFG_MASTER_FORCE; + else + cfg = MASTER_SLAVE_CFG_SLAVE_FORCE; + } else { + if (val & CTL1000_PREFER_MASTER) + cfg = MASTER_SLAVE_CFG_MASTER_PREFERRED; + else + cfg = MASTER_SLAVE_CFG_SLAVE_PREFERRED; + } + + val = phy_read(phydev, MII_STAT1000); + if (val < 0) + return val; + + if (val & LPA_1000MSFAIL) { + state = MASTER_SLAVE_STATE_ERR; + } else if (phydev->link) { + /* this bits are valid only for active link */ + if (val & LPA_1000MSRES) + state = MASTER_SLAVE_STATE_MASTER; + else + state = MASTER_SLAVE_STATE_SLAVE; + } else { + state = MASTER_SLAVE_STATE_UNKNOWN; + } + + phydev->master_slave_get = cfg; + phydev->master_slave_state = state; + + return 0; +} + /** * genphy_restart_aneg - Enable and Restart Autonegotiation * @phydev: target phy_device struct @@ -1971,6 +2055,12 @@ int __genphy_config_aneg(struct phy_device *phydev, bool changed) if (genphy_config_eee_advert(phydev)) changed = true; + err = genphy_setup_master_slave(phydev); + if (err < 0) + return err; + else if (err) + changed = true; + if (AUTONEG_ENABLE != phydev->autoneg) return genphy_setup_forced(phydev); @@ -2205,6 +2295,10 @@ int genphy_read_status(struct phy_device *phydev) phydev->pause = 0; phydev->asym_pause = 0; + err = genphy_read_master_slave(phydev); + if (err < 0) + return err; + err = genphy_read_lpa(phydev); if (err < 0) return err; diff --git a/include/linux/phy.h b/include/linux/phy.h index 1d36ac608159..a2b91b5f9d0a 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -477,6 +477,9 @@ struct phy_device { int duplex; int pause; int asym_pause; + u8 master_slave_get; + u8 master_slave_set; + u8 master_slave_state; /* Union of PHY and Attached devices' supported link modes */ /* See ethtool.h for more info */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 92f737f10117..f4662b3a9e1e 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1666,6 +1666,18 @@ static inline int ethtool_validate_duplex(__u8 duplex) return 0; } +#define MASTER_SLAVE_CFG_UNSUPPORTED 0 +#define MASTER_SLAVE_CFG_UNKNOWN 1 +#define MASTER_SLAVE_CFG_MASTER_PREFERRED 2 +#define MASTER_SLAVE_CFG_SLAVE_PREFERRED 3 +#define MASTER_SLAVE_CFG_MASTER_FORCE 4 +#define MASTER_SLAVE_CFG_SLAVE_FORCE 5 +#define MASTER_SLAVE_STATE_UNSUPPORTED 0 +#define MASTER_SLAVE_STATE_UNKNOWN 1 +#define MASTER_SLAVE_STATE_MASTER 2 +#define MASTER_SLAVE_STATE_SLAVE 3 +#define MASTER_SLAVE_STATE_ERR 4 + /* Which connector port. */ #define PORT_TP 0x00 #define PORT_AUI 0x01 @@ -1904,7 +1916,9 @@ struct ethtool_link_settings { __u8 eth_tp_mdix_ctrl; __s8 link_mode_masks_nwords; __u8 transceiver; - __u8 reserved1[3]; + __u8 master_slave_cfg; + __u8 master_slave_state; + __u8 reserved1[1]; __u32 reserved[7]; __u32 link_mode_masks[0]; /* layout of link_mode_masks fields: diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 7fde76366ba4..bf1d310e20bc 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -216,6 +216,8 @@ enum { ETHTOOL_A_LINKMODES_PEER, /* bitset */ ETHTOOL_A_LINKMODES_SPEED, /* u32 */ ETHTOOL_A_LINKMODES_DUPLEX, /* u8 */ + ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG, /* u8 */ + ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE, /* u8 */ /* add new constants above here */ __ETHTOOL_A_LINKMODES_CNT, diff --git a/include/uapi/linux/mii.h b/include/uapi/linux/mii.h index 90f9b4e1ba27..39f7c44baf53 100644 --- a/include/uapi/linux/mii.h +++ b/include/uapi/linux/mii.h @@ -151,11 +151,13 @@ /* 1000BASE-T Control register */ #define ADVERTISE_1000FULL 0x0200 /* Advertise 1000BASE-T full duplex */ #define ADVERTISE_1000HALF 0x0100 /* Advertise 1000BASE-T half duplex */ +#define CTL1000_PREFER_MASTER 0x0400 /* prefer to operate as master */ #define CTL1000_AS_MASTER 0x0800 #define CTL1000_ENABLE_MASTER 0x1000 /* 1000BASE-T Status register */ #define LPA_1000MSFAIL 0x8000 /* Master/Slave resolution failure */ +#define LPA_1000MSRES 0x4000 /* Master/Slave resolution status */ #define LPA_1000LOCALRXOK 0x2000 /* Link partner local receiver status */ #define LPA_1000REMRXOK 0x1000 /* Link partner remote receiver status */ #define LPA_1000FULL 0x0800 /* Link partner 1000BASE-T full duplex */ diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 226d5ecdd567..52102ab1709b 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -552,6 +552,8 @@ static int ethtool_get_link_ksettings(struct net_device *dev, link_ksettings.base.cmd = ETHTOOL_GLINKSETTINGS; link_ksettings.base.link_mode_masks_nwords = __ETHTOOL_LINK_MODE_MASK_NU32; + link_ksettings.base.master_slave_cfg = MASTER_SLAVE_CFG_UNSUPPORTED; + link_ksettings.base.master_slave_state = MASTER_SLAVE_STATE_UNSUPPORTED; return store_link_ksettings_for_user(useraddr, &link_ksettings); } @@ -589,6 +591,10 @@ static int ethtool_set_link_ksettings(struct net_device *dev, != link_ksettings.base.link_mode_masks_nwords) return -EINVAL; + if (link_ksettings.base.master_slave_cfg || + link_ksettings.base.master_slave_state) + return -EINVAL; + err = dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); if (err >= 0) { ethtool_notify(dev, ETHTOOL_MSG_LINKINFO_NTF, NULL); diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index 452608c6d856..fd4f3e58c6f6 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -27,6 +27,8 @@ linkmodes_get_policy[ETHTOOL_A_LINKMODES_MAX + 1] = { [ETHTOOL_A_LINKMODES_PEER] = { .type = NLA_REJECT }, [ETHTOOL_A_LINKMODES_SPEED] = { .type = NLA_REJECT }, [ETHTOOL_A_LINKMODES_DUPLEX] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE] = { .type = NLA_REJECT }, }; static int linkmodes_prepare_data(const struct ethnl_req_info *req_base, @@ -63,6 +65,7 @@ static int linkmodes_reply_size(const struct ethnl_req_info *req_base, { const struct linkmodes_reply_data *data = LINKMODES_REPDATA(reply_base); const struct ethtool_link_ksettings *ksettings = &data->ksettings; + const struct ethtool_link_settings *lsettings = &ksettings->base; bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; int len, ret; @@ -86,6 +89,12 @@ static int linkmodes_reply_size(const struct ethnl_req_info *req_base, len += ret; } + if (lsettings->master_slave_cfg != MASTER_SLAVE_CFG_UNSUPPORTED) + len += nla_total_size(sizeof(u8)); + + if (lsettings->master_slave_state != MASTER_SLAVE_STATE_UNSUPPORTED) + len += nla_total_size(sizeof(u8)); + return len; } @@ -122,6 +131,16 @@ static int linkmodes_fill_reply(struct sk_buff *skb, nla_put_u8(skb, ETHTOOL_A_LINKMODES_DUPLEX, lsettings->duplex)) return -EMSGSIZE; + if (lsettings->master_slave_cfg != MASTER_SLAVE_CFG_UNSUPPORTED && + nla_put_u8(skb, ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG, + lsettings->master_slave_cfg)) + return -EMSGSIZE; + + if (lsettings->master_slave_state != MASTER_SLAVE_STATE_UNSUPPORTED && + nla_put_u8(skb, ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE, + lsettings->master_slave_state)) + return -EMSGSIZE; + return 0; } @@ -249,6 +268,8 @@ linkmodes_set_policy[ETHTOOL_A_LINKMODES_MAX + 1] = { [ETHTOOL_A_LINKMODES_PEER] = { .type = NLA_REJECT }, [ETHTOOL_A_LINKMODES_SPEED] = { .type = NLA_U32 }, [ETHTOOL_A_LINKMODES_DUPLEX] = { .type = NLA_U8 }, + [ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG] = { .type = NLA_U8 }, + [ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE] = { .type = NLA_REJECT }, }; /* Set advertised link modes to all supported modes matching requested speed @@ -287,14 +308,45 @@ static bool ethnl_auto_linkmodes(struct ethtool_link_ksettings *ksettings, __ETHTOOL_LINK_MODE_MASK_NBITS); } +static bool ethnl_validate_master_slave_cfg(u8 cfg) +{ + switch (cfg) { + case MASTER_SLAVE_CFG_MASTER_PREFERRED: + case MASTER_SLAVE_CFG_SLAVE_PREFERRED: + case MASTER_SLAVE_CFG_MASTER_FORCE: + case MASTER_SLAVE_CFG_SLAVE_FORCE: + return true; + } + + return false; +} + static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb, struct ethtool_link_ksettings *ksettings, bool *mod) { struct ethtool_link_settings *lsettings = &ksettings->base; bool req_speed, req_duplex; + const struct nlattr *master_slave_cfg; int ret; + master_slave_cfg = tb[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG]; + if (master_slave_cfg) { + u8 cfg = nla_get_u8(master_slave_cfg); + + if (lsettings->master_slave_cfg == MASTER_SLAVE_CFG_UNSUPPORTED) { + NL_SET_ERR_MSG_ATTR(info->extack, master_slave_cfg, + "master/slave configuration not supported by device"); + return -EOPNOTSUPP; + } + + if (!ethnl_validate_master_slave_cfg(cfg)) { + NL_SET_ERR_MSG_ATTR(info->extack, master_slave_cfg, + "master/slave value is invalid"); + return -EOPNOTSUPP; + } + } + *mod = false; req_speed = tb[ETHTOOL_A_LINKMODES_SPEED]; req_duplex = tb[ETHTOOL_A_LINKMODES_DUPLEX]; @@ -311,6 +363,7 @@ static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb, mod); ethnl_update_u8(&lsettings->duplex, tb[ETHTOOL_A_LINKMODES_DUPLEX], mod); + ethnl_update_u8(&lsettings->master_slave_cfg, master_slave_cfg, mod); if (!tb[ETHTOOL_A_LINKMODES_OURS] && lsettings->autoneg && (req_speed || req_duplex) && -- cgit v1.2.3 From 8086fbaf49345f988deec539ec8e182b02914401 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 8 May 2020 10:46:11 -0700 Subject: bpf: Allow any port in bpf_bind helper We want to have a tighter control on what ports we bind to in the BPF_CGROUP_INET{4,6}_CONNECT hooks even if it means connect() becomes slightly more expensive. The expensive part comes from the fact that we now need to call inet_csk_get_port() that verifies that the port is not used and allocates an entry in the hash table for it. Since we can't rely on "snum || !bind_address_no_port" to prevent us from calling POST_BIND hook anymore, let's add another bind flag to indicate that the call site is BPF program. v5: * fix wrong AF_INET (should be AF_INET6) in the bpf program for v6 v3: * More bpf_bind documentation refinements (Martin KaFai Lau) * Add UDP tests as well (Martin KaFai Lau) * Don't start the thread, just do socket+bind+listen (Martin KaFai Lau) v2: * Update documentation (Andrey Ignatov) * Pass BIND_FORCE_ADDRESS_NO_PORT conditionally (Andrey Ignatov) Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Acked-by: Andrey Ignatov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200508174611.228805-5-sdf@google.com --- include/net/inet_common.h | 2 + include/uapi/linux/bpf.h | 9 +- net/core/filter.c | 18 ++-- net/ipv4/af_inet.c | 10 +- net/ipv6/af_inet6.c | 12 ++- tools/include/uapi/linux/bpf.h | 9 +- .../selftests/bpf/prog_tests/connect_force_port.c | 115 +++++++++++++++++++++ .../selftests/bpf/progs/connect_force_port4.c | 28 +++++ .../selftests/bpf/progs/connect_force_port6.c | 28 +++++ 9 files changed, 203 insertions(+), 28 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/connect_force_port.c create mode 100644 tools/testing/selftests/bpf/progs/connect_force_port4.c create mode 100644 tools/testing/selftests/bpf/progs/connect_force_port6.c (limited to 'include/uapi/linux') diff --git a/include/net/inet_common.h b/include/net/inet_common.h index c38f4f7d660a..cb2818862919 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -39,6 +39,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); #define BIND_FORCE_ADDRESS_NO_PORT (1 << 0) /* Grab and release socket lock. */ #define BIND_WITH_LOCK (1 << 1) +/* Called from BPF program. */ +#define BIND_FROM_BPF (1 << 2) int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, u32 flags); int inet_getname(struct socket *sock, struct sockaddr *uaddr, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b3643e27e264..6e5e7caa3739 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1994,10 +1994,11 @@ union bpf_attr { * * This helper works for IPv4 and IPv6, TCP and UDP sockets. The * domain (*addr*\ **->sa_family**) must be **AF_INET** (or - * **AF_INET6**). Looking for a free port to bind to can be - * expensive, therefore binding to port is not permitted by the - * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively) - * must be set to zero. + * **AF_INET6**). It's advised to pass zero port (**sin_port** + * or **sin6_port**) which triggers IP_BIND_ADDRESS_NO_PORT-like + * behavior and lets the kernel efficiently pick up an unused + * port as long as 4-tuple is unique. Passing non-zero port might + * lead to degraded performance. * Return * 0 on success, or a negative error in case of failure. * diff --git a/net/core/filter.c b/net/core/filter.c index fa9ddab5dd1f..da0634979f53 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4525,32 +4525,28 @@ BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr, { #ifdef CONFIG_INET struct sock *sk = ctx->sk; + u32 flags = BIND_FROM_BPF; int err; - /* Binding to port can be expensive so it's prohibited in the helper. - * Only binding to IP is supported. - */ err = -EINVAL; if (addr_len < offsetofend(struct sockaddr, sa_family)) return err; if (addr->sa_family == AF_INET) { if (addr_len < sizeof(struct sockaddr_in)) return err; - if (((struct sockaddr_in *)addr)->sin_port != htons(0)) - return err; - return __inet_bind(sk, addr, addr_len, - BIND_FORCE_ADDRESS_NO_PORT); + if (((struct sockaddr_in *)addr)->sin_port == htons(0)) + flags |= BIND_FORCE_ADDRESS_NO_PORT; + return __inet_bind(sk, addr, addr_len, flags); #if IS_ENABLED(CONFIG_IPV6) } else if (addr->sa_family == AF_INET6) { if (addr_len < SIN6_LEN_RFC2133) return err; - if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0)) - return err; + if (((struct sockaddr_in6 *)addr)->sin6_port == htons(0)) + flags |= BIND_FORCE_ADDRESS_NO_PORT; /* ipv6_bpf_stub cannot be NULL, since it's called from * bpf_cgroup_inet6_connect hook and ipv6 is already loaded */ - return ipv6_bpf_stub->inet6_bind(sk, addr, addr_len, - BIND_FORCE_ADDRESS_NO_PORT); + return ipv6_bpf_stub->inet6_bind(sk, addr, addr_len, flags); #endif /* CONFIG_IPV6 */ } #endif /* CONFIG_INET */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 68e74b1b0f26..fcf0d12a407a 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -526,10 +526,12 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, err = -EADDRINUSE; goto out_release_sock; } - err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk); - if (err) { - inet->inet_saddr = inet->inet_rcv_saddr = 0; - goto out_release_sock; + if (!(flags & BIND_FROM_BPF)) { + err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk); + if (err) { + inet->inet_saddr = inet->inet_rcv_saddr = 0; + goto out_release_sock; + } } } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 552c2592b81c..771a462a8322 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -407,11 +407,13 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, err = -EADDRINUSE; goto out; } - err = BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk); - if (err) { - sk->sk_ipv6only = saved_ipv6only; - inet_reset_saddr(sk); - goto out; + if (!(flags & BIND_FROM_BPF)) { + err = BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk); + if (err) { + sk->sk_ipv6only = saved_ipv6only; + inet_reset_saddr(sk); + goto out; + } } } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index b3643e27e264..6e5e7caa3739 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1994,10 +1994,11 @@ union bpf_attr { * * This helper works for IPv4 and IPv6, TCP and UDP sockets. The * domain (*addr*\ **->sa_family**) must be **AF_INET** (or - * **AF_INET6**). Looking for a free port to bind to can be - * expensive, therefore binding to port is not permitted by the - * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively) - * must be set to zero. + * **AF_INET6**). It's advised to pass zero port (**sin_port** + * or **sin6_port**) which triggers IP_BIND_ADDRESS_NO_PORT-like + * behavior and lets the kernel efficiently pick up an unused + * port as long as 4-tuple is unique. Passing non-zero port might + * lead to degraded performance. * Return * 0 on success, or a negative error in case of failure. * diff --git a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c new file mode 100644 index 000000000000..47fbb20cb6a6 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include "cgroup_helpers.h" +#include "network_helpers.h" + +static int verify_port(int family, int fd, int expected) +{ + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); + __u16 port; + + if (getsockname(fd, (struct sockaddr *)&addr, &len)) { + log_err("Failed to get server addr"); + return -1; + } + + if (family == AF_INET) + port = ((struct sockaddr_in *)&addr)->sin_port; + else + port = ((struct sockaddr_in6 *)&addr)->sin6_port; + + if (ntohs(port) != expected) { + log_err("Unexpected port %d, expected %d", ntohs(port), + expected); + return -1; + } + + return 0; +} + +static int run_test(int cgroup_fd, int server_fd, int family, int type) +{ + struct bpf_prog_load_attr attr = { + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + }; + struct bpf_object *obj; + int expected_port; + int prog_fd; + int err; + int fd; + + if (family == AF_INET) { + attr.file = "./connect_force_port4.o"; + attr.expected_attach_type = BPF_CGROUP_INET4_CONNECT; + expected_port = 22222; + } else { + attr.file = "./connect_force_port6.o"; + attr.expected_attach_type = BPF_CGROUP_INET6_CONNECT; + expected_port = 22223; + } + + err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); + if (err) { + log_err("Failed to load BPF object"); + return -1; + } + + err = bpf_prog_attach(prog_fd, cgroup_fd, attr.expected_attach_type, + 0); + if (err) { + log_err("Failed to attach BPF program"); + goto close_bpf_object; + } + + fd = connect_to_fd(family, type, server_fd); + if (fd < 0) { + err = -1; + goto close_bpf_object; + } + + err = verify_port(family, fd, expected_port); + + close(fd); + +close_bpf_object: + bpf_object__close(obj); + return err; +} + +void test_connect_force_port(void) +{ + int server_fd, cgroup_fd; + + cgroup_fd = test__join_cgroup("/connect_force_port"); + if (CHECK_FAIL(cgroup_fd < 0)) + return; + + server_fd = start_server(AF_INET, SOCK_STREAM); + if (CHECK_FAIL(server_fd < 0)) + goto close_cgroup_fd; + CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_STREAM)); + close(server_fd); + + server_fd = start_server(AF_INET6, SOCK_STREAM); + if (CHECK_FAIL(server_fd < 0)) + goto close_cgroup_fd; + CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_STREAM)); + close(server_fd); + + server_fd = start_server(AF_INET, SOCK_DGRAM); + if (CHECK_FAIL(server_fd < 0)) + goto close_cgroup_fd; + CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_DGRAM)); + close(server_fd); + + server_fd = start_server(AF_INET6, SOCK_DGRAM); + if (CHECK_FAIL(server_fd < 0)) + goto close_cgroup_fd; + CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_DGRAM)); + close(server_fd); + +close_cgroup_fd: + close(cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/progs/connect_force_port4.c b/tools/testing/selftests/bpf/progs/connect_force_port4.c new file mode 100644 index 000000000000..1b8eb34b2db0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect_force_port4.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +#include + +#include +#include +#include +#include + +#include +#include + +char _license[] SEC("license") = "GPL"; +int _version SEC("version") = 1; + +SEC("cgroup/connect4") +int _connect4(struct bpf_sock_addr *ctx) +{ + struct sockaddr_in sa = {}; + + sa.sin_family = AF_INET; + sa.sin_port = bpf_htons(22222); + sa.sin_addr.s_addr = bpf_htonl(0x7f000001); /* 127.0.0.1 */ + + if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0) + return 0; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/connect_force_port6.c b/tools/testing/selftests/bpf/progs/connect_force_port6.c new file mode 100644 index 000000000000..ae6f7d750b4c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect_force_port6.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +#include + +#include +#include +#include +#include + +#include +#include + +char _license[] SEC("license") = "GPL"; +int _version SEC("version") = 1; + +SEC("cgroup/connect6") +int _connect6(struct bpf_sock_addr *ctx) +{ + struct sockaddr_in6 sa = {}; + + sa.sin6_family = AF_INET6; + sa.sin6_port = bpf_htons(22223); + sa.sin6_addr.s6_addr32[3] = bpf_htonl(1); /* ::1 */ + + if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0) + return 0; + + return 1; +} -- cgit v1.2.3 From 15d83c4d7cef5c067a8b075ce59e97df4f60706e Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:00 -0700 Subject: bpf: Allow loading of a bpf_iter program A bpf_iter program is a tracing program with attach type BPF_TRACE_ITER. The load attribute attach_btf_id is used by the verifier against a particular kernel function, which represents a target, e.g., __bpf_iter__bpf_map for target bpf_map which is implemented later. The program return value must be 0 or 1 for now. 0 : successful, except potential seq_file buffer overflow which is handled by seq_file reader. 1 : request to restart the same object In the future, other return values may be used for filtering or teminating the iterator. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175900.2474947-1-yhs@fb.com --- include/linux/bpf.h | 3 +++ include/uapi/linux/bpf.h | 1 + kernel/bpf/bpf_iter.c | 36 ++++++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 21 +++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 1 + 5 files changed, 62 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 40c78b86fe38..f28bdd714754 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1127,6 +1127,8 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); +#define BPF_ITER_FUNC_PREFIX "__bpf_iter__" + typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); @@ -1140,6 +1142,7 @@ struct bpf_iter_reg { int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const char *target); +bool bpf_iter_prog_supported(struct bpf_prog *prog); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6e5e7caa3739..c8a5325cc8d0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -218,6 +218,7 @@ enum bpf_attach_type { BPF_TRACE_FEXIT, BPF_MODIFY_RETURN, BPF_LSM_MAC, + BPF_TRACE_ITER, __MAX_BPF_ATTACH_TYPE }; diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 5a8119d17d14..dec182d8395a 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -12,6 +12,7 @@ struct bpf_iter_target_info { bpf_iter_init_seq_priv_t init_seq_private; bpf_iter_fini_seq_priv_t fini_seq_private; u32 seq_priv_size; + u32 btf_id; /* cached value */ }; static struct list_head targets = LIST_HEAD_INIT(targets); @@ -57,3 +58,38 @@ void bpf_iter_unreg_target(const char *target) WARN_ON(found == false); } + +static void cache_btf_id(struct bpf_iter_target_info *tinfo, + struct bpf_prog *prog) +{ + tinfo->btf_id = prog->aux->attach_btf_id; +} + +bool bpf_iter_prog_supported(struct bpf_prog *prog) +{ + const char *attach_fname = prog->aux->attach_func_name; + u32 prog_btf_id = prog->aux->attach_btf_id; + const char *prefix = BPF_ITER_FUNC_PREFIX; + struct bpf_iter_target_info *tinfo; + int prefix_len = strlen(prefix); + bool supported = false; + + if (strncmp(attach_fname, prefix, prefix_len)) + return false; + + mutex_lock(&targets_mutex); + list_for_each_entry(tinfo, &targets, list) { + if (tinfo->btf_id && tinfo->btf_id == prog_btf_id) { + supported = true; + break; + } + if (!strcmp(attach_fname + prefix_len, tinfo->target)) { + cache_btf_id(tinfo, prog); + supported = true; + break; + } + } + mutex_unlock(&targets_mutex); + + return supported; +} diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 70ad009577f8..d725ff7d11db 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7101,6 +7101,10 @@ static int check_return_code(struct bpf_verifier_env *env) return 0; range = tnum_const(0); break; + case BPF_PROG_TYPE_TRACING: + if (env->prog->expected_attach_type != BPF_TRACE_ITER) + return 0; + break; default: return 0; } @@ -10481,6 +10485,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) struct bpf_prog *tgt_prog = prog->aux->linked_prog; u32 btf_id = prog->aux->attach_btf_id; const char prefix[] = "btf_trace_"; + struct btf_func_model fmodel; int ret = 0, subprog = -1, i; struct bpf_trampoline *tr; const struct btf_type *t; @@ -10622,6 +10627,22 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) prog->aux->attach_func_proto = t; prog->aux->attach_btf_trace = true; return 0; + case BPF_TRACE_ITER: + if (!btf_type_is_func(t)) { + verbose(env, "attach_btf_id %u is not a function\n", + btf_id); + return -EINVAL; + } + t = btf_type_by_id(btf, t->type); + if (!btf_type_is_func_proto(t)) + return -EINVAL; + prog->aux->attach_func_name = tname; + prog->aux->attach_func_proto = t; + if (!bpf_iter_prog_supported(prog)) + return -EINVAL; + ret = btf_distill_func_proto(&env->log, btf, t, + tname, &fmodel); + return ret; default: if (!prog_extension) return -EINVAL; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6e5e7caa3739..c8a5325cc8d0 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -218,6 +218,7 @@ enum bpf_attach_type { BPF_TRACE_FEXIT, BPF_MODIFY_RETURN, BPF_LSM_MAC, + BPF_TRACE_ITER, __MAX_BPF_ATTACH_TYPE }; -- cgit v1.2.3 From de4e05cac46d206f9090051ef09930514bff73e4 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:01 -0700 Subject: bpf: Support bpf tracing/iter programs for BPF_LINK_CREATE Given a bpf program, the step to create an anonymous bpf iterator is: - create a bpf_iter_link, which combines bpf program and the target. In the future, there could be more information recorded in the link. A link_fd will be returned to the user space. - create an anonymous bpf iterator with the given link_fd. The bpf_iter_link can be pinned to bpffs mount file system to create a file based bpf iterator as well. The benefit to use of bpf_iter_link: - using bpf link simplifies design and implementation as bpf link is used for other tracing bpf programs. - for file based bpf iterator, bpf_iter_link provides a standard way to replace underlying bpf programs. - for both anonymous and free based iterators, bpf link query capability can be leveraged. The patch added support of tracing/iter programs for BPF_LINK_CREATE. A new link type BPF_LINK_TYPE_ITER is added to facilitate link querying. Currently, only prog_id is needed, so there is no additional in-kernel show_fdinfo() and fill_link_info() hook is needed for BPF_LINK_TYPE_ITER link. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175901.2475084-1-yhs@fb.com --- include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/bpf_iter.c | 62 ++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 14 ++++++++++ tools/include/uapi/linux/bpf.h | 1 + 6 files changed, 80 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f28bdd714754..e93d2d33c82c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1143,6 +1143,7 @@ struct bpf_iter_reg { int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const char *target); bool bpf_iter_prog_supported(struct bpf_prog *prog); +int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 8345cdf553b8..29d22752fc87 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -124,3 +124,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) #ifdef CONFIG_CGROUP_BPF BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup) #endif +BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c8a5325cc8d0..1e8dfff5d5d4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -229,6 +229,7 @@ enum bpf_link_type { BPF_LINK_TYPE_RAW_TRACEPOINT = 1, BPF_LINK_TYPE_TRACING = 2, BPF_LINK_TYPE_CGROUP = 3, + BPF_LINK_TYPE_ITER = 4, MAX_BPF_LINK_TYPE, }; diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index dec182d8395a..03f5832909db 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -15,6 +15,11 @@ struct bpf_iter_target_info { u32 btf_id; /* cached value */ }; +struct bpf_iter_link { + struct bpf_link link; + struct bpf_iter_target_info *tinfo; +}; + static struct list_head targets = LIST_HEAD_INIT(targets); static DEFINE_MUTEX(targets_mutex); @@ -93,3 +98,60 @@ bool bpf_iter_prog_supported(struct bpf_prog *prog) return supported; } + +static void bpf_iter_link_release(struct bpf_link *link) +{ +} + +static void bpf_iter_link_dealloc(struct bpf_link *link) +{ + struct bpf_iter_link *iter_link = + container_of(link, struct bpf_iter_link, link); + + kfree(iter_link); +} + +static const struct bpf_link_ops bpf_iter_link_lops = { + .release = bpf_iter_link_release, + .dealloc = bpf_iter_link_dealloc, +}; + +int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_link_primer link_primer; + struct bpf_iter_target_info *tinfo; + struct bpf_iter_link *link; + bool existed = false; + u32 prog_btf_id; + int err; + + if (attr->link_create.target_fd || attr->link_create.flags) + return -EINVAL; + + prog_btf_id = prog->aux->attach_btf_id; + mutex_lock(&targets_mutex); + list_for_each_entry(tinfo, &targets, list) { + if (tinfo->btf_id == prog_btf_id) { + existed = true; + break; + } + } + mutex_unlock(&targets_mutex); + if (!existed) + return -ENOENT; + + link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN); + if (!link) + return -ENOMEM; + + bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog); + link->tinfo = tinfo; + + err = bpf_link_prime(&link->link, &link_primer); + if (err) { + kfree(link); + return err; + } + + return bpf_link_settle(&link_primer); +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index bb1ab7da6103..6ffe2d8fb6c7 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2729,6 +2729,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: return BPF_PROG_TYPE_CGROUP_SOCKOPT; + case BPF_TRACE_ITER: + return BPF_PROG_TYPE_TRACING; default: return BPF_PROG_TYPE_UNSPEC; } @@ -3729,6 +3731,15 @@ err_put: return err; } +static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + if (attr->link_create.attach_type == BPF_TRACE_ITER && + prog->expected_attach_type == BPF_TRACE_ITER) + return bpf_iter_link_attach(attr, prog); + + return -EINVAL; +} + #define BPF_LINK_CREATE_LAST_FIELD link_create.flags static int link_create(union bpf_attr *attr) { @@ -3765,6 +3776,9 @@ static int link_create(union bpf_attr *attr) case BPF_PROG_TYPE_CGROUP_SOCKOPT: ret = cgroup_bpf_link_attach(attr, prog); break; + case BPF_PROG_TYPE_TRACING: + ret = tracing_bpf_link_attach(attr, prog); + break; default: ret = -EINVAL; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c8a5325cc8d0..1e8dfff5d5d4 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -229,6 +229,7 @@ enum bpf_link_type { BPF_LINK_TYPE_RAW_TRACEPOINT = 1, BPF_LINK_TYPE_TRACING = 2, BPF_LINK_TYPE_CGROUP = 3, + BPF_LINK_TYPE_ITER = 4, MAX_BPF_LINK_TYPE, }; -- cgit v1.2.3 From ac51d99bf81caac8d8881fe52098948110d0de68 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:05 -0700 Subject: bpf: Create anonymous bpf iterator A new bpf command BPF_ITER_CREATE is added. The anonymous bpf iterator is seq_file based. The seq_file private data are referenced by targets. The bpf_iter infrastructure allocated additional space at seq_file->private before the space used by targets to store some meta data, e.g., prog: prog to run session_id: an unique id for each opened seq_file seq_num: how many times bpf programs are queried in this session done_stop: an internal state to decide whether bpf program should be called in seq_ops->stop() or not The seq_num will start from 0 for valid objects. The bpf program may see the same seq_num more than once if - seq_file buffer overflow happens and the same object is retried by bpf_seq_read(), or - the bpf program explicitly requests a retry of the same object Since module is not supported for bpf_iter, all target registeration happens at __init time, so there is no need to change bpf_iter_unreg_target() as it is used mostly in error path of the init function at which time no bpf iterators have been created yet. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175905.2475770-1-yhs@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 6 ++ kernel/bpf/bpf_iter.c | 129 +++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 26 +++++++++ tools/include/uapi/linux/bpf.h | 6 ++ 5 files changed, 168 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e93d2d33c82c..80b1b9d8a638 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1144,6 +1144,7 @@ int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const char *target); bool bpf_iter_prog_supported(struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int bpf_iter_new_fd(struct bpf_link *link); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1e8dfff5d5d4..708763f702e1 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -116,6 +116,7 @@ enum bpf_cmd { BPF_LINK_GET_FD_BY_ID, BPF_LINK_GET_NEXT_ID, BPF_ENABLE_STATS, + BPF_ITER_CREATE, }; enum bpf_map_type { @@ -614,6 +615,11 @@ union bpf_attr { __u32 type; } enable_stats; + struct { /* struct used by BPF_ITER_CREATE command */ + __u32 link_fd; + __u32 flags; + } iter_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 832973ee80fa..e7129b57865f 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -2,6 +2,7 @@ /* Copyright (c) 2020 Facebook */ #include +#include #include #include @@ -20,12 +21,24 @@ struct bpf_iter_link { struct bpf_iter_target_info *tinfo; }; +struct bpf_iter_priv_data { + struct bpf_iter_target_info *tinfo; + struct bpf_prog *prog; + u64 session_id; + u64 seq_num; + bool done_stop; + u8 target_private[] __aligned(8); +}; + static struct list_head targets = LIST_HEAD_INIT(targets); static DEFINE_MUTEX(targets_mutex); /* protect bpf_iter_link changes */ static DEFINE_MUTEX(link_mutex); +/* incremented on every opened seq_file */ +static atomic64_t session_id; + /* bpf_seq_read, a customized and simpler version for bpf iterator. * no_llseek is assumed for this file. * The following are differences from seq_read(): @@ -149,6 +162,33 @@ done: return copied; } +static int iter_release(struct inode *inode, struct file *file) +{ + struct bpf_iter_priv_data *iter_priv; + struct seq_file *seq; + + seq = file->private_data; + if (!seq) + return 0; + + iter_priv = container_of(seq->private, struct bpf_iter_priv_data, + target_private); + + if (iter_priv->tinfo->fini_seq_private) + iter_priv->tinfo->fini_seq_private(seq->private); + + bpf_prog_put(iter_priv->prog); + seq->private = iter_priv; + + return seq_release_private(inode, file); +} + +static const struct file_operations bpf_iter_fops = { + .llseek = no_llseek, + .read = bpf_seq_read, + .release = iter_release, +}; + int bpf_iter_reg_target(struct bpf_iter_reg *reg_info) { struct bpf_iter_target_info *tinfo; @@ -309,3 +349,92 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) return bpf_link_settle(&link_primer); } + +static void init_seq_meta(struct bpf_iter_priv_data *priv_data, + struct bpf_iter_target_info *tinfo, + struct bpf_prog *prog) +{ + priv_data->tinfo = tinfo; + priv_data->prog = prog; + priv_data->session_id = atomic64_inc_return(&session_id); + priv_data->seq_num = 0; + priv_data->done_stop = false; +} + +static int prepare_seq_file(struct file *file, struct bpf_iter_link *link) +{ + struct bpf_iter_priv_data *priv_data; + struct bpf_iter_target_info *tinfo; + struct bpf_prog *prog; + u32 total_priv_dsize; + struct seq_file *seq; + int err = 0; + + mutex_lock(&link_mutex); + prog = link->link.prog; + bpf_prog_inc(prog); + mutex_unlock(&link_mutex); + + tinfo = link->tinfo; + total_priv_dsize = offsetof(struct bpf_iter_priv_data, target_private) + + tinfo->seq_priv_size; + priv_data = __seq_open_private(file, tinfo->seq_ops, total_priv_dsize); + if (!priv_data) { + err = -ENOMEM; + goto release_prog; + } + + if (tinfo->init_seq_private) { + err = tinfo->init_seq_private(priv_data->target_private); + if (err) + goto release_seq_file; + } + + init_seq_meta(priv_data, tinfo, prog); + seq = file->private_data; + seq->private = priv_data->target_private; + + return 0; + +release_seq_file: + seq_release_private(file->f_inode, file); + file->private_data = NULL; +release_prog: + bpf_prog_put(prog); + return err; +} + +int bpf_iter_new_fd(struct bpf_link *link) +{ + struct file *file; + unsigned int flags; + int err, fd; + + if (link->ops != &bpf_iter_link_lops) + return -EINVAL; + + flags = O_RDONLY | O_CLOEXEC; + fd = get_unused_fd_flags(flags); + if (fd < 0) + return fd; + + file = anon_inode_getfile("bpf_iter", &bpf_iter_fops, NULL, flags); + if (IS_ERR(file)) { + err = PTR_ERR(file); + goto free_fd; + } + + err = prepare_seq_file(file, + container_of(link, struct bpf_iter_link, link)); + if (err) + goto free_file; + + fd_install(fd, file); + return fd; + +free_file: + fput(file); +free_fd: + put_unused_fd(fd); + return err; +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 6ffe2d8fb6c7..a293e88ee01a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3941,6 +3941,29 @@ static int bpf_enable_stats(union bpf_attr *attr) return -EINVAL; } +#define BPF_ITER_CREATE_LAST_FIELD iter_create.flags + +static int bpf_iter_create(union bpf_attr *attr) +{ + struct bpf_link *link; + int err; + + if (CHECK_ATTR(BPF_ITER_CREATE)) + return -EINVAL; + + if (attr->iter_create.flags) + return -EINVAL; + + link = bpf_link_get_from_fd(attr->iter_create.link_fd); + if (IS_ERR(link)) + return PTR_ERR(link); + + err = bpf_iter_new_fd(link); + bpf_link_put(link); + + return err; +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr; @@ -4068,6 +4091,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_ENABLE_STATS: err = bpf_enable_stats(&attr); break; + case BPF_ITER_CREATE: + err = bpf_iter_create(&attr); + break; default: err = -EINVAL; break; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1e8dfff5d5d4..708763f702e1 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -116,6 +116,7 @@ enum bpf_cmd { BPF_LINK_GET_FD_BY_ID, BPF_LINK_GET_NEXT_ID, BPF_ENABLE_STATS, + BPF_ITER_CREATE, }; enum bpf_map_type { @@ -614,6 +615,11 @@ union bpf_attr { __u32 type; } enable_stats; + struct { /* struct used by BPF_ITER_CREATE command */ + __u32 link_fd; + __u32 flags; + } iter_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF -- cgit v1.2.3 From 492e639f0c222784e2e0f121966375f641c61b15 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:14 -0700 Subject: bpf: Add bpf_seq_printf and bpf_seq_write helpers Two helpers bpf_seq_printf and bpf_seq_write, are added for writing data to the seq_file buffer. bpf_seq_printf supports common format string flag/width/type fields so at least I can get identical results for netlink and ipv6_route targets. For bpf_seq_printf and bpf_seq_write, return value -EOVERFLOW specifically indicates a write failure due to overflow, which means the object will be repeated in the next bpf invocation if object collection stays the same. Note that if the object collection is changed, depending how collection traversal is done, even if the object still in the collection, it may not be visited. For bpf_seq_printf, format %s, %p{i,I}{4,6} needs to read kernel memory. Reading kernel memory may fail in the following two cases: - invalid kernel address, or - valid kernel address but requiring a major fault If reading kernel memory failed, the %s string will be an empty string and %p{i,I}{4,6} will be all 0. Not returning error to bpf program is consistent with what bpf_trace_printk() does for now. bpf_seq_printf may return -EBUSY meaning that internal percpu buffer for memory copy of strings or other pointees is not available. Bpf program can return 1 to indicate it wants the same object to be repeated. Right now, this should not happen on no-RT kernels since migrate_disable(), which guards bpf prog call, calls preempt_disable(). Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175914.2476661-1-yhs@fb.com --- include/uapi/linux/bpf.h | 39 +++++++- kernel/trace/bpf_trace.c | 214 +++++++++++++++++++++++++++++++++++++++++ scripts/bpf_helpers_doc.py | 2 + tools/include/uapi/linux/bpf.h | 39 +++++++- 4 files changed, 292 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 708763f702e1..9d1932e23cec 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3077,6 +3077,41 @@ union bpf_attr { * See: clock_gettime(CLOCK_BOOTTIME) * Return * Current *ktime*. + * + * int bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * seq_printf uses seq_file seq_printf() to print out the format string. + * The *m* represents the seq_file. The *fmt* and *fmt_size* are for + * the format string itself. The *data* and *data_len* are format string + * arguments. The *data* are a u64 array and corresponding format string + * values are stored in the array. For strings and pointers where pointees + * are accessed, only the pointer values are stored in the *data* array. + * The *data_len* is the *data* size in term of bytes. + * + * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. + * Reading kernel memory may fail due to either invalid address or + * valid address but requiring a major memory fault. If reading kernel memory + * fails, the string for **%s** will be an empty string, and the ip + * address for **%p{i,I}{4,6}** will be 0. Not returning error to + * bpf program is consistent with what bpf_trace_printk() does for now. + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EBUSY** Percpu memory copy buffer is busy, can try again + * by returning 1 from bpf program. + * * **-EINVAL** Invalid arguments, or invalid/unsupported formats. + * * **-E2BIG** Too many format specifiers. + * * **-EOVERFLOW** Overflow happens, the same object will be tried again. + * + * int bpf_seq_write(struct seq_file *m, const void *data, u32 len) + * Description + * seq_write uses seq_file seq_write() to write the data. + * The *m* represents the seq_file. The *data* and *len* represent the + * data to write in bytes. + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EOVERFLOW** Overflow happens, the same object will be tried again. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3204,7 +3239,9 @@ union bpf_attr { FN(get_netns_cookie), \ FN(get_current_ancestor_cgroup_id), \ FN(sk_assign), \ - FN(ktime_get_boot_ns), + FN(ktime_get_boot_ns), \ + FN(seq_printf), \ + FN(seq_write), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index e875c95d3ced..d961428fb5b6 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -457,6 +457,212 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } +#define MAX_SEQ_PRINTF_VARARGS 12 +#define MAX_SEQ_PRINTF_MAX_MEMCPY 6 +#define MAX_SEQ_PRINTF_STR_LEN 128 + +struct bpf_seq_printf_buf { + char buf[MAX_SEQ_PRINTF_MAX_MEMCPY][MAX_SEQ_PRINTF_STR_LEN]; +}; +static DEFINE_PER_CPU(struct bpf_seq_printf_buf, bpf_seq_printf_buf); +static DEFINE_PER_CPU(int, bpf_seq_printf_buf_used); + +BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, + const void *, data, u32, data_len) +{ + int err = -EINVAL, fmt_cnt = 0, memcpy_cnt = 0; + int i, buf_used, copy_size, num_args; + u64 params[MAX_SEQ_PRINTF_VARARGS]; + struct bpf_seq_printf_buf *bufs; + const u64 *args = data; + + buf_used = this_cpu_inc_return(bpf_seq_printf_buf_used); + if (WARN_ON_ONCE(buf_used > 1)) { + err = -EBUSY; + goto out; + } + + bufs = this_cpu_ptr(&bpf_seq_printf_buf); + + /* + * bpf_check()->check_func_arg()->check_stack_boundary() + * guarantees that fmt points to bpf program stack, + * fmt_size bytes of it were initialized and fmt_size > 0 + */ + if (fmt[--fmt_size] != 0) + goto out; + + if (data_len & 7) + goto out; + + for (i = 0; i < fmt_size; i++) { + if (fmt[i] == '%') { + if (fmt[i + 1] == '%') + i++; + else if (!data || !data_len) + goto out; + } + } + + num_args = data_len / 8; + + /* check format string for allowed specifiers */ + for (i = 0; i < fmt_size; i++) { + /* only printable ascii for now. */ + if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) { + err = -EINVAL; + goto out; + } + + if (fmt[i] != '%') + continue; + + if (fmt[i + 1] == '%') { + i++; + continue; + } + + if (fmt_cnt >= MAX_SEQ_PRINTF_VARARGS) { + err = -E2BIG; + goto out; + } + + if (fmt_cnt >= num_args) { + err = -EINVAL; + goto out; + } + + /* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */ + i++; + + /* skip optional "[0 +-][num]" width formating field */ + while (fmt[i] == '0' || fmt[i] == '+' || fmt[i] == '-' || + fmt[i] == ' ') + i++; + if (fmt[i] >= '1' && fmt[i] <= '9') { + i++; + while (fmt[i] >= '0' && fmt[i] <= '9') + i++; + } + + if (fmt[i] == 's') { + /* try our best to copy */ + if (memcpy_cnt >= MAX_SEQ_PRINTF_MAX_MEMCPY) { + err = -E2BIG; + goto out; + } + + err = strncpy_from_unsafe(bufs->buf[memcpy_cnt], + (void *) (long) args[fmt_cnt], + MAX_SEQ_PRINTF_STR_LEN); + if (err < 0) + bufs->buf[memcpy_cnt][0] = '\0'; + params[fmt_cnt] = (u64)(long)bufs->buf[memcpy_cnt]; + + fmt_cnt++; + memcpy_cnt++; + continue; + } + + if (fmt[i] == 'p') { + if (fmt[i + 1] == 0 || + fmt[i + 1] == 'K' || + fmt[i + 1] == 'x') { + /* just kernel pointers */ + params[fmt_cnt] = args[fmt_cnt]; + fmt_cnt++; + continue; + } + + /* only support "%pI4", "%pi4", "%pI6" and "%pi6". */ + if (fmt[i + 1] != 'i' && fmt[i + 1] != 'I') { + err = -EINVAL; + goto out; + } + if (fmt[i + 2] != '4' && fmt[i + 2] != '6') { + err = -EINVAL; + goto out; + } + + if (memcpy_cnt >= MAX_SEQ_PRINTF_MAX_MEMCPY) { + err = -E2BIG; + goto out; + } + + + copy_size = (fmt[i + 2] == '4') ? 4 : 16; + + err = probe_kernel_read(bufs->buf[memcpy_cnt], + (void *) (long) args[fmt_cnt], + copy_size); + if (err < 0) + memset(bufs->buf[memcpy_cnt], 0, copy_size); + params[fmt_cnt] = (u64)(long)bufs->buf[memcpy_cnt]; + + i += 2; + fmt_cnt++; + memcpy_cnt++; + continue; + } + + if (fmt[i] == 'l') { + i++; + if (fmt[i] == 'l') + i++; + } + + if (fmt[i] != 'i' && fmt[i] != 'd' && + fmt[i] != 'u' && fmt[i] != 'x') { + err = -EINVAL; + goto out; + } + + params[fmt_cnt] = args[fmt_cnt]; + fmt_cnt++; + } + + /* Maximumly we can have MAX_SEQ_PRINTF_VARARGS parameter, just give + * all of them to seq_printf(). + */ + seq_printf(m, fmt, params[0], params[1], params[2], params[3], + params[4], params[5], params[6], params[7], params[8], + params[9], params[10], params[11]); + + err = seq_has_overflowed(m) ? -EOVERFLOW : 0; +out: + this_cpu_dec(bpf_seq_printf_buf_used); + return err; +} + +static int bpf_seq_printf_btf_ids[5]; +static const struct bpf_func_proto bpf_seq_printf_proto = { + .func = bpf_seq_printf, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_PTR_TO_MEM_OR_NULL, + .arg5_type = ARG_CONST_SIZE_OR_ZERO, + .btf_id = bpf_seq_printf_btf_ids, +}; + +BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len) +{ + return seq_write(m, data, len) ? -EOVERFLOW : 0; +} + +static int bpf_seq_write_btf_ids[5]; +static const struct bpf_func_proto bpf_seq_write_proto = { + .func = bpf_seq_write, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .btf_id = bpf_seq_write_btf_ids, +}; + static __always_inline int get_map_perf_counter(struct bpf_map *map, u64 flags, u64 *value, u64 *enabled, u64 *running) @@ -1226,6 +1432,14 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_xdp_output: return &bpf_xdp_output_proto; #endif + case BPF_FUNC_seq_printf: + return prog->expected_attach_type == BPF_TRACE_ITER ? + &bpf_seq_printf_proto : + NULL; + case BPF_FUNC_seq_write: + return prog->expected_attach_type == BPF_TRACE_ITER ? + &bpf_seq_write_proto : + NULL; default: return raw_tp_prog_func_proto(func_id, prog); } diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index f43d193aff3a..ded304c96a05 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -414,6 +414,7 @@ class PrinterHelpers(Printer): 'struct sk_reuseport_md', 'struct sockaddr', 'struct tcphdr', + 'struct seq_file', 'struct __sk_buff', 'struct sk_msg_md', @@ -450,6 +451,7 @@ class PrinterHelpers(Printer): 'struct sk_reuseport_md', 'struct sockaddr', 'struct tcphdr', + 'struct seq_file', } mapped_types = { 'u8': '__u8', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 708763f702e1..9d1932e23cec 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3077,6 +3077,41 @@ union bpf_attr { * See: clock_gettime(CLOCK_BOOTTIME) * Return * Current *ktime*. + * + * int bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * seq_printf uses seq_file seq_printf() to print out the format string. + * The *m* represents the seq_file. The *fmt* and *fmt_size* are for + * the format string itself. The *data* and *data_len* are format string + * arguments. The *data* are a u64 array and corresponding format string + * values are stored in the array. For strings and pointers where pointees + * are accessed, only the pointer values are stored in the *data* array. + * The *data_len* is the *data* size in term of bytes. + * + * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. + * Reading kernel memory may fail due to either invalid address or + * valid address but requiring a major memory fault. If reading kernel memory + * fails, the string for **%s** will be an empty string, and the ip + * address for **%p{i,I}{4,6}** will be 0. Not returning error to + * bpf program is consistent with what bpf_trace_printk() does for now. + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EBUSY** Percpu memory copy buffer is busy, can try again + * by returning 1 from bpf program. + * * **-EINVAL** Invalid arguments, or invalid/unsupported formats. + * * **-E2BIG** Too many format specifiers. + * * **-EOVERFLOW** Overflow happens, the same object will be tried again. + * + * int bpf_seq_write(struct seq_file *m, const void *data, u32 len) + * Description + * seq_write uses seq_file seq_write() to write the data. + * The *m* represents the seq_file. The *data* and *len* represent the + * data to write in bytes. + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EOVERFLOW** Overflow happens, the same object will be tried again. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3204,7 +3239,9 @@ union bpf_attr { FN(get_netns_cookie), \ FN(get_current_ancestor_cgroup_id), \ FN(sk_assign), \ - FN(ktime_get_boot_ns), + FN(ktime_get_boot_ns), \ + FN(seq_printf), \ + FN(seq_write), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call -- cgit v1.2.3 From 11ca3c4261cdb4e2f33e32daf6447f8185843317 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 10 May 2020 21:12:33 +0200 Subject: net: ethtool: netlink: Add support for triggering a cable test Add new ethtool netlink calls to trigger the starting of a PHY cable test. Add Kconfig'ury to ETHTOOL_NETLINK so that PHYLIB is not a module when ETHTOOL_NETLINK is builtin, which would result in kernel linking errors. v2: Remove unwanted white space change Remove ethnl_cable_test_act_ops and use doit handler Rename cable_test_set_policy cable_test_act_policy Remove ETHTOOL_MSG_CABLE_TEST_ACT_REPLY v3: Remove ETHTOOL_MSG_CABLE_TEST_ACT_REPLY from documentation Remove unused cable_test_get_policy Add Reviewed-by tags v4: Remove unwanted blank line Signed-off-by: Andrew Lunn Reviewed-by: Michal Kubecek Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 16 ++++++++- include/uapi/linux/ethtool_netlink.h | 12 +++++++ net/Kconfig | 1 + net/ethtool/Makefile | 2 +- net/ethtool/cabletest.c | 54 ++++++++++++++++++++++++++++ net/ethtool/netlink.c | 5 +++ net/ethtool/netlink.h | 1 + 7 files changed, 89 insertions(+), 2 deletions(-) create mode 100644 net/ethtool/cabletest.c (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 8f5cefc539cf..a8731d33d0c9 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -204,6 +204,7 @@ Userspace to kernel: ``ETHTOOL_MSG_EEE_GET`` get EEE settings ``ETHTOOL_MSG_EEE_SET`` set EEE settings ``ETHTOOL_MSG_TSINFO_GET`` get timestamping info + ``ETHTOOL_MSG_CABLE_TEST_ACT`` action start cable test ===================================== ================================ Kernel to userspace: @@ -958,13 +959,25 @@ Kernel response contents: is no special value for this case). The bitset attributes are omitted if they would be empty (no bit set). +CABLE_TEST +========== + +Start a cable test. + +Request contents: + + ==================================== ====== ========================== + ``ETHTOOL_A_CABLE_TEST_HEADER`` nested request header + ==================================== ====== ========================== + Request translation =================== The following table maps ioctl commands to netlink commands providing their functionality. Entries with "n/a" in right column are commands which do not -have their netlink replacement yet. +have their netlink replacement yet. Entries which "n/a" in the left column +are netlink only. =================================== ===================================== ioctl command netlink command @@ -1053,4 +1066,5 @@ have their netlink replacement yet. ``ETHTOOL_PHY_STUNABLE`` n/a ``ETHTOOL_GFECPARAM`` n/a ``ETHTOOL_SFECPARAM`` n/a + n/a ''ETHTOOL_MSG_CABLE_TEST_ACT'' =================================== ===================================== diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index bf1d310e20bc..6bfd648c32cf 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -39,6 +39,7 @@ enum { ETHTOOL_MSG_EEE_GET, ETHTOOL_MSG_EEE_SET, ETHTOOL_MSG_TSINFO_GET, + ETHTOOL_MSG_CABLE_TEST_ACT, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -405,6 +406,17 @@ enum { ETHTOOL_A_TSINFO_MAX = (__ETHTOOL_A_TSINFO_CNT - 1) }; +/* CABLE TEST */ + +enum { + ETHTOOL_A_CABLE_TEST_UNSPEC, + ETHTOOL_A_CABLE_TEST_HEADER, /* nest - _A_HEADER_* */ + + /* add new constants above here */ + __ETHTOOL_A_CABLE_TEST_CNT, + ETHTOOL_A_CABLE_TEST_MAX = __ETHTOOL_A_CABLE_TEST_CNT - 1 +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/net/Kconfig b/net/Kconfig index c5ba2d180c43..5c524c6ee75d 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -455,6 +455,7 @@ config FAILOVER config ETHTOOL_NETLINK bool "Netlink interface for ethtool" default y + depends on PHYLIB=y || PHYLIB=n help An alternative userspace interface for ethtool based on generic netlink. It provides better extensibility and some new features, diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 6c360c9c9370..0c2b94f20499 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -6,4 +6,4 @@ obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ - channels.o coalesce.o pause.o eee.o tsinfo.o + channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c new file mode 100644 index 000000000000..aeb6672a46d0 --- /dev/null +++ b/net/ethtool/cabletest.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include "netlink.h" +#include "common.h" + +/* CABLE_TEST_ACT */ + +static const struct nla_policy +cable_test_act_policy[ETHTOOL_A_CABLE_TEST_MAX + 1] = { + [ETHTOOL_A_CABLE_TEST_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_CABLE_TEST_HEADER] = { .type = NLA_NESTED }, +}; + +int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *tb[ETHTOOL_A_CABLE_TEST_MAX + 1]; + struct ethnl_req_info req_info = {}; + struct net_device *dev; + int ret; + + ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, + ETHTOOL_A_CABLE_TEST_MAX, + cable_test_act_policy, info->extack); + if (ret < 0) + return ret; + + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_CABLE_TEST_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + + dev = req_info.dev; + if (!dev->phydev) { + ret = -EOPNOTSUPP; + goto out_dev_put; + } + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + + ret = phy_start_cable_test(dev->phydev, info->extack); + + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); +out_dev_put: + dev_put(dev); + return ret; +} diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 0c772318c023..b9c9ddf408fe 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -839,6 +839,11 @@ static const struct genl_ops ethtool_genl_ops[] = { .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, }, + { + .cmd = ETHTOOL_MSG_CABLE_TEST_ACT, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_act_cable_test, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 81b8fa020bcb..bd7df592db2f 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -357,5 +357,6 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info); int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info); int ethnl_set_pause(struct sk_buff *skb, struct genl_info *info); int ethnl_set_eee(struct sk_buff *skb, struct genl_info *info); +int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info); #endif /* _NET_ETHTOOL_NETLINK_H */ -- cgit v1.2.3 From b28efb930ba5a7c263826fe02e13e1b6eadb5559 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 10 May 2020 21:12:34 +0200 Subject: net: ethtool: Add attributes for cable test reports Add the attributes needed to report cable test results to userspace. The reports are expected to be per twisted pair. A nested property per pair can report the result of the cable test. A nested property can also report the length of the cable to any fault. v2: Grammar fixes Change length from u16 to u32 s/DEV/HEADER/g Add status attributes Rename pairs from numbers to letters. v3: Fixed example in document Add ETHTOOL_A_CABLE_NEST_* enum Add ETHTOOL_MSG_CABLE_TEST_NTF to documentation Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Michal Kubecek Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 41 +++++++++++++++++++ include/uapi/linux/ethtool_netlink.h | 59 ++++++++++++++++++++++++++++ 2 files changed, 100 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index a8731d33d0c9..eed46b6aa07d 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -236,6 +236,7 @@ Kernel to userspace: ``ETHTOOL_MSG_EEE_GET_REPLY`` EEE settings ``ETHTOOL_MSG_EEE_NTF`` EEE settings ``ETHTOOL_MSG_TSINFO_GET_REPLY`` timestamping info + ``ETHTOOL_MSG_CABLE_TEST_NTF`` Cable test results ===================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -970,6 +971,46 @@ Request contents: ``ETHTOOL_A_CABLE_TEST_HEADER`` nested request header ==================================== ====== ========================== +Notification contents: + +An Ethernet cable typically contains 1, 2 or 4 pairs. The length of +the pair can only be measured when there is a fault in the pair and +hence a reflection. Information about the fault may not be available, +depending on the specific hardware. Hence the contents of the notify +message are mostly optional. The attributes can be repeated an +arbitrary number of times, in an arbitrary order, for an arbitrary +number of pairs. + +The example shows the notification sent when the test is completed for +a T2 cable, i.e. two pairs. One pair is OK and hence has no length +information. The second pair has a fault and does have length +information. + + +---------------------------------------------+--------+---------------------+ + | ``ETHTOOL_A_CABLE_TEST_HEADER`` | nested | reply header | + +---------------------------------------------+--------+---------------------+ + | ``ETHTOOL_A_CABLE_TEST_STATUS`` | u8 | completed | + +---------------------------------------------+--------+---------------------+ + | ``ETHTOOL_A_CABLE_TEST_NTF_NEST`` | nested | all the results | + +-+-------------------------------------------+--------+---------------------+ + | | ``ETHTOOL_A_CABLE_NEST_RESULT`` | nested | cable test result | + +-+-+-----------------------------------------+--------+---------------------+ + | | | ``ETHTOOL_A_CABLE_RESULTS_PAIR`` | u8 | pair number | + +-+-+-----------------------------------------+--------+---------------------+ + | | | ``ETHTOOL_A_CABLE_RESULTS_CODE`` | u8 | result code | + +-+-+-----------------------------------------+--------+---------------------+ + | | ``ETHTOOL_A_CABLE_NEST_RESULT`` | nested | cable test results | + +-+-+-----------------------------------------+--------+---------------------+ + | | | ``ETHTOOL_A_CABLE_RESULTS_PAIR`` | u8 | pair number | + +-+-+-----------------------------------------+--------+---------------------+ + | | | ``ETHTOOL_A_CABLE_RESULTS_CODE`` | u8 | result code | + +-+-+-----------------------------------------+--------+---------------------+ + | | ``ETHTOOL_A_CABLE_NEST_FAULT_LENGTH`` | nested | cable length | + +-+-+-----------------------------------------+--------+---------------------+ + | | | ``ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR`` | u8 | pair number | + +-+-+-----------------------------------------+--------+---------------------+ + | | | ``ETHTOOL_A_CABLE_FAULT_LENGTH_CM`` | u32 | length in cm | + +-+-+-----------------------------------------+--------+---------------------+ Request translation =================== diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 6bfd648c32cf..2881af411f76 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -75,6 +75,7 @@ enum { ETHTOOL_MSG_EEE_GET_REPLY, ETHTOOL_MSG_EEE_NTF, ETHTOOL_MSG_TSINFO_GET_REPLY, + ETHTOOL_MSG_CABLE_TEST_NTF, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -417,6 +418,64 @@ enum { ETHTOOL_A_CABLE_TEST_MAX = __ETHTOOL_A_CABLE_TEST_CNT - 1 }; +/* CABLE TEST NOTIFY */ +enum { + ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC, + ETHTOOL_A_CABLE_RESULT_CODE_OK, + ETHTOOL_A_CABLE_RESULT_CODE_OPEN, + ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT, + ETHTOOL_A_CABLE_RESULT_CODE_CROSS_SHORT, +}; + +enum { + ETHTOOL_A_CABLE_PAIR_A, + ETHTOOL_A_CABLE_PAIR_B, + ETHTOOL_A_CABLE_PAIR_C, + ETHTOOL_A_CABLE_PAIR_D, +}; + +enum { + ETHTOOL_A_CABLE_RESULT_UNSPEC, + ETHTOOL_A_CABLE_RESULT_PAIR, /* u8 ETHTOOL_A_CABLE_PAIR_ */ + ETHTOOL_A_CABLE_RESULT_CODE, /* u8 ETHTOOL_A_CABLE_RESULT_CODE_ */ + + __ETHTOOL_A_CABLE_RESULT_CNT, + ETHTOOL_A_CABLE_RESULT_MAX = (__ETHTOOL_A_CABLE_RESULT_CNT - 1) +}; + +enum { + ETHTOOL_A_CABLE_FAULT_LENGTH_UNSPEC, + ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR, /* u8 ETHTOOL_A_CABLE_PAIR_ */ + ETHTOOL_A_CABLE_FAULT_LENGTH_CM, /* u32 */ + + __ETHTOOL_A_CABLE_FAULT_LENGTH_CNT, + ETHTOOL_A_CABLE_FAULT_LENGTH_MAX = (__ETHTOOL_A_CABLE_FAULT_LENGTH_CNT - 1) +}; + +enum { + ETHTOOL_A_CABLE_TEST_NTF_STATUS_UNSPEC, + ETHTOOL_A_CABLE_TEST_NTF_STATUS_STARTED, + ETHTOOL_A_CABLE_TEST_NTF_STATUS_COMPLETED +}; + +enum { + ETHTOOL_A_CABLE_NEST_UNSPEC, + ETHTOOL_A_CABLE_NEST_RESULT, /* nest - ETHTOOL_A_CABLE_RESULT_ */ + ETHTOOL_A_CABLE_NEST_FAULT_LENGTH, /* nest - ETHTOOL_A_CABLE_FAULT_LENGTH_ */ + __ETHTOOL_A_CABLE_NEST_CNT, + ETHTOOL_A_CABLE_NEST_MAX = (__ETHTOOL_A_CABLE_NEST_CNT - 1) +}; + +enum { + ETHTOOL_A_CABLE_TEST_NTF_UNSPEC, + ETHTOOL_A_CABLE_TEST_NTF_HEADER, /* nest - ETHTOOL_A_HEADER_* */ + ETHTOOL_A_CABLE_TEST_NTF_STATUS, /* u8 - _STARTED/_COMPLETE */ + ETHTOOL_A_CABLE_TEST_NTF_NEST, /* nest - of results: */ + + __ETHTOOL_A_CABLE_TEST_NTF_CNT, + ETHTOOL_A_CABLE_TEST_NTF_MAX = (__ETHTOOL_A_CABLE_TEST_NTF_CNT - 1) +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 -- cgit v1.2.3 From 734e5e4e268f792d514ec2313792f30ec5f6c94f Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Tue, 5 May 2020 22:13:06 +0200 Subject: rtc: add new VL flag for backup switchover A new flag RTC_VL_BACKUP_SWITCH means that a backup switchover happened since last flag clear. Link: https://lore.kernel.org/r/20200505201310.255145-1-alexandre.belloni@bootlin.com Signed-off-by: Alexandre Belloni --- include/uapi/linux/rtc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index 83bba58d47f4..fa9aff91cbf2 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -99,6 +99,7 @@ struct rtc_pll_info { #define RTC_VL_BACKUP_LOW _BITUL(1) /* Backup voltage is low */ #define RTC_VL_BACKUP_EMPTY _BITUL(2) /* Backup empty or not present */ #define RTC_VL_ACCURACY_LOW _BITUL(3) /* Voltage is low, RTC accuracy is reduced */ +#define RTC_VL_BACKUP_SWITCH _BITUL(4) /* Backup switchover happened */ #define RTC_VL_READ _IOR('p', 0x13, unsigned int) /* Voltage low detection */ #define RTC_VL_CLR _IO('p', 0x14) /* Clear voltage low information */ -- cgit v1.2.3 From ab8d78093dfa2e7820ca0c28dda9142aa771c510 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Mon, 11 May 2020 17:15:35 +0100 Subject: bpf: Minor fixes to BPF helpers documentation Minor improvements to the documentation for BPF helpers: * Fix formatting for the description of "bpf_socket" for bpf_getsockopt() and bpf_setsockopt(), thus suppressing two warnings from rst2man about "Unexpected indentation". * Fix formatting for return values for bpf_sk_assign() and seq_file helpers. * Fix and harmonise formatting, in particular for function/struct names. * Remove blank lines before "Return:" sections. * Replace tabs found in the middle of text lines. * Fix typos. * Add a note to the footer (in Python script) about "bpftool feature probe", including for listing features available to unprivileged users, and add a reference to bpftool man page. Thanks to Florian for reporting two typos (duplicated words). Signed-off-by: Quentin Monnet Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200511161536.29853-4-quentin@isovalent.com --- include/uapi/linux/bpf.h | 109 ++++++++++++++++++++++++--------------------- scripts/bpf_helpers_doc.py | 6 +++ 2 files changed, 65 insertions(+), 50 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9d1932e23cec..bfb31c1be219 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -675,8 +675,8 @@ union bpf_attr { * For tracing programs, safely attempt to read *size* bytes from * kernel space address *unsafe_ptr* and store the data in *dst*. * - * Generally, use bpf_probe_read_user() or bpf_probe_read_kernel() - * instead. + * Generally, use **bpf_probe_read_user**\ () or + * **bpf_probe_read_kernel**\ () instead. * Return * 0 on success, or a negative error in case of failure. * @@ -684,7 +684,7 @@ union bpf_attr { * Description * Return the time elapsed since system boot, in nanoseconds. * Does not include time the system was suspended. - * See: clock_gettime(CLOCK_MONOTONIC) + * See: **clock_gettime**\ (**CLOCK_MONOTONIC**) * Return * Current *ktime*. * @@ -1543,11 +1543,11 @@ union bpf_attr { * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr) * Description * Copy a NUL terminated string from an unsafe kernel address - * *unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for + * *unsafe_ptr* to *dst*. See **bpf_probe_read_kernel_str**\ () for * more details. * - * Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str() - * instead. + * Generally, use **bpf_probe_read_user_str**\ () or + * **bpf_probe_read_kernel_str**\ () instead. * Return * On success, the strictly positive length of the string, * including the trailing NUL character. On error, a negative @@ -1575,7 +1575,7 @@ union bpf_attr { * * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) * Description - * Equivalent to bpf_get_socket_cookie() helper that accepts + * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts * *skb*, but gets socket from **struct bpf_sock_ops** context. * Return * A 8-byte long non-decreasing number. @@ -1604,6 +1604,7 @@ union bpf_attr { * The option value of length *optlen* is pointed by *optval*. * * *bpf_socket* should be one of the following: + * * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** * and **BPF_CGROUP_INET6_CONNECT**. @@ -1672,12 +1673,12 @@ union bpf_attr { * * The lower two bits of *flags* are used as the return code if * the map lookup fails. This is so that the return value can be - * one of the XDP program return codes up to XDP_TX, as chosen by - * the caller. Any higher bits in the *flags* argument must be + * one of the XDP program return codes up to **XDP_TX**, as chosen + * by the caller. Any higher bits in the *flags* argument must be * unset. * - * See also bpf_redirect(), which only supports redirecting to an - * ifindex, but doesn't require a map to do so. + * See also **bpf_redirect**\ (), which only supports redirecting + * to an ifindex, but doesn't require a map to do so. * Return * **XDP_REDIRECT** on success, or the value of the two lower bits * of the *flags* argument on error. @@ -1785,7 +1786,7 @@ union bpf_attr { * the time running for event since last normalization. The * enabled and running times are accumulated since the perf event * open. To achieve scaling factor between two invocations of an - * eBPF program, users can can use CPU id as the key (which is + * eBPF program, users can use CPU id as the key (which is * typical for perf array usage model) to remember the previous * value and do the calculation inside the eBPF program. * Return @@ -1812,6 +1813,7 @@ union bpf_attr { * *opval* and of length *optlen*. * * *bpf_socket* should be one of the following: + * * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** * and **BPF_CGROUP_INET6_CONNECT**. @@ -1833,7 +1835,7 @@ union bpf_attr { * The first argument is the context *regs* on which the kprobe * works. * - * This helper works by setting setting the PC (program counter) + * This helper works by setting the PC (program counter) * to an override function which is run in place of the original * probed function. This means the probed function is not run at * all. The replacement function just returns with the required @@ -2300,7 +2302,7 @@ union bpf_attr { * **bpf_rc_keydown**\ () again with the same values, or calling * **bpf_rc_repeat**\ (). * - * Some protocols include a toggle bit, in case the button was + * Some protocols include a toggle bit, in case the button was * released and pressed again between consecutive scancodes. * * The *ctx* should point to the lirc sample as passed into @@ -2646,7 +2648,6 @@ union bpf_attr { * * *th* points to the start of the TCP header, while *th_len* * contains **sizeof**\ (**struct tcphdr**). - * * Return * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative * error otherwise. @@ -2829,7 +2830,6 @@ union bpf_attr { * * *th* points to the start of the TCP header, while *th_len* * contains the length of the TCP header. - * * Return * On success, lower 32 bits hold the generated SYN cookie in * followed by 16 bits which hold the MSS value for that cookie, @@ -2912,7 +2912,7 @@ union bpf_attr { * // size, after checking its boundaries. * } * - * In comparison, using **bpf_probe_read_user()** helper here + * In comparison, using **bpf_probe_read_user**\ () helper here * instead to read the string would require to estimate the length * at compile time, and would often result in copying more memory * than necessary. @@ -2930,14 +2930,14 @@ union bpf_attr { * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr) * Description * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr* - * to *dst*. Same semantics as with bpf_probe_read_user_str() apply. + * to *dst*. Same semantics as with **bpf_probe_read_user_str**\ () apply. * Return - * On success, the strictly positive length of the string, including + * On success, the strictly positive length of the string, including * the trailing NUL character. On error, a negative value. * * int bpf_tcp_send_ack(void *tp, u32 rcv_nxt) * Description - * Send out a tcp-ack. *tp* is the in-kernel struct tcp_sock. + * Send out a tcp-ack. *tp* is the in-kernel struct **tcp_sock**. * *rcv_nxt* is the ack_seq to be sent out. * Return * 0 on success, or a negative error in case of failure. @@ -2965,19 +2965,19 @@ union bpf_attr { * int bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags) * Description * For an eBPF program attached to a perf event, retrieve the - * branch records (struct perf_branch_entry) associated to *ctx* - * and store it in the buffer pointed by *buf* up to size + * branch records (**struct perf_branch_entry**) associated to *ctx* + * and store it in the buffer pointed by *buf* up to size * *size* bytes. * Return * On success, number of bytes written to *buf*. On error, a * negative value. * * The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to - * instead return the number of bytes required to store all the + * instead return the number of bytes required to store all the * branch entries. If this flag is set, *buf* may be NULL. * * **-EINVAL** if arguments invalid or **size** not a multiple - * of sizeof(struct perf_branch_entry). + * of **sizeof**\ (**struct perf_branch_entry**\ ). * * **-ENOENT** if architecture does not support branch records. * @@ -2985,8 +2985,8 @@ union bpf_attr { * Description * Returns 0 on success, values for *pid* and *tgid* as seen from the current * *namespace* will be returned in *nsdata*. - * - * On failure, the returned value is one of the following: + * Return + * 0 on success, or one of the following in case of failure: * * **-EINVAL** if dev and inum supplied don't match dev_t and inode number * with nsfs of current task, or if dev conversion to dev_t lost high bits. @@ -3025,8 +3025,8 @@ union bpf_attr { * a global identifier that can be assumed unique. If *ctx* is * NULL, then the helper returns the cookie for the initial * network namespace. The cookie itself is very similar to that - * of bpf_get_socket_cookie() helper, but for network namespaces - * instead of sockets. + * of **bpf_get_socket_cookie**\ () helper, but for network + * namespaces instead of sockets. * Return * A 8-byte long opaque number. * @@ -3061,57 +3061,66 @@ union bpf_attr { * * The *flags* argument must be zero. * Return - * 0 on success, or a negative errno in case of failure. + * 0 on success, or a negative error in case of failure: * - * * **-EINVAL** Unsupported flags specified. - * * **-ENOENT** Socket is unavailable for assignment. - * * **-ENETUNREACH** Socket is unreachable (wrong netns). - * * **-EOPNOTSUPP** Unsupported operation, for example a - * call from outside of TC ingress. - * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport). + * **-EINVAL** if specified *flags* are not supported. + * + * **-ENOENT** if the socket is unavailable for assignment. + * + * **-ENETUNREACH** if the socket is unreachable (wrong netns). + * + * **-EOPNOTSUPP** if the operation is not supported, for example + * a call from outside of TC ingress. + * + * **-ESOCKTNOSUPPORT** if the socket type is not supported + * (reuseport). * * u64 bpf_ktime_get_boot_ns(void) * Description * Return the time elapsed since system boot, in nanoseconds. * Does include the time the system was suspended. - * See: clock_gettime(CLOCK_BOOTTIME) + * See: **clock_gettime**\ (**CLOCK_BOOTTIME**) * Return * Current *ktime*. * * int bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len) * Description - * seq_printf uses seq_file seq_printf() to print out the format string. + * **bpf_seq_printf**\ () uses seq_file **seq_printf**\ () to print + * out the format string. * The *m* represents the seq_file. The *fmt* and *fmt_size* are for * the format string itself. The *data* and *data_len* are format string - * arguments. The *data* are a u64 array and corresponding format string + * arguments. The *data* are a **u64** array and corresponding format string * values are stored in the array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* array. - * The *data_len* is the *data* size in term of bytes. + * The *data_len* is the size of *data* in bytes. * * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. * Reading kernel memory may fail due to either invalid address or * valid address but requiring a major memory fault. If reading kernel memory * fails, the string for **%s** will be an empty string, and the ip * address for **%p{i,I}{4,6}** will be 0. Not returning error to - * bpf program is consistent with what bpf_trace_printk() does for now. + * bpf program is consistent with what **bpf_trace_printk**\ () does for now. * Return - * 0 on success, or a negative errno in case of failure. + * 0 on success, or a negative error in case of failure: + * + * **-EBUSY** if per-CPU memory copy buffer is busy, can try again + * by returning 1 from bpf program. + * + * **-EINVAL** if arguments are invalid, or if *fmt* is invalid/unsupported. + * + * **-E2BIG** if *fmt* contains too many format specifiers. * - * * **-EBUSY** Percpu memory copy buffer is busy, can try again - * by returning 1 from bpf program. - * * **-EINVAL** Invalid arguments, or invalid/unsupported formats. - * * **-E2BIG** Too many format specifiers. - * * **-EOVERFLOW** Overflow happens, the same object will be tried again. + * **-EOVERFLOW** if an overflow happened: The same object will be tried again. * * int bpf_seq_write(struct seq_file *m, const void *data, u32 len) * Description - * seq_write uses seq_file seq_write() to write the data. + * **bpf_seq_write**\ () uses seq_file **seq_write**\ () to write the data. * The *m* represents the seq_file. The *data* and *len* represent the - * data to write in bytes. + * data to write in bytes. * Return - * 0 on success, or a negative errno in case of failure. + * 0 on success, or a negative error in case of failure: * - * * **-EOVERFLOW** Overflow happens, the same object will be tried again. + * **-EOVERFLOW** if an overflow happened: The same object will be tried again. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index ded304c96a05..91fa668fa860 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -318,6 +318,11 @@ may be interested in: of eBPF maps are used with a given helper function. * *kernel/bpf/* directory contains other files in which additional helpers are defined (for cgroups, sockmaps, etc.). +* The bpftool utility can be used to probe the availability of helper functions + on the system (as well as supported program and map types, and a number of + other parameters). To do so, run **bpftool feature probe** (see + **bpftool-feature**\ (8) for details). Add the **unprivileged** keyword to + list features available to unprivileged users. Compatibility between helper functions and program types can generally be found in the files where helper functions are defined. Look for the **struct @@ -338,6 +343,7 @@ SEE ALSO ======== **bpf**\ (2), +**bpftool**\ (8), **cgroups**\ (7), **ip**\ (8), **perf_event_open**\ (2), -- cgit v1.2.3 From 6446ec6cbf46483737e832cd6050885fa8eb87fa Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 7 May 2020 17:12:52 +0200 Subject: media: v4l2-subdev: add VIDIOC_SUBDEV_QUERYCAP ioctl While normal video/radio/vbi/swradio nodes have a proper QUERYCAP ioctl that apps can call to determine that it is indeed a V4L2 device, there is currently no equivalent for v4l-subdev nodes. Adding this ioctl will solve that, and it will allow utilities like v4l2-compliance to be used with these devices as well. SUBDEV_QUERYCAP currently returns the version and capabilities of the subdevice. Define a capability flag to report if the subdevice is registered in read-only mode. Signed-off-by: Hans Verkuil Signed-off-by: Jacopo Mondi Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-subdev.c | 11 +++++++++++ include/uapi/linux/v4l2-subdev.h | 16 ++++++++++++++++ 2 files changed, 27 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c index 174778f9c0bc..665b0c0f74cf 100644 --- a/drivers/media/v4l2-core/v4l2-subdev.c +++ b/drivers/media/v4l2-core/v4l2-subdev.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -344,6 +345,16 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg) int rval; switch (cmd) { + case VIDIOC_SUBDEV_QUERYCAP: { + struct v4l2_subdev_capability *cap = arg; + + memset(cap->reserved, 0, sizeof(cap->reserved)); + cap->version = LINUX_VERSION_CODE; + cap->capabilities = ro_subdev ? V4L2_SUBDEV_CAP_RO_SUBDEV : 0; + + return 0; + } + case VIDIOC_QUERYCTRL: /* * TODO: this really should be folded into v4l2_queryctrl (this diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index 03970ce30741..5d2a1dab7911 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -155,9 +155,25 @@ struct v4l2_subdev_selection { __u32 reserved[8]; }; +/** + * struct v4l2_subdev_capability - subdev capabilities + * @version: the driver versioning number + * @capabilities: the subdev capabilities, see V4L2_SUBDEV_CAP_* + * @reserved: for future use, set to zero for now + */ +struct v4l2_subdev_capability { + __u32 version; + __u32 capabilities; + __u32 reserved[14]; +}; + +/* The v4l2 sub-device video device node is registered in read-only mode. */ +#define V4L2_SUBDEV_CAP_RO_SUBDEV BIT(0) + /* Backwards compatibility define --- to be removed */ #define v4l2_subdev_edid v4l2_edid +#define VIDIOC_SUBDEV_QUERYCAP _IOR('V', 0, struct v4l2_subdev_capability) #define VIDIOC_SUBDEV_G_FMT _IOWR('V', 4, struct v4l2_subdev_format) #define VIDIOC_SUBDEV_S_FMT _IOWR('V', 5, struct v4l2_subdev_format) #define VIDIOC_SUBDEV_G_FRAME_INTERVAL _IOWR('V', 21, struct v4l2_subdev_frame_interval) -- cgit v1.2.3 From 7d33850abdb9048c6aa421440a64905eb4ad07a2 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Tue, 31 Mar 2020 11:40:33 +0200 Subject: floppy: add references to 82077's extra registers This controller provides extra status registers SRA and SRB as well as a tape drive register (TDR) and a data rate select register (DSR), which are referenced in the sparc port, so let's have their symbolic definitions centralized. Link: https://lore.kernel.org/r/20200331094054.24441-3-w@1wt.eu Signed-off-by: Willy Tarreau Signed-off-by: Denis Efremov --- include/uapi/linux/fdreg.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fdreg.h b/include/uapi/linux/fdreg.h index 1318881954e1..10d33632939d 100644 --- a/include/uapi/linux/fdreg.h +++ b/include/uapi/linux/fdreg.h @@ -7,13 +7,23 @@ * Handbook", Sanches and Canton. */ -/* Fd controller regs. S&C, about page 340 */ -#define FD_STATUS 4 -#define FD_DATA 5 +/* 82077's auxiliary status registers A & B (R) */ +#define FD_SRA 0 +#define FD_SRB 1 /* Digital Output Register */ #define FD_DOR 2 +/* 82077's tape drive register (R/W) */ +#define FD_TDR 3 + +/* 82077's data rate select register (W) */ +#define FD_DSR 4 + +/* Fd controller regs. S&C, about page 340 */ +#define FD_STATUS 4 +#define FD_DATA 5 + /* Digital Input Register (read) */ #define FD_DIR 7 -- cgit v1.2.3 From 9c4c5a24c85585fb8904bd2872501cd8181b3854 Mon Sep 17 00:00:00 2001 From: Denis Efremov Date: Fri, 1 May 2020 16:44:14 +0300 Subject: floppy: add FD_AUTODETECT_SIZE define for struct floppy_drive_params Use FD_AUTODETECT_SIZE for autodetect buffer size in struct floppy_drive_params instead of a magic number. Link: https://lore.kernel.org/r/20200501134416.72248-3-efremov@linux.com Reviewed-by: Christoph Hellwig Signed-off-by: Denis Efremov --- drivers/block/floppy.c | 9 +++++---- include/uapi/linux/fd.h | 5 ++++- 2 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 3ab6e804b5ec..b82b3d38b834 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -2073,7 +2073,8 @@ static int next_valid_format(int drive) probed_format = drive_state[drive].probed_format; while (1) { - if (probed_format >= 8 || !drive_params[drive].autodetect[probed_format]) { + if (probed_format >= FD_AUTODETECT_SIZE || + !drive_params[drive].autodetect[probed_format]) { drive_state[drive].probed_format = 0; return 1; } @@ -3442,13 +3443,13 @@ static int fd_getgeo(struct block_device *bdev, struct hd_geometry *geo) return 0; } -static bool valid_floppy_drive_params(const short autodetect[8], +static bool valid_floppy_drive_params(const short autodetect[FD_AUTODETECT_SIZE], int native_format) { size_t floppy_type_size = ARRAY_SIZE(floppy_type); size_t i = 0; - for (i = 0; i < 8; ++i) { + for (i = 0; i < FD_AUTODETECT_SIZE; ++i) { if (autodetect[i] < 0 || autodetect[i] >= floppy_type_size) return false; @@ -3673,7 +3674,7 @@ struct compat_floppy_drive_params { struct floppy_max_errors max_errors; char flags; char read_track; - short autodetect[8]; + short autodetect[FD_AUTODETECT_SIZE]; compat_int_t checkfreq; compat_int_t native_format; }; diff --git a/include/uapi/linux/fd.h b/include/uapi/linux/fd.h index 90fb94712c41..3f6b7be4c096 100644 --- a/include/uapi/linux/fd.h +++ b/include/uapi/linux/fd.h @@ -172,7 +172,10 @@ struct floppy_drive_params { * used in succession to try to read the disk. If the FDC cannot lock onto * the disk, the next format is tried. This uses the variable 'probing'. */ - short autodetect[8]; /* autodetected formats */ + +#define FD_AUTODETECT_SIZE 8 + + short autodetect[FD_AUTODETECT_SIZE]; /* autodetected formats */ int checkfreq; /* how often should the drive be checked for disk * changes */ -- cgit v1.2.3 From bd10a5f3e21b1cb8e2133c1f08b3e8207cee12dd Mon Sep 17 00:00:00 2001 From: Denis Efremov Date: Fri, 1 May 2020 16:44:15 +0300 Subject: floppy: add defines for sizes of cmd & reply buffers of floppy_raw_cmd Use FD_RAW_CMD_SIZE, FD_RAW_REPLY_SIZE defines instead of magic numbers for cmd & reply buffers of struct floppy_raw_cmd. Remove local to floppy.c MAX_REPLIES define, as it is now FD_RAW_REPLY_SIZE. FD_RAW_CMD_FULLSIZE added as we allow command to also fill reply_count and reply fields. Link: https://lore.kernel.org/r/20200501134416.72248-4-efremov@linux.com Reviewed-by: Christoph Hellwig Signed-off-by: Denis Efremov --- drivers/block/floppy.c | 19 +++++-------------- include/uapi/linux/fd.h | 14 ++++++++++++-- 2 files changed, 17 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index b82b3d38b834..9e098d53b046 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -337,8 +337,7 @@ static bool initialized; /* * globals used by 'result()' */ -#define MAX_REPLIES 16 -static unsigned char reply_buffer[MAX_REPLIES]; +static unsigned char reply_buffer[FD_RAW_REPLY_SIZE]; static int inr; /* size of reply buffer, when called from interrupt */ #define ST0 0 #define ST1 1 @@ -1162,7 +1161,7 @@ static int result(int fdc) int i; int status = 0; - for (i = 0; i < MAX_REPLIES; i++) { + for (i = 0; i < FD_RAW_REPLY_SIZE; i++) { status = wait_til_ready(fdc); if (status < 0) break; @@ -3079,7 +3078,7 @@ static void raw_cmd_done(int flag) raw_cmd->flags |= FD_RAW_HARDFAILURE; } else { raw_cmd->reply_count = inr; - if (raw_cmd->reply_count > MAX_REPLIES) + if (raw_cmd->reply_count > FD_RAW_REPLY_SIZE) raw_cmd->reply_count = 0; for (i = 0; i < raw_cmd->reply_count; i++) raw_cmd->reply[i] = reply_buffer[i]; @@ -3190,18 +3189,10 @@ loop: if (ret) return -EFAULT; param += sizeof(struct floppy_raw_cmd); - if (ptr->cmd_count > 33) - /* the command may now also take up the space - * initially intended for the reply & the - * reply count. Needed for long 82078 commands - * such as RESTORE, which takes ... 17 command - * bytes. Murphy's law #137: When you reserve - * 16 bytes for a structure, you'll one day - * discover that you really need 17... - */ + if (ptr->cmd_count > FD_RAW_CMD_FULLSIZE) return -EINVAL; - for (i = 0; i < 16; i++) + for (i = 0; i < FD_RAW_REPLY_SIZE; i++) ptr->reply[i] = 0; ptr->resultcode = 0; diff --git a/include/uapi/linux/fd.h b/include/uapi/linux/fd.h index 3f6b7be4c096..2e9c2c1c18e6 100644 --- a/include/uapi/linux/fd.h +++ b/include/uapi/linux/fd.h @@ -360,10 +360,20 @@ struct floppy_raw_cmd { int buffer_length; /* length of allocated buffer */ unsigned char rate; + +#define FD_RAW_CMD_SIZE 16 +#define FD_RAW_REPLY_SIZE 16 +#define FD_RAW_CMD_FULLSIZE (FD_RAW_CMD_SIZE + 1 + FD_RAW_REPLY_SIZE) + + /* The command may take up the space initially intended for the reply + * and the reply count. Needed for long 82078 commands such as RESTORE, + * which takes 17 command bytes. + */ + unsigned char cmd_count; - unsigned char cmd[16]; + unsigned char cmd[FD_RAW_CMD_SIZE]; unsigned char reply_count; - unsigned char reply[16]; + unsigned char reply[FD_RAW_REPLY_SIZE]; int track; int resultcode; -- cgit v1.2.3 From 0836275df4db20daf040fff5d9a1da89c4c08a85 Mon Sep 17 00:00:00 2001 From: Denis Efremov Date: Fri, 1 May 2020 16:44:16 +0300 Subject: floppy: suppress UBSAN warning in setup_rw_floppy() UBSAN: array-index-out-of-bounds in drivers/block/floppy.c:1521:45 index 16 is out of range for type 'unsigned char [16]' Call Trace: ... setup_rw_floppy+0x5c3/0x7f0 floppy_ready+0x2be/0x13b0 process_one_work+0x2c1/0x5d0 worker_thread+0x56/0x5e0 kthread+0x122/0x170 ret_from_fork+0x35/0x40 From include/uapi/linux/fd.h: struct floppy_raw_cmd { ... unsigned char cmd_count; unsigned char cmd[16]; unsigned char reply_count; unsigned char reply[16]; ... } This out-of-bounds access is intentional. The command in struct floppy_raw_cmd may take up the space initially intended for the reply and the reply count. It is needed for long 82078 commands such as RESTORE, which takes 17 command bytes. Initial cmd size is not enough and since struct setup_rw_floppy is a part of uapi we check that cmd_count is in [0:16+1+16] in raw_cmd_copyin(). The patch adds union with original cmd,reply_count,reply fields and fullcmd field of equivalent size. The cmd accesses are turned to fullcmd where appropriate to suppress UBSAN warning. Link: https://lore.kernel.org/r/20200501134416.72248-5-efremov@linux.com Reviewed-by: Christoph Hellwig Signed-off-by: Denis Efremov --- drivers/block/floppy.c | 4 ++-- include/uapi/linux/fd.h | 11 ++++++++--- 2 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 9e098d53b046..064c1acb9f00 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -1070,7 +1070,7 @@ static void setup_DMA(void) if (raw_cmd->length == 0) { print_hex_dump(KERN_INFO, "zero dma transfer size: ", DUMP_PREFIX_NONE, 16, 1, - raw_cmd->cmd, raw_cmd->cmd_count, false); + raw_cmd->fullcmd, raw_cmd->cmd_count, false); cont->done(0); fdc_state[current_fdc].reset = 1; return; @@ -1515,7 +1515,7 @@ static void setup_rw_floppy(void) r = 0; for (i = 0; i < raw_cmd->cmd_count; i++) - r |= output_byte(current_fdc, raw_cmd->cmd[i]); + r |= output_byte(current_fdc, raw_cmd->fullcmd[i]); debugt(__func__, "rw_command"); diff --git a/include/uapi/linux/fd.h b/include/uapi/linux/fd.h index 2e9c2c1c18e6..8b80c63b971c 100644 --- a/include/uapi/linux/fd.h +++ b/include/uapi/linux/fd.h @@ -371,9 +371,14 @@ struct floppy_raw_cmd { */ unsigned char cmd_count; - unsigned char cmd[FD_RAW_CMD_SIZE]; - unsigned char reply_count; - unsigned char reply[FD_RAW_REPLY_SIZE]; + union { + struct { + unsigned char cmd[FD_RAW_CMD_SIZE]; + unsigned char reply_count; + unsigned char reply[FD_RAW_REPLY_SIZE]; + }; + unsigned char fullcmd[FD_RAW_CMD_FULLSIZE]; + }; int track; int resultcode; -- cgit v1.2.3 From 17ff3b72e742192f11e3136174ac4eafb50e38d4 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 7 May 2020 19:06:55 +0200 Subject: usb: raw-gadget: improve uapi headers comments Fix typo "trasferred" => "transferred". Don't call USB requests URBs. Fix comment style. Signed-off-by: Andrey Konovalov Signed-off-by: Felipe Balbi --- include/uapi/linux/usb/raw_gadget.h | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/usb/raw_gadget.h b/include/uapi/linux/usb/raw_gadget.h index ea375082b3ac..02885e021ee5 100644 --- a/include/uapi/linux/usb/raw_gadget.h +++ b/include/uapi/linux/usb/raw_gadget.h @@ -115,11 +115,11 @@ struct usb_raw_ep_io { #define USB_RAW_IOCTL_EVENT_FETCH _IOR('U', 2, struct usb_raw_event) /* - * Queues an IN (OUT for READ) urb as a response to the last control request - * received on endpoint 0, provided that was an IN (OUT for READ) request and - * waits until the urb is completed. Copies received data to user for READ. + * Queues an IN (OUT for READ) request as a response to the last setup request + * received on endpoint 0 (provided that was an IN (OUT for READ) request), and + * waits until the request is completed. Copies received data to user for READ. * Accepts a pointer to the usb_raw_ep_io struct as an argument. - * Returns length of trasferred data on success or negative error code on + * Returns length of transferred data on success or negative error code on * failure. */ #define USB_RAW_IOCTL_EP0_WRITE _IOW('U', 3, struct usb_raw_ep_io) @@ -133,19 +133,20 @@ struct usb_raw_ep_io { */ #define USB_RAW_IOCTL_EP_ENABLE _IOW('U', 5, struct usb_endpoint_descriptor) -/* Disables specified endpoint. +/* + * Disables specified endpoint. * Accepts endpoint handle as an argument. * Returns 0 on success or negative error code on failure. */ #define USB_RAW_IOCTL_EP_DISABLE _IOW('U', 6, __u32) /* - * Queues an IN (OUT for READ) urb as a response to the last control request - * received on endpoint usb_raw_ep_io.ep, provided that was an IN (OUT for READ) - * request and waits until the urb is completed. Copies received data to user - * for READ. + * Queues an IN (OUT for READ) request as a response to the last setup request + * received on endpoint usb_raw_ep_io.ep (provided that was an IN (OUT for READ) + * request), and waits until the request is completed. Copies received data to + * user for READ. * Accepts a pointer to the usb_raw_ep_io struct as an argument. - * Returns length of trasferred data on success or negative error code on + * Returns length of transferred data on success or negative error code on * failure. */ #define USB_RAW_IOCTL_EP_WRITE _IOW('U', 7, struct usb_raw_ep_io) -- cgit v1.2.3 From 97df5e5758f7d1dd0ca97e3210696818fc45bdb3 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 7 May 2020 19:06:56 +0200 Subject: usb: raw-gadget: fix gadget endpoint selection Currently automatic gadget endpoint selection based on required features doesn't work. Raw Gadget tries iterating over the list of available endpoints and finding one that has the right direction and transfer type. Unfortunately selecting arbitrary gadget endpoints (even if they satisfy feature requirements) doesn't work, as (depending on the UDC driver) they might have fixed addresses, and one also needs to provide matching endpoint addresses in the descriptors sent to the host. The composite framework deals with this by assigning endpoint addresses in usb_ep_autoconfig() before enumeration starts. This approach won't work with Raw Gadget as the endpoints are supposed to be enabled after a set_configuration/set_interface request from the host, so it's too late to patch the endpoint descriptors that had already been sent to the host. For Raw Gadget we take another approach. Similarly to GadgetFS, we allow the user to make the decision as to which gadget endpoints to use. This patch adds another Raw Gadget ioctl USB_RAW_IOCTL_EPS_INFO that exposes information about all non-control endpoints that a currently connected UDC has. This information includes endpoints addresses, as well as their capabilities and limits to allow the user to choose the most fitting gadget endpoint. The USB_RAW_IOCTL_EP_ENABLE ioctl is updated to use the proper endpoint validation routine usb_gadget_ep_match_desc(). These changes affect the portability of the gadgets that use Raw Gadget when running on different UDCs. Nevertheless, as long as the user relies on the information provided by USB_RAW_IOCTL_EPS_INFO to dynamically choose endpoint addresses, UDC-agnostic gadgets can still be written with Raw Gadget. Fixes: f2c2e717642c ("usb: gadget: add raw-gadget interface") Signed-off-by: Andrey Konovalov Signed-off-by: Felipe Balbi --- Documentation/usb/raw-gadget.rst | 5 +- drivers/usb/gadget/legacy/raw_gadget.c | 187 ++++++++++++++++++++++----------- include/uapi/linux/usb/raw_gadget.h | 72 ++++++++++++- 3 files changed, 194 insertions(+), 70 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/usb/raw-gadget.rst b/Documentation/usb/raw-gadget.rst index 9e78cb858f86..4af8b1f15574 100644 --- a/Documentation/usb/raw-gadget.rst +++ b/Documentation/usb/raw-gadget.rst @@ -27,9 +27,8 @@ differences are: 3. Raw Gadget provides a way to select a UDC device/driver to bind to, while GadgetFS currently binds to the first available UDC. -4. Raw Gadget uses predictable endpoint names (handles) across different - UDCs (as long as UDCs have enough endpoints of each required transfer - type). +4. Raw Gadget explicitly exposes information about endpoints addresses and + capabilities allowing a user to write UDC-agnostic gadgets. 5. Raw Gadget has ioctl-based interface instead of a filesystem-based one. diff --git a/drivers/usb/gadget/legacy/raw_gadget.c b/drivers/usb/gadget/legacy/raw_gadget.c index 7b241992ad5a..775f22184aaf 100644 --- a/drivers/usb/gadget/legacy/raw_gadget.c +++ b/drivers/usb/gadget/legacy/raw_gadget.c @@ -7,6 +7,7 @@ */ #include +#include #include #include #include @@ -123,8 +124,6 @@ static void raw_event_queue_destroy(struct raw_event_queue *queue) struct raw_dev; -#define USB_RAW_MAX_ENDPOINTS 32 - enum ep_state { STATE_EP_DISABLED, STATE_EP_ENABLED, @@ -134,6 +133,7 @@ struct raw_ep { struct raw_dev *dev; enum ep_state state; struct usb_ep *ep; + u8 addr; struct usb_request *req; bool urb_queued; bool disabling; @@ -168,7 +168,8 @@ struct raw_dev { bool ep0_out_pending; bool ep0_urb_queued; ssize_t ep0_status; - struct raw_ep eps[USB_RAW_MAX_ENDPOINTS]; + struct raw_ep eps[USB_RAW_EPS_NUM_MAX]; + int eps_num; struct completion ep0_done; struct raw_event_queue queue; @@ -202,7 +203,7 @@ static void dev_free(struct kref *kref) usb_ep_free_request(dev->gadget->ep0, dev->req); } raw_event_queue_destroy(&dev->queue); - for (i = 0; i < USB_RAW_MAX_ENDPOINTS; i++) { + for (i = 0; i < dev->eps_num; i++) { if (dev->eps[i].state != STATE_EP_ENABLED) continue; usb_ep_disable(dev->eps[i].ep); @@ -249,12 +250,26 @@ static void gadget_ep0_complete(struct usb_ep *ep, struct usb_request *req) complete(&dev->ep0_done); } +static u8 get_ep_addr(const char *name) +{ + /* If the endpoint has fixed function (named as e.g. "ep12out-bulk"), + * parse the endpoint address from its name. We deliberately use + * deprecated simple_strtoul() function here, as the number isn't + * followed by '\0' nor '\n'. + */ + if (isdigit(name[2])) + return simple_strtoul(&name[2], NULL, 10); + /* Otherwise the endpoint is configurable (named as e.g. "ep-a"). */ + return USB_RAW_EP_ADDR_ANY; +} + static int gadget_bind(struct usb_gadget *gadget, struct usb_gadget_driver *driver) { - int ret = 0; + int ret = 0, i = 0; struct raw_dev *dev = container_of(driver, struct raw_dev, driver); struct usb_request *req; + struct usb_ep *ep; unsigned long flags; if (strcmp(gadget->name, dev->udc_name) != 0) @@ -273,6 +288,13 @@ static int gadget_bind(struct usb_gadget *gadget, dev->req->context = dev; dev->req->complete = gadget_ep0_complete; dev->gadget = gadget; + gadget_for_each_ep(ep, dev->gadget) { + dev->eps[i].ep = ep; + dev->eps[i].addr = get_ep_addr(ep->name); + dev->eps[i].state = STATE_EP_DISABLED; + i++; + } + dev->eps_num = i; spin_unlock_irqrestore(&dev->lock, flags); /* Matches kref_put() in gadget_unbind(). */ @@ -555,7 +577,7 @@ static void *raw_alloc_io_data(struct usb_raw_ep_io *io, void __user *ptr, if (copy_from_user(io, ptr, sizeof(*io))) return ERR_PTR(-EFAULT); - if (io->ep >= USB_RAW_MAX_ENDPOINTS) + if (io->ep >= USB_RAW_EPS_NUM_MAX) return ERR_PTR(-EINVAL); if (!usb_raw_io_flags_valid(io->flags)) return ERR_PTR(-EINVAL); @@ -682,40 +704,12 @@ free: return ret; } -static bool check_ep_caps(struct usb_ep *ep, - struct usb_endpoint_descriptor *desc) -{ - switch (usb_endpoint_type(desc)) { - case USB_ENDPOINT_XFER_ISOC: - if (!ep->caps.type_iso) - return false; - break; - case USB_ENDPOINT_XFER_BULK: - if (!ep->caps.type_bulk) - return false; - break; - case USB_ENDPOINT_XFER_INT: - if (!ep->caps.type_int) - return false; - break; - default: - return false; - } - - if (usb_endpoint_dir_in(desc) && !ep->caps.dir_in) - return false; - if (usb_endpoint_dir_out(desc) && !ep->caps.dir_out) - return false; - - return true; -} - static int raw_ioctl_ep_enable(struct raw_dev *dev, unsigned long value) { int ret = 0, i; unsigned long flags; struct usb_endpoint_descriptor *desc; - struct usb_ep *ep = NULL; + struct raw_ep *ep; desc = memdup_user((void __user *)value, sizeof(*desc)); if (IS_ERR(desc)) @@ -743,41 +737,32 @@ static int raw_ioctl_ep_enable(struct raw_dev *dev, unsigned long value) goto out_free; } - for (i = 0; i < USB_RAW_MAX_ENDPOINTS; i++) { - if (dev->eps[i].state == STATE_EP_ENABLED) + for (i = 0; i < dev->eps_num; i++) { + ep = &dev->eps[i]; + if (ep->state != STATE_EP_DISABLED) continue; - break; - } - if (i == USB_RAW_MAX_ENDPOINTS) { - dev_dbg(&dev->gadget->dev, - "fail, no device endpoints available\n"); - ret = -EBUSY; - goto out_free; - } - - gadget_for_each_ep(ep, dev->gadget) { - if (ep->enabled) + if (ep->addr != usb_endpoint_num(desc) && + ep->addr != USB_RAW_EP_ADDR_ANY) continue; - if (!check_ep_caps(ep, desc)) + if (!usb_gadget_ep_match_desc(dev->gadget, ep->ep, desc, NULL)) continue; - ep->desc = desc; - ret = usb_ep_enable(ep); + ep->ep->desc = desc; + ret = usb_ep_enable(ep->ep); if (ret < 0) { dev_err(&dev->gadget->dev, "fail, usb_ep_enable returned %d\n", ret); goto out_free; } - dev->eps[i].req = usb_ep_alloc_request(ep, GFP_ATOMIC); - if (!dev->eps[i].req) { + ep->req = usb_ep_alloc_request(ep->ep, GFP_ATOMIC); + if (!ep->req) { dev_err(&dev->gadget->dev, "fail, usb_ep_alloc_request failed\n"); - usb_ep_disable(ep); + usb_ep_disable(ep->ep); ret = -ENOMEM; goto out_free; } - dev->eps[i].ep = ep; - dev->eps[i].state = STATE_EP_ENABLED; - ep->driver_data = &dev->eps[i]; + ep->state = STATE_EP_ENABLED; + ep->ep->driver_data = ep; ret = i; goto out_unlock; } @@ -796,10 +781,6 @@ static int raw_ioctl_ep_disable(struct raw_dev *dev, unsigned long value) { int ret = 0, i = value; unsigned long flags; - const void *desc; - - if (i < 0 || i >= USB_RAW_MAX_ENDPOINTS) - return -EINVAL; spin_lock_irqsave(&dev->lock, flags); if (dev->state != STATE_DEV_RUNNING) { @@ -812,6 +793,11 @@ static int raw_ioctl_ep_disable(struct raw_dev *dev, unsigned long value) ret = -EBUSY; goto out_unlock; } + if (i < 0 || i >= dev->eps_num) { + dev_dbg(dev->dev, "fail, invalid endpoint\n"); + ret = -EBUSY; + goto out_unlock; + } if (dev->eps[i].state != STATE_EP_ENABLED) { dev_dbg(&dev->gadget->dev, "fail, endpoint is not enabled\n"); ret = -EINVAL; @@ -836,10 +822,9 @@ static int raw_ioctl_ep_disable(struct raw_dev *dev, unsigned long value) spin_lock_irqsave(&dev->lock, flags); usb_ep_free_request(dev->eps[i].ep, dev->eps[i].req); - desc = dev->eps[i].ep->desc; + kfree(dev->eps[i].ep->desc); dev->eps[i].ep = NULL; dev->eps[i].state = STATE_EP_DISABLED; - kfree(desc); dev->eps[i].disabling = false; out_unlock: @@ -868,7 +853,7 @@ static int raw_process_ep_io(struct raw_dev *dev, struct usb_raw_ep_io *io, { int ret = 0; unsigned long flags; - struct raw_ep *ep = &dev->eps[io->ep]; + struct raw_ep *ep; DECLARE_COMPLETION_ONSTACK(done); spin_lock_irqsave(&dev->lock, flags); @@ -882,6 +867,12 @@ static int raw_process_ep_io(struct raw_dev *dev, struct usb_raw_ep_io *io, ret = -EBUSY; goto out_unlock; } + if (io->ep >= dev->eps_num) { + dev_dbg(&dev->gadget->dev, "fail, invalid endpoint\n"); + ret = -EINVAL; + goto out_unlock; + } + ep = &dev->eps[io->ep]; if (ep->state != STATE_EP_ENABLED) { dev_dbg(&dev->gadget->dev, "fail, endpoint is not enabled\n"); ret = -EBUSY; @@ -1027,6 +1018,71 @@ out_unlock: return ret; } +static void fill_ep_caps(struct usb_ep_caps *caps, + struct usb_raw_ep_caps *raw_caps) +{ + raw_caps->type_control = caps->type_control; + raw_caps->type_iso = caps->type_iso; + raw_caps->type_bulk = caps->type_bulk; + raw_caps->type_int = caps->type_int; + raw_caps->dir_in = caps->dir_in; + raw_caps->dir_out = caps->dir_out; +} + +static void fill_ep_limits(struct usb_ep *ep, struct usb_raw_ep_limits *limits) +{ + limits->maxpacket_limit = ep->maxpacket_limit; + limits->max_streams = ep->max_streams; +} + +static int raw_ioctl_eps_info(struct raw_dev *dev, unsigned long value) +{ + int ret = 0, i; + unsigned long flags; + struct usb_raw_eps_info *info; + struct raw_ep *ep; + + info = kmalloc(sizeof(*info), GFP_KERNEL); + if (!info) { + ret = -ENOMEM; + goto out; + } + + spin_lock_irqsave(&dev->lock, flags); + if (dev->state != STATE_DEV_RUNNING) { + dev_dbg(dev->dev, "fail, device is not running\n"); + ret = -EINVAL; + spin_unlock_irqrestore(&dev->lock, flags); + goto out_free; + } + if (!dev->gadget) { + dev_dbg(dev->dev, "fail, gadget is not bound\n"); + ret = -EBUSY; + spin_unlock_irqrestore(&dev->lock, flags); + goto out_free; + } + + memset(info, 0, sizeof(*info)); + for (i = 0; i < dev->eps_num; i++) { + ep = &dev->eps[i]; + strscpy(&info->eps[i].name[0], ep->ep->name, + USB_RAW_EP_NAME_MAX); + info->eps[i].addr = ep->addr; + fill_ep_caps(&ep->ep->caps, &info->eps[i].caps); + fill_ep_limits(ep->ep, &info->eps[i].limits); + } + ret = dev->eps_num; + spin_unlock_irqrestore(&dev->lock, flags); + + if (copy_to_user((void __user *)value, info, sizeof(*info))) + ret = -EFAULT; + +out_free: + kfree(info); +out: + return ret; +} + static long raw_ioctl(struct file *fd, unsigned int cmd, unsigned long value) { struct raw_dev *dev = fd->private_data; @@ -1069,6 +1125,9 @@ static long raw_ioctl(struct file *fd, unsigned int cmd, unsigned long value) case USB_RAW_IOCTL_VBUS_DRAW: ret = raw_ioctl_vbus_draw(dev, value); break; + case USB_RAW_IOCTL_EPS_INFO: + ret = raw_ioctl_eps_info(dev, value); + break; default: ret = -EINVAL; } diff --git a/include/uapi/linux/usb/raw_gadget.h b/include/uapi/linux/usb/raw_gadget.h index 02885e021ee5..c89f6341229c 100644 --- a/include/uapi/linux/usb/raw_gadget.h +++ b/include/uapi/linux/usb/raw_gadget.h @@ -93,6 +93,64 @@ struct usb_raw_ep_io { __u8 data[0]; }; +/* Maximum number of non-control endpoints in struct usb_raw_eps_info. */ +#define USB_RAW_EPS_NUM_MAX 30 + +/* Maximum length of UDC endpoint name in struct usb_raw_ep_info. */ +#define USB_RAW_EP_NAME_MAX 16 + +/* Used as addr in struct usb_raw_ep_info if endpoint accepts any address. */ +#define USB_RAW_EP_ADDR_ANY 0xff + +/* + * struct usb_raw_ep_caps - exposes endpoint capabilities from struct usb_ep + * (technically from its member struct usb_ep_caps). + */ +struct usb_raw_ep_caps { + __u32 type_control : 1; + __u32 type_iso : 1; + __u32 type_bulk : 1; + __u32 type_int : 1; + __u32 dir_in : 1; + __u32 dir_out : 1; +}; + +/* + * struct usb_raw_ep_limits - exposes endpoint limits from struct usb_ep. + * @maxpacket_limit: Maximum packet size value supported by this endpoint. + * @max_streams: maximum number of streams supported by this endpoint + * (actual number is 2^n). + * @reserved: Empty, reserved for potential future extensions. + */ +struct usb_raw_ep_limits { + __u16 maxpacket_limit; + __u16 max_streams; + __u32 reserved; +}; + +/* + * struct usb_raw_ep_info - stores information about a gadget endpoint. + * @name: Name of the endpoint as it is defined in the UDC driver. + * @addr: Address of the endpoint that must be specified in the endpoint + * descriptor passed to USB_RAW_IOCTL_EP_ENABLE ioctl. + * @caps: Endpoint capabilities. + * @limits: Endpoint limits. + */ +struct usb_raw_ep_info { + __u8 name[USB_RAW_EP_NAME_MAX]; + __u32 addr; + struct usb_raw_ep_caps caps; + struct usb_raw_ep_limits limits; +}; + +/* + * struct usb_raw_eps_info - argument for USB_RAW_IOCTL_EPS_INFO ioctl. + * eps: Structures that store information about non-control endpoints. + */ +struct usb_raw_eps_info { + struct usb_raw_ep_info eps[USB_RAW_EPS_NUM_MAX]; +}; + /* * Initializes a Raw Gadget instance. * Accepts a pointer to the usb_raw_init struct as an argument. @@ -126,9 +184,9 @@ struct usb_raw_ep_io { #define USB_RAW_IOCTL_EP0_READ _IOWR('U', 4, struct usb_raw_ep_io) /* - * Finds an endpoint that supports the transfer type specified in the - * descriptor and enables it. - * Accepts a pointer to the usb_endpoint_descriptor struct as an argument. + * Finds an endpoint that satisfies the parameters specified in the provided + * descriptors (address, transfer type, etc.) and enables it. + * Accepts a pointer to the usb_raw_ep_descs struct as an argument. * Returns enabled endpoint handle on success or negative error code on failure. */ #define USB_RAW_IOCTL_EP_ENABLE _IOW('U', 5, struct usb_endpoint_descriptor) @@ -165,4 +223,12 @@ struct usb_raw_ep_io { */ #define USB_RAW_IOCTL_VBUS_DRAW _IOW('U', 10, __u32) +/* + * Fills in the usb_raw_eps_info structure with information about non-control + * endpoints available for the currently connected UDC. + * Returns the number of available endpoints on success or negative error code + * on failure. + */ +#define USB_RAW_IOCTL_EPS_INFO _IOR('U', 11, struct usb_raw_eps_info) + #endif /* _UAPI__LINUX_USB_RAW_GADGET_H */ -- cgit v1.2.3 From c61769bd4777a922952aed0d042a2572e5bd9b74 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 7 May 2020 19:06:57 +0200 Subject: usb: raw-gadget: support stalling/halting/wedging endpoints Raw Gadget is currently unable to stall/halt/wedge gadget endpoints, which is required for proper emulation of certain USB classes. This patch adds a few more ioctls: - USB_RAW_IOCTL_EP0_STALL allows to stall control endpoint #0 when there's a pending setup request for it. - USB_RAW_IOCTL_SET/CLEAR_HALT/WEDGE allow to set/clear halt/wedge status on non-control non-isochronous endpoints. Fixes: f2c2e717642c ("usb: gadget: add raw-gadget interface") Signed-off-by: Andrey Konovalov Signed-off-by: Felipe Balbi --- Documentation/usb/raw-gadget.rst | 2 - drivers/usb/gadget/legacy/raw_gadget.c | 131 ++++++++++++++++++++++++++++++++- include/uapi/linux/usb/raw_gadget.h | 15 ++++ 3 files changed, 144 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/usb/raw-gadget.rst b/Documentation/usb/raw-gadget.rst index 4af8b1f15574..3b3d78e850b2 100644 --- a/Documentation/usb/raw-gadget.rst +++ b/Documentation/usb/raw-gadget.rst @@ -52,8 +52,6 @@ The typical usage of Raw Gadget looks like: Potential future improvements ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -- Implement ioctl's for setting/clearing halt status on endpoints. - - Reporting more events (suspend, resume, etc.) through USB_RAW_IOCTL_EVENT_FETCH. diff --git a/drivers/usb/gadget/legacy/raw_gadget.c b/drivers/usb/gadget/legacy/raw_gadget.c index 775f22184aaf..d73ba77014c8 100644 --- a/drivers/usb/gadget/legacy/raw_gadget.c +++ b/drivers/usb/gadget/legacy/raw_gadget.c @@ -204,7 +204,7 @@ static void dev_free(struct kref *kref) } raw_event_queue_destroy(&dev->queue); for (i = 0; i < dev->eps_num; i++) { - if (dev->eps[i].state != STATE_EP_ENABLED) + if (dev->eps[i].state == STATE_EP_DISABLED) continue; usb_ep_disable(dev->eps[i].ep); usb_ep_free_request(dev->eps[i].ep, dev->eps[i].req); @@ -704,6 +704,50 @@ free: return ret; } +static int raw_ioctl_ep0_stall(struct raw_dev *dev, unsigned long value) +{ + int ret = 0; + unsigned long flags; + + if (value) + return -EINVAL; + spin_lock_irqsave(&dev->lock, flags); + if (dev->state != STATE_DEV_RUNNING) { + dev_dbg(dev->dev, "fail, device is not running\n"); + ret = -EINVAL; + goto out_unlock; + } + if (!dev->gadget) { + dev_dbg(dev->dev, "fail, gadget is not bound\n"); + ret = -EBUSY; + goto out_unlock; + } + if (dev->ep0_urb_queued) { + dev_dbg(&dev->gadget->dev, "fail, urb already queued\n"); + ret = -EBUSY; + goto out_unlock; + } + if (!dev->ep0_in_pending && !dev->ep0_out_pending) { + dev_dbg(&dev->gadget->dev, "fail, no request pending\n"); + ret = -EBUSY; + goto out_unlock; + } + + ret = usb_ep_set_halt(dev->gadget->ep0); + if (ret < 0) + dev_err(&dev->gadget->dev, + "fail, usb_ep_set_halt returned %d\n", ret); + + if (dev->ep0_in_pending) + dev->ep0_in_pending = false; + else + dev->ep0_out_pending = false; + +out_unlock: + spin_unlock_irqrestore(&dev->lock, flags); + return ret; +} + static int raw_ioctl_ep_enable(struct raw_dev *dev, unsigned long value) { int ret = 0, i; @@ -798,7 +842,7 @@ static int raw_ioctl_ep_disable(struct raw_dev *dev, unsigned long value) ret = -EBUSY; goto out_unlock; } - if (dev->eps[i].state != STATE_EP_ENABLED) { + if (dev->eps[i].state == STATE_EP_DISABLED) { dev_dbg(&dev->gadget->dev, "fail, endpoint is not enabled\n"); ret = -EINVAL; goto out_unlock; @@ -832,6 +876,74 @@ out_unlock: return ret; } +static int raw_ioctl_ep_set_clear_halt_wedge(struct raw_dev *dev, + unsigned long value, bool set, bool halt) +{ + int ret = 0, i = value; + unsigned long flags; + + spin_lock_irqsave(&dev->lock, flags); + if (dev->state != STATE_DEV_RUNNING) { + dev_dbg(dev->dev, "fail, device is not running\n"); + ret = -EINVAL; + goto out_unlock; + } + if (!dev->gadget) { + dev_dbg(dev->dev, "fail, gadget is not bound\n"); + ret = -EBUSY; + goto out_unlock; + } + if (i < 0 || i >= dev->eps_num) { + dev_dbg(dev->dev, "fail, invalid endpoint\n"); + ret = -EBUSY; + goto out_unlock; + } + if (dev->eps[i].state == STATE_EP_DISABLED) { + dev_dbg(&dev->gadget->dev, "fail, endpoint is not enabled\n"); + ret = -EINVAL; + goto out_unlock; + } + if (dev->eps[i].disabling) { + dev_dbg(&dev->gadget->dev, + "fail, disable is in progress\n"); + ret = -EINVAL; + goto out_unlock; + } + if (dev->eps[i].urb_queued) { + dev_dbg(&dev->gadget->dev, + "fail, waiting for urb completion\n"); + ret = -EINVAL; + goto out_unlock; + } + if (usb_endpoint_xfer_isoc(dev->eps[i].ep->desc)) { + dev_dbg(&dev->gadget->dev, + "fail, can't halt/wedge ISO endpoint\n"); + ret = -EINVAL; + goto out_unlock; + } + + if (set && halt) { + ret = usb_ep_set_halt(dev->eps[i].ep); + if (ret < 0) + dev_err(&dev->gadget->dev, + "fail, usb_ep_set_halt returned %d\n", ret); + } else if (!set && halt) { + ret = usb_ep_clear_halt(dev->eps[i].ep); + if (ret < 0) + dev_err(&dev->gadget->dev, + "fail, usb_ep_clear_halt returned %d\n", ret); + } else if (set && !halt) { + ret = usb_ep_set_wedge(dev->eps[i].ep); + if (ret < 0) + dev_err(&dev->gadget->dev, + "fail, usb_ep_set_wedge returned %d\n", ret); + } + +out_unlock: + spin_unlock_irqrestore(&dev->lock, flags); + return ret; +} + static void gadget_ep_complete(struct usb_ep *ep, struct usb_request *req) { struct raw_ep *r_ep = (struct raw_ep *)ep->driver_data; @@ -1128,6 +1240,21 @@ static long raw_ioctl(struct file *fd, unsigned int cmd, unsigned long value) case USB_RAW_IOCTL_EPS_INFO: ret = raw_ioctl_eps_info(dev, value); break; + case USB_RAW_IOCTL_EP0_STALL: + ret = raw_ioctl_ep0_stall(dev, value); + break; + case USB_RAW_IOCTL_EP_SET_HALT: + ret = raw_ioctl_ep_set_clear_halt_wedge( + dev, value, true, true); + break; + case USB_RAW_IOCTL_EP_CLEAR_HALT: + ret = raw_ioctl_ep_set_clear_halt_wedge( + dev, value, false, true); + break; + case USB_RAW_IOCTL_EP_SET_WEDGE: + ret = raw_ioctl_ep_set_clear_halt_wedge( + dev, value, true, false); + break; default: ret = -EINVAL; } diff --git a/include/uapi/linux/usb/raw_gadget.h b/include/uapi/linux/usb/raw_gadget.h index c89f6341229c..0be685272eb1 100644 --- a/include/uapi/linux/usb/raw_gadget.h +++ b/include/uapi/linux/usb/raw_gadget.h @@ -231,4 +231,19 @@ struct usb_raw_eps_info { */ #define USB_RAW_IOCTL_EPS_INFO _IOR('U', 11, struct usb_raw_eps_info) +/* + * Stalls a pending control request on endpoint 0. + * Returns 0 on success or negative error code on failure. + */ +#define USB_RAW_IOCTL_EP0_STALL _IO('U', 12) + +/* + * Sets or clears halt or wedge status of the endpoint. + * Accepts endpoint handle as an argument. + * Returns 0 on success or negative error code on failure. + */ +#define USB_RAW_IOCTL_EP_SET_HALT _IOW('U', 13, __u32) +#define USB_RAW_IOCTL_EP_CLEAR_HALT _IOW('U', 14, __u32) +#define USB_RAW_IOCTL_EP_SET_WEDGE _IOW('U', 15, __u32) + #endif /* _UAPI__LINUX_USB_RAW_GADGET_H */ -- cgit v1.2.3 From 581701b7efd60ba13d8a7eed60cbdd7fefaf6696 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 14 May 2020 16:44:24 +0200 Subject: uapi: deprecate STATX_ALL Constants of the *_ALL type can be actively harmful due to the fact that developers will usually fail to consider the possible effects of future changes to the definition. Deprecate STATX_ALL in the uapi, while no damage has been done yet. We could keep something like this around in the kernel, but there's actually no point, since all filesystems should be explicitly checking flags that they support and not rely on the VFS masking unknown ones out: a flag could be known to the VFS, yet not known to the filesystem. Cc: David Howells Cc: linux-api@vger.kernel.org Cc: linux-man@vger.kernel.org Signed-off-by: Miklos Szeredi Reviewed-by: Christoph Hellwig --- fs/stat.c | 1 - include/uapi/linux/stat.h | 11 ++++++++++- samples/vfs/test-statx.c | 2 +- tools/include/uapi/linux/stat.h | 11 ++++++++++- 4 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/stat.c b/fs/stat.c index 030008796479..a6709e7ba71d 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -70,7 +70,6 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, memset(stat, 0, sizeof(*stat)); stat->result_mask |= STATX_BASIC_STATS; - request_mask &= STATX_ALL; query_flags &= KSTAT_QUERY_FLAGS; /* allow the fs to override these if it really wants to */ diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index ad80a5c885d5..d1192783139a 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -148,9 +148,18 @@ struct statx { #define STATX_BLOCKS 0x00000400U /* Want/got stx_blocks */ #define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */ #define STATX_BTIME 0x00000800U /* Want/got stx_btime */ -#define STATX_ALL 0x00000fffU /* All currently supported flags */ + #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ +#ifndef __KERNEL__ +/* + * This is deprecated, and shall remain the same value in the future. To avoid + * confusion please use the equivalent (STATX_BASIC_STATS | STATX_BTIME) + * instead. + */ +#define STATX_ALL 0x00000fffU +#endif + /* * Attributes to be found in stx_attributes and masked in stx_attributes_mask. * diff --git a/samples/vfs/test-statx.c b/samples/vfs/test-statx.c index a3d68159fb51..76c577ea4fd8 100644 --- a/samples/vfs/test-statx.c +++ b/samples/vfs/test-statx.c @@ -216,7 +216,7 @@ int main(int argc, char **argv) struct statx stx; int ret, raw = 0, atflag = AT_SYMLINK_NOFOLLOW; - unsigned int mask = STATX_ALL; + unsigned int mask = STATX_BASIC_STATS | STATX_BTIME; for (argv++; *argv; argv++) { if (strcmp(*argv, "-F") == 0) { diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index ad80a5c885d5..d1192783139a 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -148,9 +148,18 @@ struct statx { #define STATX_BLOCKS 0x00000400U /* Want/got stx_blocks */ #define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */ #define STATX_BTIME 0x00000800U /* Want/got stx_btime */ -#define STATX_ALL 0x00000fffU /* All currently supported flags */ + #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ +#ifndef __KERNEL__ +/* + * This is deprecated, and shall remain the same value in the future. To avoid + * confusion please use the equivalent (STATX_BASIC_STATS | STATX_BTIME) + * instead. + */ +#define STATX_ALL 0x00000fffU +#endif + /* * Attributes to be found in stx_attributes and masked in stx_attributes_mask. * -- cgit v1.2.3 From fa2fcf4f1df1559a0a4ee0f46915b496cc2ebf60 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 14 May 2020 16:44:24 +0200 Subject: statx: add mount ID Systemd is hacking around to get it and it's trivial to add to statx, so... Cc: linux-api@vger.kernel.org Cc: linux-man@vger.kernel.org Signed-off-by: Miklos Szeredi Reviewed-by: Christoph Hellwig --- fs/stat.c | 4 ++++ include/linux/stat.h | 1 + include/uapi/linux/stat.h | 6 +++++- 3 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/stat.c b/fs/stat.c index f7f07d1b73cb..3d88c99f7743 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -22,6 +22,7 @@ #include #include "internal.h" +#include "mount.h" /** * generic_fillattr - Fill in the basic attributes from the inode struct @@ -199,6 +200,8 @@ retry: goto out; error = vfs_getattr(&path, stat, request_mask, flags); + stat->mnt_id = real_mount(path.mnt)->mnt_id; + stat->result_mask |= STATX_MNT_ID; path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; @@ -563,6 +566,7 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer) tmp.stx_rdev_minor = MINOR(stat->rdev); tmp.stx_dev_major = MAJOR(stat->dev); tmp.stx_dev_minor = MINOR(stat->dev); + tmp.stx_mnt_id = stat->mnt_id; return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } diff --git a/include/linux/stat.h b/include/linux/stat.h index 528c4baad091..56614af83d4a 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -47,6 +47,7 @@ struct kstat { struct timespec64 ctime; struct timespec64 btime; /* File creation time */ u64 blocks; + u64 mnt_id; }; #endif diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index d1192783139a..d81456247f10 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -123,7 +123,10 @@ struct statx { __u32 stx_dev_major; /* ID of device containing file [uncond] */ __u32 stx_dev_minor; /* 0x90 */ - __u64 __spare2[14]; /* Spare space for future expansion */ + __u64 stx_mnt_id; + __u64 __spare2; + /* 0xa0 */ + __u64 __spare3[12]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -148,6 +151,7 @@ struct statx { #define STATX_BLOCKS 0x00000400U /* Want/got stx_blocks */ #define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */ #define STATX_BTIME 0x00000800U /* Want/got stx_btime */ +#define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ -- cgit v1.2.3 From 80340fe3605c0e78cfe496c3b3878be828cfdbfe Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 14 May 2020 16:44:24 +0200 Subject: statx: add mount_root Determining whether a path or file descriptor refers to a mountpoint (or more precisely a mount root) is not trivial using current tools. Add a flag to statx that indicates whether the path or fd refers to the root of a mount or not. Cc: linux-api@vger.kernel.org Cc: linux-man@vger.kernel.org Reported-by: Lennart Poettering Reported-by: J. Bruce Fields Signed-off-by: Miklos Szeredi Reviewed-by: Christoph Hellwig --- fs/stat.c | 3 +++ include/uapi/linux/stat.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/stat.c b/fs/stat.c index 3d88c99f7743..b9faa6cafafe 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -202,6 +202,9 @@ retry: error = vfs_getattr(&path, stat, request_mask, flags); stat->mnt_id = real_mount(path.mnt)->mnt_id; stat->result_mask |= STATX_MNT_ID; + if (path.mnt->mnt_root == path.dentry) + stat->attributes |= STATX_ATTR_MOUNT_ROOT; + stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT; path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index d81456247f10..6df9348bb277 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -181,6 +181,7 @@ struct statx { #define STATX_ATTR_NODUMP 0x00000040 /* [I] File is not to be dumped */ #define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */ #define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ +#define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ -- cgit v1.2.3 From c8ffd8bcdd28296a198f237cc595148a8d4adfbe Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 14 May 2020 16:44:25 +0200 Subject: vfs: add faccessat2 syscall POSIX defines faccessat() as having a fourth "flags" argument, while the linux syscall doesn't have it. Glibc tries to emulate AT_EACCESS and AT_SYMLINK_NOFOLLOW, but AT_EACCESS emulation is broken. Add a new faccessat(2) syscall with the added flags argument and implement both flags. The value of AT_EACCESS is defined in glibc headers to be the same as AT_REMOVEDIR. Use this value for the kernel interface as well, together with the explanatory comment. Also add AT_EMPTY_PATH support, which is not documented by POSIX, but can be useful and is trivial to implement. Signed-off-by: Miklos Szeredi --- arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/arm/tools/syscall.tbl | 1 + arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 2 ++ arch/ia64/kernel/syscalls/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/mips/kernel/syscalls/syscall_n32.tbl | 1 + arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 1 + arch/parisc/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/s390/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + fs/internal.h | 1 - fs/open.c | 34 ++++++++++++++++++++++------- include/linux/syscalls.h | 6 +++-- include/uapi/asm-generic/unistd.h | 4 +++- include/uapi/linux/fcntl.h | 10 +++++++++ 23 files changed, 62 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 36d42da7466a..5ddd128d4b7a 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -477,3 +477,4 @@ # 545 reserved for clone3 547 common openat2 sys_openat2 548 common pidfd_getfd sys_pidfd_getfd +549 common faccessat2 sys_faccessat2 diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 4d1cf74a2caa..d5cae5ffede0 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -451,3 +451,4 @@ 435 common clone3 sys_clone3 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 803039d504de..3b859596840d 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -38,7 +38,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 439 +#define __NR_compat_syscalls 440 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index c1c61635f89c..6d95d0c8bf2f 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -883,6 +883,8 @@ __SYSCALL(__NR_clone3, sys_clone3) __SYSCALL(__NR_openat2, sys_openat2) #define __NR_pidfd_getfd 438 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) +#define __NR_faccessat2 439 +__SYSCALL(__NR_faccessat2, sys_faccessat2) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index 042911e670b8..49e325b604b3 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -358,3 +358,4 @@ # 435 reserved for clone3 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index f4f49fcb76d0..f71b1bbcc198 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -437,3 +437,4 @@ 435 common clone3 __sys_clone3 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 4c67b11f9c9e..edacc4561f2b 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -443,3 +443,4 @@ 435 common clone3 sys_clone3 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 1f9e8ad636cc..f777141f5256 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -376,3 +376,4 @@ 435 n32 clone3 __sys_clone3 437 n32 openat2 sys_openat2 438 n32 pidfd_getfd sys_pidfd_getfd +439 n32 faccessat2 sys_faccessat2 diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index c0b9d802dbf6..da8c76394e17 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -352,3 +352,4 @@ 435 n64 clone3 __sys_clone3 437 n64 openat2 sys_openat2 438 n64 pidfd_getfd sys_pidfd_getfd +439 n64 faccessat2 sys_faccessat2 diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index ac586774c980..13280625d312 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -425,3 +425,4 @@ 435 o32 clone3 __sys_clone3 437 o32 openat2 sys_openat2 438 o32 pidfd_getfd sys_pidfd_getfd +439 o32 faccessat2 sys_faccessat2 diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index 52a15f5cd130..5a758fa6ec52 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -435,3 +435,4 @@ 435 common clone3 sys_clone3_wrapper 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 220ae11555f2..f833a3190822 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -527,3 +527,4 @@ 435 spu clone3 sys_ni_syscall 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index bd7bd3581a0f..bfdcb7633957 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -440,3 +440,4 @@ 435 common clone3 sys_clone3 sys_clone3 437 common openat2 sys_openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 sys_faccessat2 diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index c7a30fcd135f..acc35daa1b79 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -440,3 +440,4 @@ # 435 reserved for clone3 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index f13615ecdecc..8004a276cb74 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -483,3 +483,4 @@ # 435 reserved for clone3 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 54581ac671b4..d8f8a1a69ed1 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -442,3 +442,4 @@ 435 i386 clone3 sys_clone3 437 i386 openat2 sys_openat2 438 i386 pidfd_getfd sys_pidfd_getfd +439 i386 faccessat2 sys_faccessat2 diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 37b844f839bc..78847b32e137 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -359,6 +359,7 @@ 435 common clone3 sys_clone3 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 85a9ab1bc04d..69d0d73876b3 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -408,3 +408,4 @@ 435 common clone3 sys_clone3 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 diff --git a/fs/internal.h b/fs/internal.h index aa5d45524e87..0d467e32dd7e 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -126,7 +126,6 @@ extern struct open_how build_open_how(int flags, umode_t mode); extern int build_open_flags(const struct open_how *how, struct open_flags *op); long do_sys_ftruncate(unsigned int fd, loff_t length, int small); -long do_faccessat(int dfd, const char __user *filename, int mode); int do_fchmodat(int dfd, const char __user *filename, umode_t mode); int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag); diff --git a/fs/open.c b/fs/open.c index 0ea3cd1a1250..e62b1db06638 100644 --- a/fs/open.c +++ b/fs/open.c @@ -394,20 +394,30 @@ static const struct cred *access_override_creds(void) return old_cred; } -long do_faccessat(int dfd, const char __user *filename, int mode) +long do_faccessat(int dfd, const char __user *filename, int mode, int flags) { struct path path; struct inode *inode; int res; unsigned int lookup_flags = LOOKUP_FOLLOW; - const struct cred *old_cred; + const struct cred *old_cred = NULL; if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */ return -EINVAL; - old_cred = access_override_creds(); - if (!old_cred) - return -ENOMEM; + if (flags & ~(AT_EACCESS | AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) + return -EINVAL; + + if (flags & AT_SYMLINK_NOFOLLOW) + lookup_flags &= ~LOOKUP_FOLLOW; + if (flags & AT_EMPTY_PATH) + lookup_flags |= LOOKUP_EMPTY; + + if (!(flags & AT_EACCESS)) { + old_cred = access_override_creds(); + if (!old_cred) + return -ENOMEM; + } retry: res = user_path_at(dfd, filename, lookup_flags, &path); @@ -450,18 +460,26 @@ out_path_release: goto retry; } out: - revert_creds(old_cred); + if (old_cred) + revert_creds(old_cred); + return res; } SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) { - return do_faccessat(dfd, filename, mode); + return do_faccessat(dfd, filename, mode, 0); +} + +SYSCALL_DEFINE4(faccessat2, int, dfd, const char __user *, filename, int, mode, + int, flags) +{ + return do_faccessat(dfd, filename, mode, flags); } SYSCALL_DEFINE2(access, const char __user *, filename, int, mode) { - return do_faccessat(AT_FDCWD, filename, mode); + return do_faccessat(AT_FDCWD, filename, mode, 0); } int ksys_chdir(const char __user *filename) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 1815065d52f3..7c354c2955f5 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -428,6 +428,8 @@ asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length); #endif asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len); asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode); +asmlinkage long sys_faccessat2(int dfd, const char __user *filename, int mode, + int flags); asmlinkage long sys_chdir(const char __user *filename); asmlinkage long sys_fchdir(unsigned int fd); asmlinkage long sys_chroot(const char __user *filename); @@ -1333,11 +1335,11 @@ static inline int ksys_chmod(const char __user *filename, umode_t mode) return do_fchmodat(AT_FDCWD, filename, mode); } -extern long do_faccessat(int dfd, const char __user *filename, int mode); +long do_faccessat(int dfd, const char __user *filename, int mode, int flags); static inline long ksys_access(const char __user *filename, int mode) { - return do_faccessat(AT_FDCWD, filename, mode); + return do_faccessat(AT_FDCWD, filename, mode, 0); } extern int do_fchownat(int dfd, const char __user *filename, uid_t user, diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 3a3201e4618e..f4a01305d9a6 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -855,9 +855,11 @@ __SYSCALL(__NR_clone3, sys_clone3) __SYSCALL(__NR_openat2, sys_openat2) #define __NR_pidfd_getfd 438 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) +#define __NR_faccessat2 439 +__SYSCALL(__NR_faccessat2, sys_faccessat2) #undef __NR_syscalls -#define __NR_syscalls 439 +#define __NR_syscalls 440 /* * 32 bit systems traditionally used different diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index ca88b7bce553..2f86b2ad6d7e 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -84,10 +84,20 @@ #define DN_ATTRIB 0x00000020 /* File changed attibutes */ #define DN_MULTISHOT 0x80000000 /* Don't remove notifier */ +/* + * The constants AT_REMOVEDIR and AT_EACCESS have the same value. AT_EACCESS is + * meaningful only to faccessat, while AT_REMOVEDIR is meaningful only to + * unlinkat. The two functions do completely different things and therefore, + * the flags can be allowed to overlap. For example, passing AT_REMOVEDIR to + * faccessat would be undefined behavior and thus treating it equivalent to + * AT_EACCESS is valid undefined behavior. + */ #define AT_FDCWD -100 /* Special value used to indicate openat should use the current working directory. */ #define AT_SYMLINK_NOFOLLOW 0x100 /* Do not follow symbolic links. */ +#define AT_EACCESS 0x200 /* Test access permitted for + effective IDs, not real IDs. */ #define AT_REMOVEDIR 0x200 /* Remove directory instead of unlinking file. */ #define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */ -- cgit v1.2.3 From 7aebfa1b3885b5aa29fcb4a596d0485ac463bbe8 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Wed, 13 May 2020 18:50:27 -0700 Subject: bpf: Support narrow loads from bpf_sock_addr.user_port bpf_sock_addr.user_port supports only 4-byte load and it leads to ugly code in BPF programs, like: volatile __u32 user_port = ctx->user_port; __u16 port = bpf_ntohs(user_port); Since otherwise clang may optimize the load to be 2-byte and it's rejected by verifier. Add support for 1- and 2-byte loads same way as it's supported for other fields in bpf_sock_addr like user_ip4, msg_src_ip4, etc. Signed-off-by: Andrey Ignatov Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/c1e983f4c17573032601d0b2b1f9d1274f24bc16.1589420814.git.rdna@fb.com --- include/uapi/linux/bpf.h | 2 +- net/core/filter.c | 15 +++++++-------- tools/include/uapi/linux/bpf.h | 2 +- 3 files changed, 9 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bfb31c1be219..85cfdffde182 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3728,7 +3728,7 @@ struct bpf_sock_addr { __u32 user_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. * Stored in network byte order. */ - __u32 user_port; /* Allows 4-byte read and write. + __u32 user_port; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order */ __u32 family; /* Allows 4-byte read, but no write */ diff --git a/net/core/filter.c b/net/core/filter.c index da0634979f53..1fe8c0c2d408 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7029,6 +7029,7 @@ static bool sock_addr_is_valid_access(int off, int size, case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): + case bpf_ctx_range(struct bpf_sock_addr, user_port): if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); @@ -7059,10 +7060,6 @@ static bool sock_addr_is_valid_access(int off, int size, return false; } break; - case bpf_ctx_range(struct bpf_sock_addr, user_port): - if (size != size_default) - return false; - break; case offsetof(struct bpf_sock_addr, sk): if (type != BPF_READ) return false; @@ -7958,8 +7955,8 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { + int off, port_size = sizeof_field(struct sockaddr_in6, sin6_port); struct bpf_insn *insn = insn_buf; - int off; switch (si->off) { case offsetof(struct bpf_sock_addr, user_family): @@ -7994,9 +7991,11 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, offsetof(struct sockaddr_in6, sin6_port)); BUILD_BUG_ON(sizeof_field(struct sockaddr_in, sin_port) != sizeof_field(struct sockaddr_in6, sin6_port)); - SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD(struct bpf_sock_addr_kern, - struct sockaddr_in6, uaddr, - sin6_port, tmp_reg); + /* Account for sin6_port being smaller than user_port. */ + port_size = min(port_size, BPF_LDST_BYTES(si)); + SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( + struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, + sin6_port, bytes_to_bpf_size(port_size), 0, tmp_reg); break; case offsetof(struct bpf_sock_addr, family): diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index bfb31c1be219..85cfdffde182 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3728,7 +3728,7 @@ struct bpf_sock_addr { __u32 user_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. * Stored in network byte order. */ - __u32 user_port; /* Allows 4-byte read and write. + __u32 user_port; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order */ __u32 family; /* Allows 4-byte read, but no write */ -- cgit v1.2.3 From f307fa2cb4c935f7f1ff0aeb880c7b44fb9a642b Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Thu, 14 May 2020 13:03:47 -0700 Subject: bpf: Introduce bpf_sk_{, ancestor_}cgroup_id helpers With having ability to lookup sockets in cgroup skb programs it becomes useful to access cgroup id of retrieved sockets so that policies can be implemented based on origin cgroup of such socket. For example, a container running in a cgroup can have cgroup skb ingress program that can lookup peer socket that is sending packets to a process inside the container and decide whether those packets should be allowed or denied based on cgroup id of the peer. More specifically such ingress program can implement intra-host policy "allow incoming packets only from this same container and not from any other container on same host" w/o relying on source IP addresses since quite often it can be the case that containers share same IP address on the host. Introduce two new helpers for this use-case: bpf_sk_cgroup_id() and bpf_sk_ancestor_cgroup_id(). These helpers are similar to existing bpf_skb_{,ancestor_}cgroup_id helpers with the only difference that sk is used to get cgroup id instead of skb, and share code with them. See documentation in UAPI for more details. Signed-off-by: Andrey Ignatov Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/f5884981249ce911f63e9b57ecd5d7d19154ff39.1589486450.git.rdna@fb.com --- include/uapi/linux/bpf.h | 36 ++++++++++++++++++++++++- net/core/filter.c | 60 +++++++++++++++++++++++++++++++++++------- tools/include/uapi/linux/bpf.h | 36 ++++++++++++++++++++++++- 3 files changed, 121 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 85cfdffde182..146c742f1d49 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3121,6 +3121,38 @@ union bpf_attr { * 0 on success, or a negative error in case of failure: * * **-EOVERFLOW** if an overflow happened: The same object will be tried again. + * + * u64 bpf_sk_cgroup_id(struct bpf_sock *sk) + * Description + * Return the cgroup v2 id of the socket *sk*. + * + * *sk* must be a non-**NULL** pointer to a full socket, e.g. one + * returned from **bpf_sk_lookup_xxx**\ (), + * **bpf_sk_fullsock**\ (), etc. The format of returned id is + * same as in **bpf_skb_cgroup_id**\ (). + * + * This helper is available only if the kernel was compiled with + * the **CONFIG_SOCK_CGROUP_DATA** configuration option. + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * u64 bpf_sk_ancestor_cgroup_id(struct bpf_sock *sk, int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *sk* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *sk*, then return value will be same as that + * of **bpf_sk_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *sk*. + * + * The format of returned id and helper limitations are same as in + * **bpf_sk_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3250,7 +3282,9 @@ union bpf_attr { FN(sk_assign), \ FN(ktime_get_boot_ns), \ FN(seq_printf), \ - FN(seq_write), + FN(seq_write), \ + FN(sk_cgroup_id), \ + FN(sk_ancestor_cgroup_id), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/net/core/filter.c b/net/core/filter.c index a47dc5b9dad4..5815902bb617 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4003,16 +4003,22 @@ static const struct bpf_func_proto bpf_skb_under_cgroup_proto = { }; #ifdef CONFIG_SOCK_CGROUP_DATA +static inline u64 __bpf_sk_cgroup_id(struct sock *sk) +{ + struct cgroup *cgrp; + + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + return cgroup_id(cgrp); +} + BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb) { struct sock *sk = skb_to_full_sk(skb); - struct cgroup *cgrp; if (!sk || !sk_fullsock(sk)) return 0; - cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - return cgroup_id(cgrp); + return __bpf_sk_cgroup_id(sk); } static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { @@ -4022,16 +4028,12 @@ static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { .arg1_type = ARG_PTR_TO_CTX, }; -BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, - ancestor_level) +static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk, + int ancestor_level) { - struct sock *sk = skb_to_full_sk(skb); struct cgroup *ancestor; struct cgroup *cgrp; - if (!sk || !sk_fullsock(sk)) - return 0; - cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ancestor = cgroup_ancestor(cgrp, ancestor_level); if (!ancestor) @@ -4040,6 +4042,17 @@ BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, return cgroup_id(ancestor); } +BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, + ancestor_level) +{ + struct sock *sk = skb_to_full_sk(skb); + + if (!sk || !sk_fullsock(sk)) + return 0; + + return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level); +} + static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { .func = bpf_skb_ancestor_cgroup_id, .gpl_only = false, @@ -4047,6 +4060,31 @@ static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; + +BPF_CALL_1(bpf_sk_cgroup_id, struct sock *, sk) +{ + return __bpf_sk_cgroup_id(sk); +} + +static const struct bpf_func_proto bpf_sk_cgroup_id_proto = { + .func = bpf_sk_cgroup_id, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_SOCKET, +}; + +BPF_CALL_2(bpf_sk_ancestor_cgroup_id, struct sock *, sk, int, ancestor_level) +{ + return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level); +} + +static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = { + .func = bpf_sk_ancestor_cgroup_id, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_SOCKET, + .arg2_type = ARG_ANYTHING, +}; #endif static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff, @@ -6159,6 +6197,10 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skb_cgroup_id_proto; case BPF_FUNC_skb_ancestor_cgroup_id: return &bpf_skb_ancestor_cgroup_id_proto; + case BPF_FUNC_sk_cgroup_id: + return &bpf_sk_cgroup_id_proto; + case BPF_FUNC_sk_ancestor_cgroup_id: + return &bpf_sk_ancestor_cgroup_id_proto; #endif #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 85cfdffde182..146c742f1d49 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3121,6 +3121,38 @@ union bpf_attr { * 0 on success, or a negative error in case of failure: * * **-EOVERFLOW** if an overflow happened: The same object will be tried again. + * + * u64 bpf_sk_cgroup_id(struct bpf_sock *sk) + * Description + * Return the cgroup v2 id of the socket *sk*. + * + * *sk* must be a non-**NULL** pointer to a full socket, e.g. one + * returned from **bpf_sk_lookup_xxx**\ (), + * **bpf_sk_fullsock**\ (), etc. The format of returned id is + * same as in **bpf_skb_cgroup_id**\ (). + * + * This helper is available only if the kernel was compiled with + * the **CONFIG_SOCK_CGROUP_DATA** configuration option. + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * u64 bpf_sk_ancestor_cgroup_id(struct bpf_sock *sk, int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *sk* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *sk*, then return value will be same as that + * of **bpf_sk_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *sk*. + * + * The format of returned id and helper limitations are same as in + * **bpf_sk_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3250,7 +3282,9 @@ union bpf_attr { FN(sk_assign), \ FN(ktime_get_boot_ns), \ FN(seq_printf), \ - FN(seq_write), + FN(seq_write), \ + FN(sk_cgroup_id), \ + FN(sk_ancestor_cgroup_id), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call -- cgit v1.2.3 From c8741e2bfe872425ea6f10bb6f7dc1d67bc60c3a Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 14 May 2020 12:51:25 +0200 Subject: xdp: Allow bpf_xdp_adjust_tail() to grow packet size Finally, after all drivers have a frame size, allow BPF-helper bpf_xdp_adjust_tail() to grow or extend packet size at frame tail. Remember that helper/macro xdp_data_hard_end have reserved some tailroom. Thus, this helper makes sure that the BPF-prog don't have access to this tailroom area. V2: Remove one chicken check and use WARN_ONCE for other Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/158945348530.97035.12577148209134239291.stgit@firesoul --- include/uapi/linux/bpf.h | 4 ++-- net/core/filter.c | 11 +++++++++-- 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 32cbf36c7729..b9b8a0f63b91 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2015,8 +2015,8 @@ union bpf_attr { * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta) * Description * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is - * only possible to shrink the packet as of this writing, - * therefore *delta* must be a negative integer. + * possible to both shrink and grow the packet tail. + * Shrink done via *delta* being a negative integer. * * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers diff --git a/net/core/filter.c b/net/core/filter.c index 5815902bb617..e7b033dad44e 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3411,12 +3411,19 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) { + void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */ void *data_end = xdp->data_end + offset; - /* only shrinking is allowed for now. */ - if (unlikely(offset >= 0)) + /* Notice that xdp_data_hard_end have reserved some tailroom */ + if (unlikely(data_end > data_hard_end)) return -EINVAL; + /* ALL drivers MUST init xdp->frame_sz, chicken check below */ + if (unlikely(xdp->frame_sz > PAGE_SIZE)) { + WARN_ONCE(1, "Too BIG xdp->frame_sz = %d\n", xdp->frame_sz); + return -EINVAL; + } + if (unlikely(data_end < xdp->data + ETH_HLEN)) return -EINVAL; -- cgit v1.2.3 From a17b53c4a4b55ec322c132b6670743612229ee9c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 13 May 2020 16:03:53 -0700 Subject: bpf, capability: Introduce CAP_BPF Split BPF operations that are allowed under CAP_SYS_ADMIN into combination of CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN. For backward compatibility include them in CAP_SYS_ADMIN as well. The end result provides simple safety model for applications that use BPF: - to load tracing program types BPF_PROG_TYPE_{KPROBE, TRACEPOINT, PERF_EVENT, RAW_TRACEPOINT, etc} use CAP_BPF and CAP_PERFMON - to load networking program types BPF_PROG_TYPE_{SCHED_CLS, XDP, SK_SKB, etc} use CAP_BPF and CAP_NET_ADMIN There are few exceptions from this rule: - bpf_trace_printk() is allowed in networking programs, but it's using tracing mechanism, hence this helper needs additional CAP_PERFMON if networking program is using this helper. - BPF_F_ZERO_SEED flag for hash/lru map is allowed under CAP_SYS_ADMIN only to discourage production use. - BPF HW offload is allowed under CAP_SYS_ADMIN. - bpf_probe_write_user() is allowed under CAP_SYS_ADMIN only. CAPs are not checked at attach/detach time with two exceptions: - loading BPF_PROG_TYPE_CGROUP_SKB is allowed for unprivileged users, hence CAP_NET_ADMIN is required at attach time. - flow_dissector detach doesn't check prog FD at detach, hence CAP_NET_ADMIN is required at detach time. CAP_SYS_ADMIN is required to iterate BPF objects (progs, maps, links) via get_next_id command and convert them to file descriptor via GET_FD_BY_ID command. This restriction guarantees that mutliple tasks with CAP_BPF are not able to affect each other. That leads to clean isolation of tasks. For example: task A with CAP_BPF and CAP_NET_ADMIN loads and attaches a firewall via bpf_link. task B with the same capabilities cannot detach that firewall unless task A explicitly passed link FD to task B via scm_rights or bpffs. CAP_SYS_ADMIN can still detach/unload everything. Two networking user apps with CAP_SYS_ADMIN and CAP_NET_ADMIN can accidentely mess with each other programs and maps. Two networking user apps with CAP_NET_ADMIN and CAP_BPF cannot affect each other. CAP_NET_ADMIN + CAP_BPF allows networking programs access only packet data. Such networking progs cannot access arbitrary kernel memory or leak pointers. bpftool, bpftrace, bcc tools binaries should NOT be installed with CAP_BPF and CAP_PERFMON, since unpriv users will be able to read kernel secrets. But users with these two permissions will be able to use these tracing tools. CAP_PERFMON is least secure, since it allows kprobes and kernel memory access. CAP_NET_ADMIN can stop network traffic via iproute2. CAP_BPF is the safest from security point of view and harmless on its own. Having CAP_BPF and/or CAP_NET_ADMIN is not enough to write into arbitrary map and if that map is used by firewall-like bpf prog. CAP_BPF allows many bpf prog_load commands in parallel. The verifier may consume large amount of memory and significantly slow down the system. Existing unprivileged BPF operations are not affected. In particular unprivileged users are allowed to load socket_filter and cg_skb program types and to create array, hash, prog_array, map-in-map map types. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200513230355.7858-2-alexei.starovoitov@gmail.com --- include/linux/capability.h | 5 +++++ include/uapi/linux/capability.h | 34 +++++++++++++++++++++++++++++++++- security/selinux/include/classmap.h | 4 ++-- 3 files changed, 40 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index 027d7e4a853b..b4345b38a6be 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -256,6 +256,11 @@ static inline bool perfmon_capable(void) return capable(CAP_PERFMON) || capable(CAP_SYS_ADMIN); } +static inline bool bpf_capable(void) +{ + return capable(CAP_BPF) || capable(CAP_SYS_ADMIN); +} + /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index e58c9636741b..c7372180a0a9 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -274,6 +274,7 @@ struct vfs_ns_cap_data { arbitrary SCSI commands */ /* Allow setting encryption key on loopback filesystem */ /* Allow setting zone reclaim policy */ +/* Allow everything under CAP_BPF and CAP_PERFMON for backward compatibility */ #define CAP_SYS_ADMIN 21 @@ -374,7 +375,38 @@ struct vfs_ns_cap_data { #define CAP_PERFMON 38 -#define CAP_LAST_CAP CAP_PERFMON +/* + * CAP_BPF allows the following BPF operations: + * - Creating all types of BPF maps + * - Advanced verifier features + * - Indirect variable access + * - Bounded loops + * - BPF to BPF function calls + * - Scalar precision tracking + * - Larger complexity limits + * - Dead code elimination + * - And potentially other features + * - Loading BPF Type Format (BTF) data + * - Retrieve xlated and JITed code of BPF programs + * - Use bpf_spin_lock() helper + * + * CAP_PERFMON relaxes the verifier checks further: + * - BPF progs can use of pointer-to-integer conversions + * - speculation attack hardening measures are bypassed + * - bpf_probe_read to read arbitrary kernel memory is allowed + * - bpf_trace_printk to print kernel memory is allowed + * + * CAP_SYS_ADMIN is required to use bpf_probe_write_user. + * + * CAP_SYS_ADMIN is required to iterate system wide loaded + * programs, maps, links, BTFs and convert their IDs to file descriptors. + * + * CAP_PERFMON and CAP_BPF are required to load tracing programs. + * CAP_NET_ADMIN and CAP_BPF are required to load networking programs. + */ +#define CAP_BPF 39 + +#define CAP_LAST_CAP CAP_BPF #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP) diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index d233ab3f1533..98e1513b608a 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -27,9 +27,9 @@ "audit_control", "setfcap" #define COMMON_CAP2_PERMS "mac_override", "mac_admin", "syslog", \ - "wake_alarm", "block_suspend", "audit_read", "perfmon" + "wake_alarm", "block_suspend", "audit_read", "perfmon", "bpf" -#if CAP_LAST_CAP > CAP_PERFMON +#if CAP_LAST_CAP > CAP_BPF #error New capability defined, please update COMMON_CAP2_PERMS. #endif -- cgit v1.2.3 From f8ab1807a9c9aa14478920e64d1c9d3685aae26f Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Fri, 15 May 2020 14:40:11 +0300 Subject: net: sched: introduce terse dump flag Add new TCA_DUMP_FLAGS attribute and use it in cls API to request terse filter output from classifiers with TCA_DUMP_FLAGS_TERSE flag. This option is intended to be used to improve performance of TC filter dump when userland only needs to obtain stats and not the whole classifier/action data. Extend struct tcf_proto_ops with new terse_dump() callback that must be defined by supporting classifier implementations. Support of the options in specific classifiers and actions is implemented in following patches in the series. Signed-off-by: Vlad Buslov Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/sch_generic.h | 4 ++++ include/uapi/linux/rtnetlink.h | 6 ++++++ net/sched/cls_api.c | 39 +++++++++++++++++++++++++++++++-------- 3 files changed, 41 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index ab87a8b86a32..c510b03b9751 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -330,6 +330,10 @@ struct tcf_proto_ops { int (*dump)(struct net*, struct tcf_proto*, void *, struct sk_buff *skb, struct tcmsg*, bool); + int (*terse_dump)(struct net *net, + struct tcf_proto *tp, void *fh, + struct sk_buff *skb, + struct tcmsg *t, bool rtnl_held); int (*tmplt_dump)(struct sk_buff *skb, struct net *net, void *tmplt_priv); diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 4a8c5b745157..073e71ef6bdd 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -609,11 +609,17 @@ enum { TCA_HW_OFFLOAD, TCA_INGRESS_BLOCK, TCA_EGRESS_BLOCK, + TCA_DUMP_FLAGS, __TCA_MAX }; #define TCA_MAX (__TCA_MAX - 1) +#define TCA_DUMP_FLAGS_TERSE (1 << 0) /* Means that in dump user gets only basic + * data necessary to identify the objects + * (handle, cookie, etc.) and stats. + */ + #define TCA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcmsg)))) #define TCA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcmsg)) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 299b963c796e..cb2c10e0fee5 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1851,7 +1851,7 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, struct tcf_proto *tp, struct tcf_block *block, struct Qdisc *q, u32 parent, void *fh, u32 portid, u32 seq, u16 flags, int event, - bool rtnl_held) + bool terse_dump, bool rtnl_held) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -1878,6 +1878,14 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; if (!fh) { tcm->tcm_handle = 0; + } else if (terse_dump) { + if (tp->ops->terse_dump) { + if (tp->ops->terse_dump(net, tp, fh, skb, tcm, + rtnl_held) < 0) + goto nla_put_failure; + } else { + goto cls_op_not_supp; + } } else { if (tp->ops->dump && tp->ops->dump(net, tp, fh, skb, tcm, rtnl_held) < 0) @@ -1888,6 +1896,7 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, out_nlmsg_trim: nla_put_failure: +cls_op_not_supp: nlmsg_trim(skb, b); return -1; } @@ -1908,7 +1917,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, n->nlmsg_seq, n->nlmsg_flags, event, - rtnl_held) <= 0) { + false, rtnl_held) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -1940,7 +1949,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER, - rtnl_held) <= 0) { + false, rtnl_held) <= 0) { NL_SET_ERR_MSG(extack, "Failed to build del event notification"); kfree_skb(skb); return -EINVAL; @@ -2501,6 +2510,7 @@ struct tcf_dump_args { struct tcf_block *block; struct Qdisc *q; u32 parent; + bool terse_dump; }; static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) @@ -2511,12 +2521,12 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) return tcf_fill_node(net, a->skb, tp, a->block, a->q, a->parent, n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTFILTER, true); + RTM_NEWTFILTER, a->terse_dump, true); } static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, struct sk_buff *skb, struct netlink_callback *cb, - long index_start, long *p_index) + long index_start, long *p_index, bool terse) { struct net *net = sock_net(skb->sk); struct tcf_block *block = chain->block; @@ -2545,7 +2555,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, if (tcf_fill_node(net, skb, tp, block, q, parent, NULL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTFILTER, true) <= 0) + RTM_NEWTFILTER, false, true) <= 0) goto errout; cb->args[1] = 1; } @@ -2561,6 +2571,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, arg.w.skip = cb->args[1] - 1; arg.w.count = 0; arg.w.cookie = cb->args[2]; + arg.terse_dump = terse; tp->ops->walk(tp, &arg.w, true); cb->args[2] = arg.w.cookie; cb->args[1] = arg.w.count + 1; @@ -2574,6 +2585,10 @@ errout: return false; } +static const struct nla_policy tcf_tfilter_dump_policy[TCA_MAX + 1] = { + [TCA_DUMP_FLAGS] = NLA_POLICY_BITFIELD32(TCA_DUMP_FLAGS_TERSE), +}; + /* called with RTNL */ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) { @@ -2583,6 +2598,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) struct Qdisc *q = NULL; struct tcf_block *block; struct tcmsg *tcm = nlmsg_data(cb->nlh); + bool terse_dump = false; long index_start; long index; u32 parent; @@ -2592,10 +2608,17 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; err = nlmsg_parse_deprecated(cb->nlh, sizeof(*tcm), tca, TCA_MAX, - NULL, cb->extack); + tcf_tfilter_dump_policy, cb->extack); if (err) return err; + if (tca[TCA_DUMP_FLAGS]) { + struct nla_bitfield32 flags = + nla_get_bitfield32(tca[TCA_DUMP_FLAGS]); + + terse_dump = flags.value & TCA_DUMP_FLAGS_TERSE; + } + if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) { block = tcf_block_refcnt_get(net, tcm->tcm_block_index); if (!block) @@ -2653,7 +2676,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) nla_get_u32(tca[TCA_CHAIN]) != chain->index) continue; if (!tcf_chain_dump(chain, q, parent, skb, cb, - index_start, &index)) { + index_start, &index, terse_dump)) { tcf_chain_put(chain); err = -EMSGSIZE; break; -- cgit v1.2.3 From 0d9b5b3af134cddfdc1dd31d41946a0ad389bbf2 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 15 May 2020 18:38:04 +0200 Subject: io_uring: add 'cq_flags' field for the CQ ring This patch adds the new 'cq_flags' field that should be written by the application and read by the kernel. This new field is available to the userspace application through 'cq_off.flags'. We are using 4-bytes previously reserved and set to zero. This means that if the application finds this field to zero, then the new functionality is not supported. In the next patch we will introduce the first flag available. Signed-off-by: Stefano Garzarella Signed-off-by: Jens Axboe --- fs/io_uring.c | 10 +++++++++- include/uapi/linux/io_uring.h | 4 +++- 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 982066844c5a..02250693a406 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -142,7 +142,7 @@ struct io_rings { */ u32 sq_dropped; /* - * Runtime flags + * Runtime SQ flags * * Written by the kernel, shouldn't be modified by the * application. @@ -151,6 +151,13 @@ struct io_rings { * for IORING_SQ_NEED_WAKEUP after updating the sq tail. */ u32 sq_flags; + /* + * Runtime CQ flags + * + * Written by the application, shouldn't be modified by the + * kernel. + */ + u32 cq_flags; /* * Number of completion events lost because the queue was full; * this should be avoided by the application by making sure @@ -7930,6 +7937,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, p->cq_off.ring_entries = offsetof(struct io_rings, cq_ring_entries); p->cq_off.overflow = offsetof(struct io_rings, cq_overflow); p->cq_off.cqes = offsetof(struct io_rings, cqes); + p->cq_off.flags = offsetof(struct io_rings, cq_flags); p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index e48d746b8e2a..602bb0ece607 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -204,7 +204,9 @@ struct io_cqring_offsets { __u32 ring_entries; __u32 overflow; __u32 cqes; - __u64 resv[2]; + __u32 flags; + __u32 resv1; + __u64 resv2; }; /* -- cgit v1.2.3 From 7e55a19cf6e70ce08964b46dbbfbdb07fbc995fc Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 15 May 2020 18:38:05 +0200 Subject: io_uring: add IORING_CQ_EVENTFD_DISABLED to the CQ ring flags This new flag should be set/clear from the application to disable/enable eventfd notifications when a request is completed and queued to the CQ ring. Before this patch, notifications were always sent if an eventfd is registered, so IORING_CQ_EVENTFD_DISABLED is not set during the initialization. It will be up to the application to set the flag after initialization if no notifications are required at the beginning. Signed-off-by: Stefano Garzarella Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 ++ include/uapi/linux/io_uring.h | 7 +++++++ 2 files changed, 9 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 02250693a406..f800b0b4498f 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1153,6 +1153,8 @@ static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx) { if (!ctx->cq_ev_fd) return false; + if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED) + return false; if (!ctx->eventfd_async) return true; return io_wq_current_is_worker(); diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 602bb0ece607..8c5775df08b8 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -209,6 +209,13 @@ struct io_cqring_offsets { __u64 resv2; }; +/* + * cq_ring->flags + */ + +/* disable eventfd notifications */ +#define IORING_CQ_EVENTFD_DISABLED (1U << 0) + /* * io_uring_enter(2) flags */ -- cgit v1.2.3 From f2a8d5c7a218b9c24befb756c4eb30aa550ce822 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sun, 17 May 2020 14:18:06 +0300 Subject: io_uring: add tee(2) support Add IORING_OP_TEE implementing tee(2) support. Almost identical to splice bits, but without offsets. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- fs/io_uring.c | 62 ++++++++++++++++++++++++++++++++++++++++--- include/uapi/linux/io_uring.h | 1 + 2 files changed, 60 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index c43340396f6d..026350b9c33f 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -853,6 +853,11 @@ static const struct io_op_def io_op_defs[] = { }, [IORING_OP_PROVIDE_BUFFERS] = {}, [IORING_OP_REMOVE_BUFFERS] = {}, + [IORING_OP_TEE] = { + .needs_file = 1, + .hash_reg_file = 1, + .unbound_nonreg_file = 1, + }, }; static void io_wq_submit_work(struct io_wq_work **workptr); @@ -2748,7 +2753,8 @@ out_free: return ret; } -static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int __io_splice_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) { struct io_splice* sp = &req->splice; unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL; @@ -2758,8 +2764,6 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; sp->file_in = NULL; - sp->off_in = READ_ONCE(sqe->splice_off_in); - sp->off_out = READ_ONCE(sqe->off); sp->len = READ_ONCE(sqe->len); sp->flags = READ_ONCE(sqe->splice_flags); @@ -2778,6 +2782,46 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } +static int io_tee_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + if (READ_ONCE(sqe->splice_off_in) || READ_ONCE(sqe->off)) + return -EINVAL; + return __io_splice_prep(req, sqe); +} + +static int io_tee(struct io_kiocb *req, bool force_nonblock) +{ + struct io_splice *sp = &req->splice; + struct file *in = sp->file_in; + struct file *out = sp->file_out; + unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; + long ret = 0; + + if (force_nonblock) + return -EAGAIN; + if (sp->len) + ret = do_tee(in, out, sp->len, flags); + + io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED)); + req->flags &= ~REQ_F_NEED_CLEANUP; + + io_cqring_add_event(req, ret); + if (ret != sp->len) + req_set_fail_links(req); + io_put_req(req); + return 0; +} + +static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_splice* sp = &req->splice; + + sp->off_in = READ_ONCE(sqe->splice_off_in); + sp->off_out = READ_ONCE(sqe->off); + return __io_splice_prep(req, sqe); +} + static int io_splice(struct io_kiocb *req, bool force_nonblock) { struct io_splice *sp = &req->splice; @@ -5085,6 +5129,9 @@ static int io_req_defer_prep(struct io_kiocb *req, case IORING_OP_REMOVE_BUFFERS: ret = io_remove_buffers_prep(req, sqe); break; + case IORING_OP_TEE: + ret = io_tee_prep(req, sqe); + break; default: printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n", req->opcode); @@ -5158,6 +5205,7 @@ static void io_cleanup_req(struct io_kiocb *req) putname(req->open.filename); break; case IORING_OP_SPLICE: + case IORING_OP_TEE: io_put_file(req, req->splice.file_in, (req->splice.flags & SPLICE_F_FD_IN_FIXED)); break; @@ -5388,6 +5436,14 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, } ret = io_remove_buffers(req, force_nonblock); break; + case IORING_OP_TEE: + if (sqe) { + ret = io_tee_prep(req, sqe); + if (ret < 0) + break; + } + ret = io_tee(req, force_nonblock); + break; default: ret = -EINVAL; break; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 8c5775df08b8..92c22699a5a7 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -129,6 +129,7 @@ enum { IORING_OP_SPLICE, IORING_OP_PROVIDE_BUFFERS, IORING_OP_REMOVE_BUFFERS, + IORING_OP_TEE, /* this goes last, obviously */ IORING_OP_LAST, -- cgit v1.2.3 From 926645d43fd43622a2b056471a2cf41cc19cbf4c Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Sat, 9 May 2020 11:04:48 +0200 Subject: media: v4l2-ctrls: Add camera orientation and rotation Add support for the newly defined V4L2_CID_CAMERA_ORIENTATION and V4L2_CID_CAMERA_SENSOR_ROTATION read-only controls used to report the camera device mounting position and orientation respectively. Reviewed-by: Laurent Pinchart Signed-off-by: Jacopo Mondi Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-ctrls.c | 13 +++++++++++++ include/uapi/linux/v4l2-controls.h | 7 +++++++ 2 files changed, 20 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 1c617b42a944..92c3e39efc28 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -583,6 +583,12 @@ const char * const *v4l2_ctrl_get_menu(u32 id) "Annex B Start Code", NULL, }; + static const char * const camera_orientation[] = { + "Front", + "Back", + "External", + NULL, + }; switch (id) { case V4L2_CID_MPEG_AUDIO_SAMPLING_FREQ: @@ -708,6 +714,8 @@ const char * const *v4l2_ctrl_get_menu(u32 id) return hevc_decode_mode; case V4L2_CID_MPEG_VIDEO_HEVC_START_CODE: return hevc_start_code; + case V4L2_CID_CAMERA_ORIENTATION: + return camera_orientation; default: return NULL; } @@ -1020,6 +1028,8 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_PAN_SPEED: return "Pan, Speed"; case V4L2_CID_TILT_SPEED: return "Tilt, Speed"; case V4L2_CID_UNIT_CELL_SIZE: return "Unit Cell Size"; + case V4L2_CID_CAMERA_ORIENTATION: return "Camera Orientation"; + case V4L2_CID_CAMERA_SENSOR_ROTATION: return "Camera Sensor Rotation"; /* FM Radio Modulator controls */ /* Keep the order of the 'case's the same as in v4l2-controls.h! */ @@ -1293,6 +1303,7 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, case V4L2_CID_MPEG_VIDEO_HEVC_LOOP_FILTER_MODE: case V4L2_CID_MPEG_VIDEO_HEVC_DECODE_MODE: case V4L2_CID_MPEG_VIDEO_HEVC_START_CODE: + case V4L2_CID_CAMERA_ORIENTATION: *type = V4L2_CTRL_TYPE_MENU; break; case V4L2_CID_LINK_FREQ: @@ -1482,6 +1493,8 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, case V4L2_CID_RDS_RX_TRAFFIC_ANNOUNCEMENT: case V4L2_CID_RDS_RX_TRAFFIC_PROGRAM: case V4L2_CID_RDS_RX_MUSIC_SPEECH: + case V4L2_CID_CAMERA_ORIENTATION: + case V4L2_CID_CAMERA_SENSOR_ROTATION: *flags |= V4L2_CTRL_FLAG_READ_ONLY; break; case V4L2_CID_RF_TUNER_PLL_LOCK: diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 0ba1005c9651..62271418c1be 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -923,6 +923,13 @@ enum v4l2_auto_focus_range { #define V4L2_CID_PAN_SPEED (V4L2_CID_CAMERA_CLASS_BASE+32) #define V4L2_CID_TILT_SPEED (V4L2_CID_CAMERA_CLASS_BASE+33) +#define V4L2_CID_CAMERA_ORIENTATION (V4L2_CID_CAMERA_CLASS_BASE+34) +#define V4L2_CAMERA_ORIENTATION_FRONT 0 +#define V4L2_CAMERA_ORIENTATION_BACK 1 +#define V4L2_CAMERA_ORIENTATION_EXTERNAL 2 + +#define V4L2_CID_CAMERA_SENSOR_ROTATION (V4L2_CID_CAMERA_CLASS_BASE+35) + /* FM Modulator class control IDs */ #define V4L2_CID_FM_TX_CLASS_BASE (V4L2_CTRL_CLASS_FM_TX | 0x900) -- cgit v1.2.3 From b0d1f8741b812352fe0e5f3b2381427085f23e19 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Sat, 16 May 2020 14:20:46 +0800 Subject: iommu/vt-d: Add nested translation helper function Nested translation mode is supported in VT-d 3.0 Spec.CH 3.8. With PASID granular translation type set to 0x11b, translation result from the first level(FL) also subject to a second level(SL) page table translation. This mode is used for SVA virtualization, where FL performs guest virtual to guest physical translation and SL performs guest physical to host physical translation. This patch adds a helper function for setting up nested translation where second level comes from a domain and first level comes from a guest PGD. Signed-off-by: Jacob Pan Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20200516062101.29541-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 25 ------- drivers/iommu/intel-pasid.c | 174 +++++++++++++++++++++++++++++++++++++++++++- drivers/iommu/intel-pasid.h | 10 +++ include/linux/intel-iommu.h | 20 +++++ include/uapi/linux/iommu.h | 5 ++ 5 files changed, 206 insertions(+), 28 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 8027f21073eb..7e85c09eec71 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -296,31 +296,6 @@ static inline void context_clear_entry(struct context_entry *context) static struct dmar_domain *si_domain; static int hw_pass_through = 1; -/* si_domain contains mulitple devices */ -#define DOMAIN_FLAG_STATIC_IDENTITY BIT(0) - -/* - * This is a DMA domain allocated through the iommu domain allocation - * interface. But one or more devices belonging to this domain have - * been chosen to use a private domain. We should avoid to use the - * map/unmap/iova_to_phys APIs on it. - */ -#define DOMAIN_FLAG_LOSE_CHILDREN BIT(1) - -/* - * When VT-d works in the scalable mode, it allows DMA translation to - * happen through either first level or second level page table. This - * bit marks that the DMA translation for the domain goes through the - * first level page table, otherwise, it goes through the second level. - */ -#define DOMAIN_FLAG_USE_FIRST_LEVEL BIT(2) - -/* - * Domain represents a virtual machine which demands iommu nested - * translation mode support. - */ -#define DOMAIN_FLAG_NESTING_MODE BIT(3) - #define for_each_domain_iommu(idx, domain) \ for (idx = 0; idx < g_num_of_iommus; idx++) \ if (domain->iommu_refcnt[idx]) diff --git a/drivers/iommu/intel-pasid.c b/drivers/iommu/intel-pasid.c index d9cea3011b58..c7fa1b79eaf7 100644 --- a/drivers/iommu/intel-pasid.c +++ b/drivers/iommu/intel-pasid.c @@ -359,6 +359,16 @@ pasid_set_flpm(struct pasid_entry *pe, u64 value) pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2); } +/* + * Setup the Extended Access Flag Enable (EAFE) field (Bit 135) + * of a scalable mode PASID entry. + */ +static inline void +pasid_set_eafe(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7); +} + static void pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu, u16 did, int pasid) @@ -492,7 +502,7 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu, pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); /* Setup Present and PASID Granular Transfer Type: */ - pasid_set_translation_type(pte, 1); + pasid_set_translation_type(pte, PASID_ENTRY_PGTT_FL_ONLY); pasid_set_present(pte); pasid_flush_caches(iommu, pte, pasid, did); @@ -561,7 +571,7 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, pasid_set_domain_id(pte, did); pasid_set_slptr(pte, pgd_val); pasid_set_address_width(pte, agaw); - pasid_set_translation_type(pte, 2); + pasid_set_translation_type(pte, PASID_ENTRY_PGTT_SL_ONLY); pasid_set_fault_enable(pte); pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); @@ -595,7 +605,7 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu, pasid_clear_entry(pte); pasid_set_domain_id(pte, did); pasid_set_address_width(pte, iommu->agaw); - pasid_set_translation_type(pte, 4); + pasid_set_translation_type(pte, PASID_ENTRY_PGTT_PT); pasid_set_fault_enable(pte); pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); @@ -609,3 +619,161 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu, return 0; } + +static int +intel_pasid_setup_bind_data(struct intel_iommu *iommu, struct pasid_entry *pte, + struct iommu_gpasid_bind_data_vtd *pasid_data) +{ + /* + * Not all guest PASID table entry fields are passed down during bind, + * here we only set up the ones that are dependent on guest settings. + * Execution related bits such as NXE, SMEP are not supported. + * Other fields, such as snoop related, are set based on host needs + * regardless of guest settings. + */ + if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_SRE) { + if (!ecap_srs(iommu->ecap)) { + pr_err_ratelimited("No supervisor request support on %s\n", + iommu->name); + return -EINVAL; + } + pasid_set_sre(pte); + } + + if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_EAFE) { + if (!ecap_eafs(iommu->ecap)) { + pr_err_ratelimited("No extended access flag support on %s\n", + iommu->name); + return -EINVAL; + } + pasid_set_eafe(pte); + } + + /* + * Memory type is only applicable to devices inside processor coherent + * domain. Will add MTS support once coherent devices are available. + */ + if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_MTS_MASK) { + pr_warn_ratelimited("No memory type support %s\n", + iommu->name); + return -EINVAL; + } + + return 0; +} + +/** + * intel_pasid_setup_nested() - Set up PASID entry for nested translation. + * This could be used for guest shared virtual address. In this case, the + * first level page tables are used for GVA-GPA translation in the guest, + * second level page tables are used for GPA-HPA translation. + * + * @iommu: IOMMU which the device belong to + * @dev: Device to be set up for translation + * @gpgd: FLPTPTR: First Level Page translation pointer in GPA + * @pasid: PASID to be programmed in the device PASID table + * @pasid_data: Additional PASID info from the guest bind request + * @domain: Domain info for setting up second level page tables + * @addr_width: Address width of the first level (guest) + */ +int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev, + pgd_t *gpgd, int pasid, + struct iommu_gpasid_bind_data_vtd *pasid_data, + struct dmar_domain *domain, int addr_width) +{ + struct pasid_entry *pte; + struct dma_pte *pgd; + int ret = 0; + u64 pgd_val; + int agaw; + u16 did; + + if (!ecap_nest(iommu->ecap)) { + pr_err_ratelimited("IOMMU: %s: No nested translation support\n", + iommu->name); + return -EINVAL; + } + + if (!(domain->flags & DOMAIN_FLAG_NESTING_MODE)) { + pr_err_ratelimited("Domain is not in nesting mode, %x\n", + domain->flags); + return -EINVAL; + } + + pte = intel_pasid_get_entry(dev, pasid); + if (WARN_ON(!pte)) + return -EINVAL; + + /* + * Caller must ensure PASID entry is not in use, i.e. not bind the + * same PASID to the same device twice. + */ + if (pasid_pte_is_present(pte)) + return -EBUSY; + + pasid_clear_entry(pte); + + /* Sanity checking performed by caller to make sure address + * width matching in two dimensions: + * 1. CPU vs. IOMMU + * 2. Guest vs. Host. + */ + switch (addr_width) { +#ifdef CONFIG_X86 + case ADDR_WIDTH_5LEVEL: + if (!cpu_feature_enabled(X86_FEATURE_LA57) || + !cap_5lp_support(iommu->cap)) { + dev_err_ratelimited(dev, + "5-level paging not supported\n"); + return -EINVAL; + } + + pasid_set_flpm(pte, 1); + break; +#endif + case ADDR_WIDTH_4LEVEL: + pasid_set_flpm(pte, 0); + break; + default: + dev_err_ratelimited(dev, "Invalid guest address width %d\n", + addr_width); + return -EINVAL; + } + + /* First level PGD is in GPA, must be supported by the second level */ + if ((unsigned long long)gpgd > domain->max_addr) { + dev_err_ratelimited(dev, + "Guest PGD %llx not supported, max %llx\n", + (unsigned long long)gpgd, domain->max_addr); + return -EINVAL; + } + pasid_set_flptr(pte, (u64)gpgd); + + ret = intel_pasid_setup_bind_data(iommu, pte, pasid_data); + if (ret) + return ret; + + /* Setup the second level based on the given domain */ + pgd = domain->pgd; + + agaw = iommu_skip_agaw(domain, iommu, &pgd); + if (agaw < 0) { + dev_err_ratelimited(dev, "Invalid domain page table\n"); + return -EINVAL; + } + pgd_val = virt_to_phys(pgd); + pasid_set_slptr(pte, pgd_val); + pasid_set_fault_enable(pte); + + did = domain->iommu_did[iommu->seq_id]; + pasid_set_domain_id(pte, did); + + pasid_set_address_width(pte, agaw); + pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); + + pasid_set_translation_type(pte, PASID_ENTRY_PGTT_NESTED); + pasid_set_present(pte); + pasid_flush_caches(iommu, pte, pasid, did); + + return ret; +} diff --git a/drivers/iommu/intel-pasid.h b/drivers/iommu/intel-pasid.h index 92de6df24ccb..ccd50c2ae75c 100644 --- a/drivers/iommu/intel-pasid.h +++ b/drivers/iommu/intel-pasid.h @@ -36,6 +36,7 @@ * to vmalloc or even module mappings. */ #define PASID_FLAG_SUPERVISOR_MODE BIT(0) +#define PASID_FLAG_NESTED BIT(1) /* * The PASID_FLAG_FL5LP flag Indicates using 5-level paging for first- @@ -51,6 +52,11 @@ struct pasid_entry { u64 val[8]; }; +#define PASID_ENTRY_PGTT_FL_ONLY (1) +#define PASID_ENTRY_PGTT_SL_ONLY (2) +#define PASID_ENTRY_PGTT_NESTED (3) +#define PASID_ENTRY_PGTT_PT (4) + /* The representative of a PASID table */ struct pasid_table { void *table; /* pasid table pointer */ @@ -99,6 +105,10 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, int intel_pasid_setup_pass_through(struct intel_iommu *iommu, struct dmar_domain *domain, struct device *dev, int pasid); +int intel_pasid_setup_nested(struct intel_iommu *iommu, + struct device *dev, pgd_t *pgd, int pasid, + struct iommu_gpasid_bind_data_vtd *pasid_data, + struct dmar_domain *domain, int addr_width); void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev, int pasid); diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index ed7171d2ae1f..e0d1fed7cbe4 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -42,6 +42,9 @@ #define DMA_FL_PTE_PRESENT BIT_ULL(0) #define DMA_FL_PTE_XD BIT_ULL(63) +#define ADDR_WIDTH_5LEVEL (57) +#define ADDR_WIDTH_4LEVEL (48) + #define CONTEXT_TT_MULTI_LEVEL 0 #define CONTEXT_TT_DEV_IOTLB 1 #define CONTEXT_TT_PASS_THROUGH 2 @@ -480,6 +483,23 @@ struct context_entry { u64 hi; }; +/* si_domain contains mulitple devices */ +#define DOMAIN_FLAG_STATIC_IDENTITY BIT(0) + +/* + * When VT-d works in the scalable mode, it allows DMA translation to + * happen through either first level or second level page table. This + * bit marks that the DMA translation for the domain goes through the + * first level page table, otherwise, it goes through the second level. + */ +#define DOMAIN_FLAG_USE_FIRST_LEVEL BIT(1) + +/* + * Domain represents a virtual machine which demands iommu nested + * translation mode support. + */ +#define DOMAIN_FLAG_NESTING_MODE BIT(2) + struct dmar_domain { int nid; /* node id */ diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index 4ad3496e5c43..e907b7091a46 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -285,6 +285,11 @@ struct iommu_gpasid_bind_data_vtd { __u32 emt; }; +#define IOMMU_SVA_VTD_GPASID_MTS_MASK (IOMMU_SVA_VTD_GPASID_CD | \ + IOMMU_SVA_VTD_GPASID_EMTE | \ + IOMMU_SVA_VTD_GPASID_PCD | \ + IOMMU_SVA_VTD_GPASID_PWT) + /** * struct iommu_gpasid_bind_data - Information about device and guest PASID binding * @version: Version of this data structure -- cgit v1.2.3 From 0858caa419e6cf9d31e734d09d70b34f64443ef6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 12 Feb 2020 13:58:35 +0000 Subject: uapi: General notification queue definitions Add UAPI definitions for the general notification queue, including the following pieces: (*) struct watch_notification. This is the metadata header for notification messages. It includes a type and subtype that indicate the source of the message (eg. WATCH_TYPE_MOUNT_NOTIFY) and the kind of the message (eg. NOTIFY_MOUNT_NEW_MOUNT). The header also contains an information field that conveys the following information: - WATCH_INFO_LENGTH. The size of the entry (entries are variable length). - WATCH_INFO_ID. The watch ID specified when the watchpoint was set. - WATCH_INFO_TYPE_INFO. (Sub)type-specific information. - WATCH_INFO_FLAG_*. Flag bits overlain on the type-specific information. For use by the type. All the information in the header can be used in filtering messages at the point of writing into the buffer. (*) struct watch_notification_removal This is an extended watch-removal notification record that includes an 'id' field that can indicate the identifier of the object being removed if available (for instance, a keyring serial number). Signed-off-by: David Howells --- include/uapi/linux/watch_queue.h | 55 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) create mode 100644 include/uapi/linux/watch_queue.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/watch_queue.h b/include/uapi/linux/watch_queue.h new file mode 100644 index 000000000000..5f3d21e8a34b --- /dev/null +++ b/include/uapi/linux/watch_queue.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_WATCH_QUEUE_H +#define _UAPI_LINUX_WATCH_QUEUE_H + +#include + +enum watch_notification_type { + WATCH_TYPE_META = 0, /* Special record */ + WATCH_TYPE__NR = 1 +}; + +enum watch_meta_notification_subtype { + WATCH_META_REMOVAL_NOTIFICATION = 0, /* Watched object was removed */ + WATCH_META_LOSS_NOTIFICATION = 1, /* Data loss occurred */ +}; + +/* + * Notification record header. This is aligned to 64-bits so that subclasses + * can contain __u64 fields. + */ +struct watch_notification { + __u32 type:24; /* enum watch_notification_type */ + __u32 subtype:8; /* Type-specific subtype (filterable) */ + __u32 info; +#define WATCH_INFO_LENGTH 0x0000007f /* Length of record */ +#define WATCH_INFO_LENGTH__SHIFT 0 +#define WATCH_INFO_ID 0x0000ff00 /* ID of watchpoint */ +#define WATCH_INFO_ID__SHIFT 8 +#define WATCH_INFO_TYPE_INFO 0xffff0000 /* Type-specific info */ +#define WATCH_INFO_TYPE_INFO__SHIFT 16 +#define WATCH_INFO_FLAG_0 0x00010000 /* Type-specific info, flag bit 0 */ +#define WATCH_INFO_FLAG_1 0x00020000 /* ... */ +#define WATCH_INFO_FLAG_2 0x00040000 +#define WATCH_INFO_FLAG_3 0x00080000 +#define WATCH_INFO_FLAG_4 0x00100000 +#define WATCH_INFO_FLAG_5 0x00200000 +#define WATCH_INFO_FLAG_6 0x00400000 +#define WATCH_INFO_FLAG_7 0x00800000 +}; + + +/* + * Extended watch removal notification. This is used optionally if the type + * wants to indicate an identifier for the object being watched, if there is + * such. This can be distinguished by the length. + * + * type -> WATCH_TYPE_META + * subtype -> WATCH_META_REMOVAL_NOTIFICATION + */ +struct watch_notification_removal { + struct watch_notification watch; + __u64 id; /* Type-dependent identifier */ +}; + +#endif /* _UAPI_LINUX_WATCH_QUEUE_H */ -- cgit v1.2.3 From b580b93664f91db8cb503429030df0f1c1e53528 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 12 Feb 2020 13:58:35 +0000 Subject: pipe: Add O_NOTIFICATION_PIPE Add an O_NOTIFICATION_PIPE flag that can be passed to pipe2() to indicate that the pipe being created is going to be used for notifications. This suppresses the use of splice(), vmsplice(), tee() and sendfile() on the pipe as calling iov_iter_revert() on a pipe when a kernel notification message has been inserted into the middle of a multi-buffer splice will be messy. The flag is given the same value as O_EXCL as it seems unlikely that this flag will ever be applicable to pipes and I don't want to use up another O_* bit unnecessarily. An alternative could be to add a pipe3() system call. Signed-off-by: David Howells --- include/uapi/linux/watch_queue.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/watch_queue.h b/include/uapi/linux/watch_queue.h index 5f3d21e8a34b..9df72227f515 100644 --- a/include/uapi/linux/watch_queue.h +++ b/include/uapi/linux/watch_queue.h @@ -3,6 +3,9 @@ #define _UAPI_LINUX_WATCH_QUEUE_H #include +#include + +#define O_NOTIFICATION_PIPE O_EXCL /* Parameter to pipe2() selecting notification pipe */ enum watch_notification_type { WATCH_TYPE_META = 0, /* Special record */ -- cgit v1.2.3 From c73be61cede5882f9605a852414db559c0ebedfd Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Jan 2020 17:07:11 +0000 Subject: pipe: Add general notification queue support Make it possible to have a general notification queue built on top of a standard pipe. Notifications are 'spliced' into the pipe and then read out. splice(), vmsplice() and sendfile() are forbidden on pipes used for notifications as post_one_notification() cannot take pipe->mutex. This means that notifications could be posted in between individual pipe buffers, making iov_iter_revert() difficult to effect. The way the notification queue is used is: (1) An application opens a pipe with a special flag and indicates the number of messages it wishes to be able to queue at once (this can only be set once): pipe2(fds, O_NOTIFICATION_PIPE); ioctl(fds[0], IOC_WATCH_QUEUE_SET_SIZE, queue_depth); (2) The application then uses poll() and read() as normal to extract data from the pipe. read() will return multiple notifications if the buffer is big enough, but it will not split a notification across buffers - rather it will return a short read or EMSGSIZE. Notification messages include a length in the header so that the caller can split them up. Each message has a header that describes it: struct watch_notification { __u32 type:24; __u32 subtype:8; __u32 info; }; The type indicates the source (eg. mount tree changes, superblock events, keyring changes, block layer events) and the subtype indicates the event type (eg. mount, unmount; EIO, EDQUOT; link, unlink). The info field indicates a number of things, including the entry length, an ID assigned to a watchpoint contributing to this buffer and type-specific flags. Supplementary data, such as the key ID that generated an event, can be attached in additional slots. The maximum message size is 127 bytes. Messages may not be padded or aligned, so there is no guarantee, for example, that the notification type will be on a 4-byte bounary. Signed-off-by: David Howells --- Documentation/userspace-api/ioctl/ioctl-number.rst | 1 + Documentation/watch_queue.rst | 339 +++++++++++ fs/pipe.c | 206 ++++--- fs/splice.c | 12 +- include/linux/pipe_fs_i.h | 19 +- include/linux/watch_queue.h | 127 ++++ include/uapi/linux/watch_queue.h | 20 + init/Kconfig | 12 + kernel/Makefile | 1 + kernel/watch_queue.c | 657 +++++++++++++++++++++ 10 files changed, 1318 insertions(+), 76 deletions(-) create mode 100644 Documentation/watch_queue.rst create mode 100644 include/linux/watch_queue.h create mode 100644 kernel/watch_queue.c (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index f759edafd938..9425377615ce 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -201,6 +201,7 @@ Code Seq# Include File Comments 'W' 00-1F linux/wanrouter.h conflict! (pre 3.9) 'W' 00-3F sound/asound.h conflict! 'W' 40-5F drivers/pci/switch/switchtec.c +'W' 60-61 linux/watch_queue.h 'X' all fs/xfs/xfs_fs.h, conflict! fs/xfs/linux-2.6/xfs_ioctl32.h, include/linux/falloc.h, diff --git a/Documentation/watch_queue.rst b/Documentation/watch_queue.rst new file mode 100644 index 000000000000..849fad6893ef --- /dev/null +++ b/Documentation/watch_queue.rst @@ -0,0 +1,339 @@ +============================== +General notification mechanism +============================== + +The general notification mechanism is built on top of the standard pipe driver +whereby it effectively splices notification messages from the kernel into pipes +opened by userspace. This can be used in conjunction with:: + + * Key/keyring notifications + + +The notifications buffers can be enabled by: + + "General setup"/"General notification queue" + (CONFIG_WATCH_QUEUE) + +This document has the following sections: + +.. contents:: :local: + + +Overview +======== + +This facility appears as a pipe that is opened in a special mode. The pipe's +internal ring buffer is used to hold messages that are generated by the kernel. +These messages are then read out by read(). Splice and similar are disabled on +such pipes due to them wanting to, under some circumstances, revert their +additions to the ring - which might end up interleaved with notification +messages. + +The owner of the pipe has to tell the kernel which sources it would like to +watch through that pipe. Only sources that have been connected to a pipe will +insert messages into it. Note that a source may be bound to multiple pipes and +insert messages into all of them simultaneously. + +Filters may also be emplaced on a pipe so that certain source types and +subevents can be ignored if they're not of interest. + +A message will be discarded if there isn't a slot available in the ring or if +no preallocated message buffer is available. In both of these cases, read() +will insert a WATCH_META_LOSS_NOTIFICATION message into the output buffer after +the last message currently in the buffer has been read. + +Note that when producing a notification, the kernel does not wait for the +consumers to collect it, but rather just continues on. This means that +notifications can be generated whilst spinlocks are held and also protects the +kernel from being held up indefinitely by a userspace malfunction. + + +Message Structure +================= + +Notification messages begin with a short header:: + + struct watch_notification { + __u32 type:24; + __u32 subtype:8; + __u32 info; + }; + +"type" indicates the source of the notification record and "subtype" indicates +the type of record from that source (see the Watch Sources section below). The +type may also be "WATCH_TYPE_META". This is a special record type generated +internally by the watch queue itself. There are two subtypes: + + * WATCH_META_REMOVAL_NOTIFICATION + * WATCH_META_LOSS_NOTIFICATION + +The first indicates that an object on which a watch was installed was removed +or destroyed and the second indicates that some messages have been lost. + +"info" indicates a bunch of things, including: + + * The length of the message in bytes, including the header (mask with + WATCH_INFO_LENGTH and shift by WATCH_INFO_LENGTH__SHIFT). This indicates + the size of the record, which may be between 8 and 127 bytes. + + * The watch ID (mask with WATCH_INFO_ID and shift by WATCH_INFO_ID__SHIFT). + This indicates that caller's ID of the watch, which may be between 0 + and 255. Multiple watches may share a queue, and this provides a means to + distinguish them. + + * A type-specific field (WATCH_INFO_TYPE_INFO). This is set by the + notification producer to indicate some meaning specific to the type and + subtype. + +Everything in info apart from the length can be used for filtering. + +The header can be followed by supplementary information. The format of this is +at the discretion is defined by the type and subtype. + + +Watch List (Notification Source) API +==================================== + +A "watch list" is a list of watchers that are subscribed to a source of +notifications. A list may be attached to an object (say a key or a superblock) +or may be global (say for device events). From a userspace perspective, a +non-global watch list is typically referred to by reference to the object it +belongs to (such as using KEYCTL_NOTIFY and giving it a key serial number to +watch that specific key). + +To manage a watch list, the following functions are provided: + + * ``void init_watch_list(struct watch_list *wlist, + void (*release_watch)(struct watch *wlist));`` + + Initialise a watch list. If ``release_watch`` is not NULL, then this + indicates a function that should be called when the watch_list object is + destroyed to discard any references the watch list holds on the watched + object. + + * ``void remove_watch_list(struct watch_list *wlist);`` + + This removes all of the watches subscribed to a watch_list and frees them + and then destroys the watch_list object itself. + + +Watch Queue (Notification Output) API +===================================== + +A "watch queue" is the buffer allocated by an application that notification +records will be written into. The workings of this are hidden entirely inside +of the pipe device driver, but it is necessary to gain a reference to it to set +a watch. These can be managed with: + + * ``struct watch_queue *get_watch_queue(int fd);`` + + Since watch queues are indicated to the kernel by the fd of the pipe that + implements the buffer, userspace must hand that fd through a system call. + This can be used to look up an opaque pointer to the watch queue from the + system call. + + * ``void put_watch_queue(struct watch_queue *wqueue);`` + + This discards the reference obtained from ``get_watch_queue()``. + + +Watch Subscription API +====================== + +A "watch" is a subscription on a watch list, indicating the watch queue, and +thus the buffer, into which notification records should be written. The watch +queue object may also carry filtering rules for that object, as set by +userspace. Some parts of the watch struct can be set by the driver:: + + struct watch { + union { + u32 info_id; /* ID to be OR'd in to info field */ + ... + }; + void *private; /* Private data for the watched object */ + u64 id; /* Internal identifier */ + ... + }; + +The ``info_id`` value should be an 8-bit number obtained from userspace and +shifted by WATCH_INFO_ID__SHIFT. This is OR'd into the WATCH_INFO_ID field of +struct watch_notification::info when and if the notification is written into +the associated watch queue buffer. + +The ``private`` field is the driver's data associated with the watch_list and +is cleaned up by the ``watch_list::release_watch()`` method. + +The ``id`` field is the source's ID. Notifications that are posted with a +different ID are ignored. + +The following functions are provided to manage watches: + + * ``void init_watch(struct watch *watch, struct watch_queue *wqueue);`` + + Initialise a watch object, setting its pointer to the watch queue, using + appropriate barriering to avoid lockdep complaints. + + * ``int add_watch_to_object(struct watch *watch, struct watch_list *wlist);`` + + Subscribe a watch to a watch list (notification source). The + driver-settable fields in the watch struct must have been set before this + is called. + + * ``int remove_watch_from_object(struct watch_list *wlist, + struct watch_queue *wqueue, + u64 id, false);`` + + Remove a watch from a watch list, where the watch must match the specified + watch queue (``wqueue``) and object identifier (``id``). A notification + (``WATCH_META_REMOVAL_NOTIFICATION``) is sent to the watch queue to + indicate that the watch got removed. + + * ``int remove_watch_from_object(struct watch_list *wlist, NULL, 0, true);`` + + Remove all the watches from a watch list. It is expected that this will be + called preparatory to destruction and that the watch list will be + inaccessible to new watches by this point. A notification + (``WATCH_META_REMOVAL_NOTIFICATION``) is sent to the watch queue of each + subscribed watch to indicate that the watch got removed. + + +Notification Posting API +======================== + +To post a notification to watch list so that the subscribed watches can see it, +the following function should be used:: + + void post_watch_notification(struct watch_list *wlist, + struct watch_notification *n, + const struct cred *cred, + u64 id); + +The notification should be preformatted and a pointer to the header (``n``) +should be passed in. The notification may be larger than this and the size in +units of buffer slots is noted in ``n->info & WATCH_INFO_LENGTH``. + +The ``cred`` struct indicates the credentials of the source (subject) and is +passed to the LSMs, such as SELinux, to allow or suppress the recording of the +note in each individual queue according to the credentials of that queue +(object). + +The ``id`` is the ID of the source object (such as the serial number on a key). +Only watches that have the same ID set in them will see this notification. + + +Watch Sources +============= + +Any particular buffer can be fed from multiple sources. Sources include: + + * WATCH_TYPE_KEY_NOTIFY + + Notifications of this type indicate changes to keys and keyrings, including + the changes of keyring contents or the attributes of keys. + + See Documentation/security/keys/core.rst for more information. + + +Event Filtering +=============== + +Once a watch queue has been created, a set of filters can be applied to limit +the events that are received using:: + + struct watch_notification_filter filter = { + ... + }; + ioctl(fd, IOC_WATCH_QUEUE_SET_FILTER, &filter) + +The filter description is a variable of type:: + + struct watch_notification_filter { + __u32 nr_filters; + __u32 __reserved; + struct watch_notification_type_filter filters[]; + }; + +Where "nr_filters" is the number of filters in filters[] and "__reserved" +should be 0. The "filters" array has elements of the following type:: + + struct watch_notification_type_filter { + __u32 type; + __u32 info_filter; + __u32 info_mask; + __u32 subtype_filter[8]; + }; + +Where: + + * ``type`` is the event type to filter for and should be something like + "WATCH_TYPE_KEY_NOTIFY" + + * ``info_filter`` and ``info_mask`` act as a filter on the info field of the + notification record. The notification is only written into the buffer if:: + + (watch.info & info_mask) == info_filter + + This could be used, for example, to ignore events that are not exactly on + the watched point in a mount tree. + + * ``subtype_filter`` is a bitmask indicating the subtypes that are of + interest. Bit 0 of subtype_filter[0] corresponds to subtype 0, bit 1 to + subtype 1, and so on. + +If the argument to the ioctl() is NULL, then the filters will be removed and +all events from the watched sources will come through. + + +Userspace Code Example +====================== + +A buffer is created with something like the following:: + + pipe2(fds, O_TMPFILE); + ioctl(fds[1], IOC_WATCH_QUEUE_SET_SIZE, 256); + +It can then be set to receive keyring change notifications:: + + keyctl(KEYCTL_WATCH_KEY, KEY_SPEC_SESSION_KEYRING, fds[1], 0x01); + +The notifications can then be consumed by something like the following:: + + static void consumer(int rfd, struct watch_queue_buffer *buf) + { + unsigned char buffer[128]; + ssize_t buf_len; + + while (buf_len = read(rfd, buffer, sizeof(buffer)), + buf_len > 0 + ) { + void *p = buffer; + void *end = buffer + buf_len; + while (p < end) { + union { + struct watch_notification n; + unsigned char buf1[128]; + } n; + size_t largest, len; + + largest = end - p; + if (largest > 128) + largest = 128; + memcpy(&n, p, largest); + + len = (n->info & WATCH_INFO_LENGTH) >> + WATCH_INFO_LENGTH__SHIFT; + if (len == 0 || len > largest) + return; + + switch (n.n.type) { + case WATCH_TYPE_META: + got_meta(&n.n); + case WATCH_TYPE_KEY_NOTIFY: + saw_key_change(&n.n); + break; + } + + p += len; + } + } + } diff --git a/fs/pipe.c b/fs/pipe.c index 16fb72e9abf7..da9bc1f21fd1 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -459,6 +460,13 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) goto out; } +#ifdef CONFIG_WATCH_QUEUE + if (pipe->watch_queue) { + ret = -EXDEV; + goto out; + } +#endif + /* * Only wake up if the pipe started out empty, since * otherwise there should be no readers waiting. @@ -628,22 +636,37 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) int count, head, tail, mask; switch (cmd) { - case FIONREAD: - __pipe_lock(pipe); - count = 0; - head = pipe->head; - tail = pipe->tail; - mask = pipe->ring_size - 1; + case FIONREAD: + __pipe_lock(pipe); + count = 0; + head = pipe->head; + tail = pipe->tail; + mask = pipe->ring_size - 1; - while (tail != head) { - count += pipe->bufs[tail & mask].len; - tail++; - } - __pipe_unlock(pipe); + while (tail != head) { + count += pipe->bufs[tail & mask].len; + tail++; + } + __pipe_unlock(pipe); - return put_user(count, (int __user *)arg); - default: - return -ENOIOCTLCMD; + return put_user(count, (int __user *)arg); + +#ifdef CONFIG_WATCH_QUEUE + case IOC_WATCH_QUEUE_SET_SIZE: { + int ret; + __pipe_lock(pipe); + ret = watch_queue_set_size(pipe, arg); + __pipe_unlock(pipe); + return ret; + } + + case IOC_WATCH_QUEUE_SET_FILTER: + return watch_queue_set_filter( + pipe, (struct watch_notification_filter __user *)arg); +#endif + + default: + return -ENOIOCTLCMD; } } @@ -754,27 +777,27 @@ pipe_fasync(int fd, struct file *filp, int on) return retval; } -static unsigned long account_pipe_buffers(struct user_struct *user, - unsigned long old, unsigned long new) +unsigned long account_pipe_buffers(struct user_struct *user, + unsigned long old, unsigned long new) { return atomic_long_add_return(new - old, &user->pipe_bufs); } -static bool too_many_pipe_buffers_soft(unsigned long user_bufs) +bool too_many_pipe_buffers_soft(unsigned long user_bufs) { unsigned long soft_limit = READ_ONCE(pipe_user_pages_soft); return soft_limit && user_bufs > soft_limit; } -static bool too_many_pipe_buffers_hard(unsigned long user_bufs) +bool too_many_pipe_buffers_hard(unsigned long user_bufs) { unsigned long hard_limit = READ_ONCE(pipe_user_pages_hard); return hard_limit && user_bufs > hard_limit; } -static bool is_unprivileged_user(void) +bool pipe_is_unprivileged_user(void) { return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); } @@ -796,12 +819,12 @@ struct pipe_inode_info *alloc_pipe_info(void) user_bufs = account_pipe_buffers(user, 0, pipe_bufs); - if (too_many_pipe_buffers_soft(user_bufs) && is_unprivileged_user()) { + if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) { user_bufs = account_pipe_buffers(user, pipe_bufs, 1); pipe_bufs = 1; } - if (too_many_pipe_buffers_hard(user_bufs) && is_unprivileged_user()) + if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) goto out_revert_acct; pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), @@ -813,6 +836,7 @@ struct pipe_inode_info *alloc_pipe_info(void) pipe->r_counter = pipe->w_counter = 1; pipe->max_usage = pipe_bufs; pipe->ring_size = pipe_bufs; + pipe->nr_accounted = pipe_bufs; pipe->user = user; mutex_init(&pipe->mutex); return pipe; @@ -830,7 +854,14 @@ void free_pipe_info(struct pipe_inode_info *pipe) { int i; - (void) account_pipe_buffers(pipe->user, pipe->ring_size, 0); +#ifdef CONFIG_WATCH_QUEUE + if (pipe->watch_queue) { + watch_queue_clear(pipe->watch_queue); + put_watch_queue(pipe->watch_queue); + } +#endif + + (void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0); free_uid(pipe->user); for (i = 0; i < pipe->ring_size; i++) { struct pipe_buffer *buf = pipe->bufs + i; @@ -906,6 +937,17 @@ int create_pipe_files(struct file **res, int flags) if (!inode) return -ENFILE; + if (flags & O_NOTIFICATION_PIPE) { +#ifdef CONFIG_WATCH_QUEUE + if (watch_queue_init(inode->i_pipe) < 0) { + iput(inode); + return -ENOMEM; + } +#else + return -ENOPKG; +#endif + } + f = alloc_file_pseudo(inode, pipe_mnt, "", O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)), &pipefifo_fops); @@ -936,7 +978,7 @@ static int __do_pipe_flags(int *fd, struct file **files, int flags) int error; int fdw, fdr; - if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT)) + if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT | O_NOTIFICATION_PIPE)) return -EINVAL; error = create_pipe_files(files, flags); @@ -1184,42 +1226,12 @@ unsigned int round_pipe_size(unsigned long size) } /* - * Allocate a new array of pipe buffers and copy the info over. Returns the - * pipe size if successful, or return -ERROR on error. + * Resize the pipe ring to a number of slots. */ -static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) +int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) { struct pipe_buffer *bufs; - unsigned int size, nr_slots, head, tail, mask, n; - unsigned long user_bufs; - long ret = 0; - - size = round_pipe_size(arg); - nr_slots = size >> PAGE_SHIFT; - - if (!nr_slots) - return -EINVAL; - - /* - * If trying to increase the pipe capacity, check that an - * unprivileged user is not trying to exceed various limits - * (soft limit check here, hard limit check just below). - * Decreasing the pipe capacity is always permitted, even - * if the user is currently over a limit. - */ - if (nr_slots > pipe->ring_size && - size > pipe_max_size && !capable(CAP_SYS_RESOURCE)) - return -EPERM; - - user_bufs = account_pipe_buffers(pipe->user, pipe->ring_size, nr_slots); - - if (nr_slots > pipe->ring_size && - (too_many_pipe_buffers_hard(user_bufs) || - too_many_pipe_buffers_soft(user_bufs)) && - is_unprivileged_user()) { - ret = -EPERM; - goto out_revert_acct; - } + unsigned int head, tail, mask, n; /* * We can shrink the pipe, if arg is greater than the ring occupancy. @@ -1231,17 +1243,13 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) head = pipe->head; tail = pipe->tail; n = pipe_occupancy(pipe->head, pipe->tail); - if (nr_slots < n) { - ret = -EBUSY; - goto out_revert_acct; - } + if (nr_slots < n) + return -EBUSY; bufs = kcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); - if (unlikely(!bufs)) { - ret = -ENOMEM; - goto out_revert_acct; - } + if (unlikely(!bufs)) + return -ENOMEM; /* * The pipe array wraps around, so just start the new one at zero @@ -1269,16 +1277,68 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; - pipe->max_usage = nr_slots; + if (pipe->max_usage > nr_slots) + pipe->max_usage = nr_slots; pipe->tail = tail; pipe->head = head; /* This might have made more room for writers */ wake_up_interruptible(&pipe->wr_wait); + return 0; +} + +/* + * Allocate a new array of pipe buffers and copy the info over. Returns the + * pipe size if successful, or return -ERROR on error. + */ +static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) +{ + unsigned long user_bufs; + unsigned int nr_slots, size; + long ret = 0; + +#ifdef CONFIG_WATCH_QUEUE + if (pipe->watch_queue) + return -EBUSY; +#endif + + size = round_pipe_size(arg); + nr_slots = size >> PAGE_SHIFT; + + if (!nr_slots) + return -EINVAL; + + /* + * If trying to increase the pipe capacity, check that an + * unprivileged user is not trying to exceed various limits + * (soft limit check here, hard limit check just below). + * Decreasing the pipe capacity is always permitted, even + * if the user is currently over a limit. + */ + if (nr_slots > pipe->max_usage && + size > pipe_max_size && !capable(CAP_SYS_RESOURCE)) + return -EPERM; + + user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_slots); + + if (nr_slots > pipe->max_usage && + (too_many_pipe_buffers_hard(user_bufs) || + too_many_pipe_buffers_soft(user_bufs)) && + pipe_is_unprivileged_user()) { + ret = -EPERM; + goto out_revert_acct; + } + + ret = pipe_resize_ring(pipe, nr_slots); + if (ret < 0) + goto out_revert_acct; + + pipe->max_usage = nr_slots; + pipe->nr_accounted = nr_slots; return pipe->max_usage * PAGE_SIZE; out_revert_acct: - (void) account_pipe_buffers(pipe->user, nr_slots, pipe->ring_size); + (void) account_pipe_buffers(pipe->user, nr_slots, pipe->nr_accounted); return ret; } @@ -1287,9 +1347,17 @@ out_revert_acct: * location, so checking ->i_pipe is not enough to verify that this is a * pipe. */ -struct pipe_inode_info *get_pipe_info(struct file *file) +struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) { - return file->f_op == &pipefifo_fops ? file->private_data : NULL; + struct pipe_inode_info *pipe = file->private_data; + + if (file->f_op != &pipefifo_fops || !pipe) + return NULL; +#ifdef CONFIG_WATCH_QUEUE + if (for_splice && pipe->watch_queue) + return NULL; +#endif + return pipe; } long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) @@ -1297,7 +1365,7 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) struct pipe_inode_info *pipe; long ret; - pipe = get_pipe_info(file); + pipe = get_pipe_info(file, false); if (!pipe) return -EBADF; diff --git a/fs/splice.c b/fs/splice.c index fd0a1e7e5959..50f3c0260c00 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1122,8 +1122,8 @@ long do_splice(struct file *in, loff_t __user *off_in, !(out->f_mode & FMODE_WRITE))) return -EBADF; - ipipe = get_pipe_info(in); - opipe = get_pipe_info(out); + ipipe = get_pipe_info(in, true); + opipe = get_pipe_info(out, true); if (ipipe && opipe) { if (off_in || off_out) @@ -1273,7 +1273,7 @@ static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf, static long vmsplice_to_user(struct file *file, struct iov_iter *iter, unsigned int flags) { - struct pipe_inode_info *pipe = get_pipe_info(file); + struct pipe_inode_info *pipe = get_pipe_info(file, true); struct splice_desc sd = { .total_len = iov_iter_count(iter), .flags = flags, @@ -1308,7 +1308,7 @@ static long vmsplice_to_pipe(struct file *file, struct iov_iter *iter, if (flags & SPLICE_F_GIFT) buf_flag = PIPE_BUF_FLAG_GIFT; - pipe = get_pipe_info(file); + pipe = get_pipe_info(file, true); if (!pipe) return -EBADF; @@ -1757,8 +1757,8 @@ static int link_pipe(struct pipe_inode_info *ipipe, static long do_tee(struct file *in, struct file *out, size_t len, unsigned int flags) { - struct pipe_inode_info *ipipe = get_pipe_info(in); - struct pipe_inode_info *opipe = get_pipe_info(out); + struct pipe_inode_info *ipipe = get_pipe_info(in, true); + struct pipe_inode_info *opipe = get_pipe_info(out, true); int ret = -EINVAL; if (unlikely(!(in->f_mode & FMODE_READ) || diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index ae58fad7f1e0..1d3eaa233f4a 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -35,6 +35,7 @@ struct pipe_buffer { * @tail: The point of buffer consumption * @max_usage: The maximum number of slots that may be used in the ring * @ring_size: total number of buffers (should be a power of 2) + * @nr_accounted: The amount this pipe accounts for in user->pipe_bufs * @tmp_page: cached released page * @readers: number of current readers of this pipe * @writers: number of current writers of this pipe @@ -45,6 +46,7 @@ struct pipe_buffer { * @fasync_writers: writer side fasync * @bufs: the circular array of pipe buffers * @user: the user who created this pipe + * @watch_queue: If this pipe is a watch_queue, this is the stuff for that **/ struct pipe_inode_info { struct mutex mutex; @@ -53,6 +55,7 @@ struct pipe_inode_info { unsigned int tail; unsigned int max_usage; unsigned int ring_size; + unsigned int nr_accounted; unsigned int readers; unsigned int writers; unsigned int files; @@ -63,6 +66,9 @@ struct pipe_inode_info { struct fasync_struct *fasync_writers; struct pipe_buffer *bufs; struct user_struct *user; +#ifdef CONFIG_WATCH_QUEUE + struct watch_queue *watch_queue; +#endif }; /* @@ -237,9 +243,20 @@ void pipe_buf_mark_unmergeable(struct pipe_buffer *buf); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; +#ifdef CONFIG_WATCH_QUEUE +unsigned long account_pipe_buffers(struct user_struct *user, + unsigned long old, unsigned long new); +bool too_many_pipe_buffers_soft(unsigned long user_bufs); +bool too_many_pipe_buffers_hard(unsigned long user_bufs); +bool pipe_is_unprivileged_user(void); +#endif + /* for F_SETPIPE_SZ and F_GETPIPE_SZ */ +#ifdef CONFIG_WATCH_QUEUE +int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots); +#endif long pipe_fcntl(struct file *, unsigned int, unsigned long arg); -struct pipe_inode_info *get_pipe_info(struct file *file); +struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice); int create_pipe_files(struct file **, int); unsigned int round_pipe_size(unsigned long size); diff --git a/include/linux/watch_queue.h b/include/linux/watch_queue.h new file mode 100644 index 000000000000..5e08db2adc31 --- /dev/null +++ b/include/linux/watch_queue.h @@ -0,0 +1,127 @@ +// SPDX-License-Identifier: GPL-2.0 +/* User-mappable watch queue + * + * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * See Documentation/watch_queue.rst + */ + +#ifndef _LINUX_WATCH_QUEUE_H +#define _LINUX_WATCH_QUEUE_H + +#include +#include +#include + +#ifdef CONFIG_WATCH_QUEUE + +struct cred; + +struct watch_type_filter { + enum watch_notification_type type; + __u32 subtype_filter[1]; /* Bitmask of subtypes to filter on */ + __u32 info_filter; /* Filter on watch_notification::info */ + __u32 info_mask; /* Mask of relevant bits in info_filter */ +}; + +struct watch_filter { + union { + struct rcu_head rcu; + unsigned long type_filter[2]; /* Bitmask of accepted types */ + }; + u32 nr_filters; /* Number of filters */ + struct watch_type_filter filters[]; +}; + +struct watch_queue { + struct rcu_head rcu; + struct watch_filter __rcu *filter; + struct pipe_inode_info *pipe; /* The pipe we're using as a buffer */ + struct hlist_head watches; /* Contributory watches */ + struct page **notes; /* Preallocated notifications */ + unsigned long *notes_bitmap; /* Allocation bitmap for notes */ + struct kref usage; /* Object usage count */ + spinlock_t lock; + unsigned int nr_notes; /* Number of notes */ + unsigned int nr_pages; /* Number of pages in notes[] */ + bool defunct; /* T when queues closed */ +}; + +/* + * Representation of a watch on an object. + */ +struct watch { + union { + struct rcu_head rcu; + u32 info_id; /* ID to be OR'd in to info field */ + }; + struct watch_queue __rcu *queue; /* Queue to post events to */ + struct hlist_node queue_node; /* Link in queue->watches */ + struct watch_list __rcu *watch_list; + struct hlist_node list_node; /* Link in watch_list->watchers */ + const struct cred *cred; /* Creds of the owner of the watch */ + void *private; /* Private data for the watched object */ + u64 id; /* Internal identifier */ + struct kref usage; /* Object usage count */ +}; + +/* + * List of watches on an object. + */ +struct watch_list { + struct rcu_head rcu; + struct hlist_head watchers; + void (*release_watch)(struct watch *); + spinlock_t lock; +}; + +extern void __post_watch_notification(struct watch_list *, + struct watch_notification *, + const struct cred *, + u64); +extern struct watch_queue *get_watch_queue(int); +extern void put_watch_queue(struct watch_queue *); +extern void init_watch(struct watch *, struct watch_queue *); +extern int add_watch_to_object(struct watch *, struct watch_list *); +extern int remove_watch_from_object(struct watch_list *, struct watch_queue *, u64, bool); +extern long watch_queue_set_size(struct pipe_inode_info *, unsigned int); +extern long watch_queue_set_filter(struct pipe_inode_info *, + struct watch_notification_filter __user *); +extern int watch_queue_init(struct pipe_inode_info *); +extern void watch_queue_clear(struct watch_queue *); + +static inline void init_watch_list(struct watch_list *wlist, + void (*release_watch)(struct watch *)) +{ + INIT_HLIST_HEAD(&wlist->watchers); + spin_lock_init(&wlist->lock); + wlist->release_watch = release_watch; +} + +static inline void post_watch_notification(struct watch_list *wlist, + struct watch_notification *n, + const struct cred *cred, + u64 id) +{ + if (unlikely(wlist)) + __post_watch_notification(wlist, n, cred, id); +} + +static inline void remove_watch_list(struct watch_list *wlist, u64 id) +{ + if (wlist) { + remove_watch_from_object(wlist, NULL, id, true); + kfree_rcu(wlist, rcu); + } +} + +/** + * watch_sizeof - Calculate the information part of the size of a watch record, + * given the structure size. + */ +#define watch_sizeof(STRUCT) (sizeof(STRUCT) << WATCH_INFO_LENGTH__SHIFT) + +#endif + +#endif /* _LINUX_WATCH_QUEUE_H */ diff --git a/include/uapi/linux/watch_queue.h b/include/uapi/linux/watch_queue.h index 9df72227f515..3a5790f1f05d 100644 --- a/include/uapi/linux/watch_queue.h +++ b/include/uapi/linux/watch_queue.h @@ -4,9 +4,13 @@ #include #include +#include #define O_NOTIFICATION_PIPE O_EXCL /* Parameter to pipe2() selecting notification pipe */ +#define IOC_WATCH_QUEUE_SET_SIZE _IO('W', 0x60) /* Set the size in pages */ +#define IOC_WATCH_QUEUE_SET_FILTER _IO('W', 0x61) /* Set the filter */ + enum watch_notification_type { WATCH_TYPE_META = 0, /* Special record */ WATCH_TYPE__NR = 1 @@ -41,6 +45,22 @@ struct watch_notification { #define WATCH_INFO_FLAG_7 0x00800000 }; +/* + * Notification filtering rules (IOC_WATCH_QUEUE_SET_FILTER). + */ +struct watch_notification_type_filter { + __u32 type; /* Type to apply filter to */ + __u32 info_filter; /* Filter on watch_notification::info */ + __u32 info_mask; /* Mask of relevant bits in info_filter */ + __u32 subtype_filter[8]; /* Bitmask of subtypes to filter on */ +}; + +struct watch_notification_filter { + __u32 nr_filters; /* Number of filters */ + __u32 __reserved; /* Must be 0 */ + struct watch_notification_type_filter filters[]; +}; + /* * Extended watch removal notification. This is used optionally if the type diff --git a/init/Kconfig b/init/Kconfig index 74a5ac65644f..c95a2a5654a9 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -326,6 +326,18 @@ config POSIX_MQUEUE_SYSCTL depends on SYSCTL default y +config WATCH_QUEUE + bool "General notification queue" + default n + help + + This is a general notification queue for the kernel to pass events to + userspace by splicing them into pipes. It can be used in conjunction + with watches for key/keyring change notifications and device + notifications. + + See Documentation/watch_queue.rst + config CROSS_MEMORY_ATTACH bool "Enable process_vm_readv/writev syscalls" depends on MMU diff --git a/kernel/Makefile b/kernel/Makefile index 4cb4130ced32..41e7e3ae07ec 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -115,6 +115,7 @@ obj-$(CONFIG_TORTURE_TEST) += torture.o obj-$(CONFIG_HAS_IOMEM) += iomem.o obj-$(CONFIG_RSEQ) += rseq.o +obj-$(CONFIG_WATCH_QUEUE) += watch_queue.o obj-$(CONFIG_SYSCTL_KUNIT_TEST) += sysctl-test.o diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c new file mode 100644 index 000000000000..c103e34f8705 --- /dev/null +++ b/kernel/watch_queue.c @@ -0,0 +1,657 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Watch queue and general notification mechanism, built on pipes + * + * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * See Documentation/watch_queue.rst + */ + +#define pr_fmt(fmt) "watchq: " fmt +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +MODULE_DESCRIPTION("Watch queue"); +MODULE_AUTHOR("Red Hat, Inc."); +MODULE_LICENSE("GPL"); + +#define WATCH_QUEUE_NOTE_SIZE 128 +#define WATCH_QUEUE_NOTES_PER_PAGE (PAGE_SIZE / WATCH_QUEUE_NOTE_SIZE) + +static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + struct watch_queue *wqueue = (struct watch_queue *)buf->private; + struct page *page; + unsigned int bit; + + /* We need to work out which note within the page this refers to, but + * the note might have been maximum size, so merely ANDing the offset + * off doesn't work. OTOH, the note must've been more than zero size. + */ + bit = buf->offset + buf->len; + if ((bit & (WATCH_QUEUE_NOTE_SIZE - 1)) == 0) + bit -= WATCH_QUEUE_NOTE_SIZE; + bit /= WATCH_QUEUE_NOTE_SIZE; + + page = buf->page; + bit += page->index; + + set_bit(bit, wqueue->notes_bitmap); +} + +static int watch_queue_pipe_buf_steal(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + return -1; /* No. */ +} + +/* New data written to a pipe may be appended to a buffer with this type. */ +static const struct pipe_buf_operations watch_queue_pipe_buf_ops = { + .confirm = generic_pipe_buf_confirm, + .release = watch_queue_pipe_buf_release, + .steal = watch_queue_pipe_buf_steal, + .get = generic_pipe_buf_get, +}; + +/* + * Post a notification to a watch queue. + */ +static bool post_one_notification(struct watch_queue *wqueue, + struct watch_notification *n) +{ + void *p; + struct pipe_inode_info *pipe = wqueue->pipe; + struct pipe_buffer *buf; + struct page *page; + unsigned int head, tail, mask, note, offset, len; + bool done = false; + + if (!pipe) + return false; + + spin_lock_irq(&pipe->rd_wait.lock); + + if (wqueue->defunct) + goto out; + + mask = pipe->ring_size - 1; + head = pipe->head; + tail = pipe->tail; + if (pipe_full(head, tail, pipe->ring_size)) + goto lost; + + note = find_first_bit(wqueue->notes_bitmap, wqueue->nr_notes); + if (note >= wqueue->nr_notes) + goto lost; + + page = wqueue->notes[note / WATCH_QUEUE_NOTES_PER_PAGE]; + offset = note % WATCH_QUEUE_NOTES_PER_PAGE * WATCH_QUEUE_NOTE_SIZE; + get_page(page); + len = n->info & WATCH_INFO_LENGTH; + p = kmap_atomic(page); + memcpy(p + offset, n, len); + kunmap_atomic(p); + + buf = &pipe->bufs[head & mask]; + buf->page = page; + buf->private = (unsigned long)wqueue; + buf->ops = &watch_queue_pipe_buf_ops; + buf->offset = offset; + buf->len = len; + buf->flags = 0; + pipe->head = head + 1; + + if (!test_and_clear_bit(note, wqueue->notes_bitmap)) { + spin_unlock_irq(&pipe->rd_wait.lock); + BUG(); + } + wake_up_interruptible_sync_poll_locked(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); + done = true; + +out: + spin_unlock_irq(&pipe->rd_wait.lock); + if (done) + kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); + return done; + +lost: + goto out; +} + +/* + * Apply filter rules to a notification. + */ +static bool filter_watch_notification(const struct watch_filter *wf, + const struct watch_notification *n) +{ + const struct watch_type_filter *wt; + unsigned int st_bits = sizeof(wt->subtype_filter[0]) * 8; + unsigned int st_index = n->subtype / st_bits; + unsigned int st_bit = 1U << (n->subtype % st_bits); + int i; + + if (!test_bit(n->type, wf->type_filter)) + return false; + + for (i = 0; i < wf->nr_filters; i++) { + wt = &wf->filters[i]; + if (n->type == wt->type && + (wt->subtype_filter[st_index] & st_bit) && + (n->info & wt->info_mask) == wt->info_filter) + return true; + } + + return false; /* If there is a filter, the default is to reject. */ +} + +/** + * __post_watch_notification - Post an event notification + * @wlist: The watch list to post the event to. + * @n: The notification record to post. + * @cred: The creds of the process that triggered the notification. + * @id: The ID to match on the watch. + * + * Post a notification of an event into a set of watch queues and let the users + * know. + * + * The size of the notification should be set in n->info & WATCH_INFO_LENGTH and + * should be in units of sizeof(*n). + */ +void __post_watch_notification(struct watch_list *wlist, + struct watch_notification *n, + const struct cred *cred, + u64 id) +{ + const struct watch_filter *wf; + struct watch_queue *wqueue; + struct watch *watch; + + if (((n->info & WATCH_INFO_LENGTH) >> WATCH_INFO_LENGTH__SHIFT) == 0) { + WARN_ON(1); + return; + } + + rcu_read_lock(); + + hlist_for_each_entry_rcu(watch, &wlist->watchers, list_node) { + if (watch->id != id) + continue; + n->info &= ~WATCH_INFO_ID; + n->info |= watch->info_id; + + wqueue = rcu_dereference(watch->queue); + wf = rcu_dereference(wqueue->filter); + if (wf && !filter_watch_notification(wf, n)) + continue; + + if (security_post_notification(watch->cred, cred, n) < 0) + continue; + + post_one_notification(wqueue, n); + } + + rcu_read_unlock(); +} +EXPORT_SYMBOL(__post_watch_notification); + +/* + * Allocate sufficient pages to preallocation for the requested number of + * notifications. + */ +long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) +{ + struct watch_queue *wqueue = pipe->watch_queue; + struct page **pages; + unsigned long *bitmap; + unsigned long user_bufs; + unsigned int bmsize; + int ret, i, nr_pages; + + if (!wqueue) + return -ENODEV; + if (wqueue->notes) + return -EBUSY; + + if (nr_notes < 1 || + nr_notes > 512) /* TODO: choose a better hard limit */ + return -EINVAL; + + nr_pages = (nr_notes + WATCH_QUEUE_NOTES_PER_PAGE - 1); + nr_pages /= WATCH_QUEUE_NOTES_PER_PAGE; + user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_pages); + + if (nr_pages > pipe->max_usage && + (too_many_pipe_buffers_hard(user_bufs) || + too_many_pipe_buffers_soft(user_bufs)) && + pipe_is_unprivileged_user()) { + ret = -EPERM; + goto error; + } + + ret = pipe_resize_ring(pipe, nr_notes); + if (ret < 0) + goto error; + + pages = kcalloc(sizeof(struct page *), nr_pages, GFP_KERNEL); + if (!pages) + goto error; + + for (i = 0; i < nr_pages; i++) { + pages[i] = alloc_page(GFP_KERNEL); + if (!pages[i]) + goto error_p; + pages[i]->index = i * WATCH_QUEUE_NOTES_PER_PAGE; + } + + bmsize = (nr_notes + BITS_PER_LONG - 1) / BITS_PER_LONG; + bmsize *= sizeof(unsigned long); + bitmap = kmalloc(bmsize, GFP_KERNEL); + if (!bitmap) + goto error_p; + + memset(bitmap, 0xff, bmsize); + wqueue->notes = pages; + wqueue->notes_bitmap = bitmap; + wqueue->nr_pages = nr_pages; + wqueue->nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE; + return 0; + +error_p: + for (i = 0; i < nr_pages; i++) + __free_page(pages[i]); + kfree(pages); +error: + (void) account_pipe_buffers(pipe->user, nr_pages, pipe->nr_accounted); + return ret; +} + +/* + * Set the filter on a watch queue. + */ +long watch_queue_set_filter(struct pipe_inode_info *pipe, + struct watch_notification_filter __user *_filter) +{ + struct watch_notification_type_filter *tf; + struct watch_notification_filter filter; + struct watch_type_filter *q; + struct watch_filter *wfilter; + struct watch_queue *wqueue = pipe->watch_queue; + int ret, nr_filter = 0, i; + + if (!wqueue) + return -ENODEV; + + if (!_filter) { + /* Remove the old filter */ + wfilter = NULL; + goto set; + } + + /* Grab the user's filter specification */ + if (copy_from_user(&filter, _filter, sizeof(filter)) != 0) + return -EFAULT; + if (filter.nr_filters == 0 || + filter.nr_filters > 16 || + filter.__reserved != 0) + return -EINVAL; + + tf = memdup_user(_filter->filters, filter.nr_filters * sizeof(*tf)); + if (IS_ERR(tf)) + return PTR_ERR(tf); + + ret = -EINVAL; + for (i = 0; i < filter.nr_filters; i++) { + if ((tf[i].info_filter & ~tf[i].info_mask) || + tf[i].info_mask & WATCH_INFO_LENGTH) + goto err_filter; + /* Ignore any unknown types */ + if (tf[i].type >= sizeof(wfilter->type_filter) * 8) + continue; + nr_filter++; + } + + /* Now we need to build the internal filter from only the relevant + * user-specified filters. + */ + ret = -ENOMEM; + wfilter = kzalloc(struct_size(wfilter, filters, nr_filter), GFP_KERNEL); + if (!wfilter) + goto err_filter; + wfilter->nr_filters = nr_filter; + + q = wfilter->filters; + for (i = 0; i < filter.nr_filters; i++) { + if (tf[i].type >= sizeof(wfilter->type_filter) * BITS_PER_LONG) + continue; + + q->type = tf[i].type; + q->info_filter = tf[i].info_filter; + q->info_mask = tf[i].info_mask; + q->subtype_filter[0] = tf[i].subtype_filter[0]; + __set_bit(q->type, wfilter->type_filter); + q++; + } + + kfree(tf); +set: + pipe_lock(pipe); + wfilter = rcu_replace_pointer(wqueue->filter, wfilter, + lockdep_is_held(&pipe->mutex)); + pipe_unlock(pipe); + if (wfilter) + kfree_rcu(wfilter, rcu); + return 0; + +err_filter: + kfree(tf); + return ret; +} + +static void __put_watch_queue(struct kref *kref) +{ + struct watch_queue *wqueue = + container_of(kref, struct watch_queue, usage); + struct watch_filter *wfilter; + int i; + + for (i = 0; i < wqueue->nr_pages; i++) + __free_page(wqueue->notes[i]); + + wfilter = rcu_access_pointer(wqueue->filter); + if (wfilter) + kfree_rcu(wfilter, rcu); + kfree_rcu(wqueue, rcu); +} + +/** + * put_watch_queue - Dispose of a ref on a watchqueue. + * @wqueue: The watch queue to unref. + */ +void put_watch_queue(struct watch_queue *wqueue) +{ + kref_put(&wqueue->usage, __put_watch_queue); +} +EXPORT_SYMBOL(put_watch_queue); + +static void free_watch(struct rcu_head *rcu) +{ + struct watch *watch = container_of(rcu, struct watch, rcu); + + put_watch_queue(rcu_access_pointer(watch->queue)); + put_cred(watch->cred); +} + +static void __put_watch(struct kref *kref) +{ + struct watch *watch = container_of(kref, struct watch, usage); + + call_rcu(&watch->rcu, free_watch); +} + +/* + * Discard a watch. + */ +static void put_watch(struct watch *watch) +{ + kref_put(&watch->usage, __put_watch); +} + +/** + * init_watch_queue - Initialise a watch + * @watch: The watch to initialise. + * @wqueue: The queue to assign. + * + * Initialise a watch and set the watch queue. + */ +void init_watch(struct watch *watch, struct watch_queue *wqueue) +{ + kref_init(&watch->usage); + INIT_HLIST_NODE(&watch->list_node); + INIT_HLIST_NODE(&watch->queue_node); + rcu_assign_pointer(watch->queue, wqueue); +} + +/** + * add_watch_to_object - Add a watch on an object to a watch list + * @watch: The watch to add + * @wlist: The watch list to add to + * + * @watch->queue must have been set to point to the queue to post notifications + * to and the watch list of the object to be watched. @watch->cred must also + * have been set to the appropriate credentials and a ref taken on them. + * + * The caller must pin the queue and the list both and must hold the list + * locked against racing watch additions/removals. + */ +int add_watch_to_object(struct watch *watch, struct watch_list *wlist) +{ + struct watch_queue *wqueue = rcu_access_pointer(watch->queue); + struct watch *w; + + hlist_for_each_entry(w, &wlist->watchers, list_node) { + struct watch_queue *wq = rcu_access_pointer(w->queue); + if (wqueue == wq && watch->id == w->id) + return -EBUSY; + } + + watch->cred = get_current_cred(); + rcu_assign_pointer(watch->watch_list, wlist); + + spin_lock_bh(&wqueue->lock); + kref_get(&wqueue->usage); + kref_get(&watch->usage); + hlist_add_head(&watch->queue_node, &wqueue->watches); + spin_unlock_bh(&wqueue->lock); + + hlist_add_head(&watch->list_node, &wlist->watchers); + return 0; +} +EXPORT_SYMBOL(add_watch_to_object); + +/** + * remove_watch_from_object - Remove a watch or all watches from an object. + * @wlist: The watch list to remove from + * @wq: The watch queue of interest (ignored if @all is true) + * @id: The ID of the watch to remove (ignored if @all is true) + * @all: True to remove all objects + * + * Remove a specific watch or all watches from an object. A notification is + * sent to the watcher to tell them that this happened. + */ +int remove_watch_from_object(struct watch_list *wlist, struct watch_queue *wq, + u64 id, bool all) +{ + struct watch_notification_removal n; + struct watch_queue *wqueue; + struct watch *watch; + int ret = -EBADSLT; + + rcu_read_lock(); + +again: + spin_lock(&wlist->lock); + hlist_for_each_entry(watch, &wlist->watchers, list_node) { + if (all || + (watch->id == id && rcu_access_pointer(watch->queue) == wq)) + goto found; + } + spin_unlock(&wlist->lock); + goto out; + +found: + ret = 0; + hlist_del_init_rcu(&watch->list_node); + rcu_assign_pointer(watch->watch_list, NULL); + spin_unlock(&wlist->lock); + + /* We now own the reference on watch that used to belong to wlist. */ + + n.watch.type = WATCH_TYPE_META; + n.watch.subtype = WATCH_META_REMOVAL_NOTIFICATION; + n.watch.info = watch->info_id | watch_sizeof(n.watch); + n.id = id; + if (id != 0) + n.watch.info = watch->info_id | watch_sizeof(n); + + wqueue = rcu_dereference(watch->queue); + + /* We don't need the watch list lock for the next bit as RCU is + * protecting *wqueue from deallocation. + */ + if (wqueue) { + post_one_notification(wqueue, &n.watch); + + spin_lock_bh(&wqueue->lock); + + if (!hlist_unhashed(&watch->queue_node)) { + hlist_del_init_rcu(&watch->queue_node); + put_watch(watch); + } + + spin_unlock_bh(&wqueue->lock); + } + + if (wlist->release_watch) { + void (*release_watch)(struct watch *); + + release_watch = wlist->release_watch; + rcu_read_unlock(); + (*release_watch)(watch); + rcu_read_lock(); + } + put_watch(watch); + + if (all && !hlist_empty(&wlist->watchers)) + goto again; +out: + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL(remove_watch_from_object); + +/* + * Remove all the watches that are contributory to a queue. This has the + * potential to race with removal of the watches by the destruction of the + * objects being watched or with the distribution of notifications. + */ +void watch_queue_clear(struct watch_queue *wqueue) +{ + struct watch_list *wlist; + struct watch *watch; + bool release; + + rcu_read_lock(); + spin_lock_bh(&wqueue->lock); + + /* Prevent new additions and prevent notifications from happening */ + wqueue->defunct = true; + + while (!hlist_empty(&wqueue->watches)) { + watch = hlist_entry(wqueue->watches.first, struct watch, queue_node); + hlist_del_init_rcu(&watch->queue_node); + /* We now own a ref on the watch. */ + spin_unlock_bh(&wqueue->lock); + + /* We can't do the next bit under the queue lock as we need to + * get the list lock - which would cause a deadlock if someone + * was removing from the opposite direction at the same time or + * posting a notification. + */ + wlist = rcu_dereference(watch->watch_list); + if (wlist) { + void (*release_watch)(struct watch *); + + spin_lock(&wlist->lock); + + release = !hlist_unhashed(&watch->list_node); + if (release) { + hlist_del_init_rcu(&watch->list_node); + rcu_assign_pointer(watch->watch_list, NULL); + + /* We now own a second ref on the watch. */ + } + + release_watch = wlist->release_watch; + spin_unlock(&wlist->lock); + + if (release) { + if (release_watch) { + rcu_read_unlock(); + /* This might need to call dput(), so + * we have to drop all the locks. + */ + (*release_watch)(watch); + rcu_read_lock(); + } + put_watch(watch); + } + } + + put_watch(watch); + spin_lock_bh(&wqueue->lock); + } + + spin_unlock_bh(&wqueue->lock); + rcu_read_unlock(); +} + +/** + * get_watch_queue - Get a watch queue from its file descriptor. + * @fd: The fd to query. + */ +struct watch_queue *get_watch_queue(int fd) +{ + struct pipe_inode_info *pipe; + struct watch_queue *wqueue = ERR_PTR(-EINVAL); + struct fd f; + + f = fdget(fd); + if (f.file) { + pipe = get_pipe_info(f.file, false); + if (pipe && pipe->watch_queue) { + wqueue = pipe->watch_queue; + kref_get(&wqueue->usage); + } + fdput(f); + } + + return wqueue; +} +EXPORT_SYMBOL(get_watch_queue); + +/* + * Initialise a watch queue + */ +int watch_queue_init(struct pipe_inode_info *pipe) +{ + struct watch_queue *wqueue; + + wqueue = kzalloc(sizeof(*wqueue), GFP_KERNEL); + if (!wqueue) + return -ENOMEM; + + wqueue->pipe = pipe; + kref_init(&wqueue->usage); + spin_lock_init(&wqueue->lock); + INIT_HLIST_HEAD(&wqueue->watches); + + pipe->watch_queue = wqueue; + return 0; +} -- cgit v1.2.3 From f7e47677e39a03057dcced2016c92a9c868693ec Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Jan 2020 17:07:11 +0000 Subject: watch_queue: Add a key/keyring notification facility Add a key/keyring change notification facility whereby notifications about changes in key and keyring content and attributes can be received. Firstly, an event queue needs to be created: pipe2(fds, O_NOTIFICATION_PIPE); ioctl(fds[1], IOC_WATCH_QUEUE_SET_SIZE, 256); then a notification can be set up to report notifications via that queue: struct watch_notification_filter filter = { .nr_filters = 1, .filters = { [0] = { .type = WATCH_TYPE_KEY_NOTIFY, .subtype_filter[0] = UINT_MAX, }, }, }; ioctl(fds[1], IOC_WATCH_QUEUE_SET_FILTER, &filter); keyctl_watch_key(KEY_SPEC_SESSION_KEYRING, fds[1], 0x01); After that, records will be placed into the queue when events occur in which keys are changed in some way. Records are of the following format: struct key_notification { struct watch_notification watch; __u32 key_id; __u32 aux; } *n; Where: n->watch.type will be WATCH_TYPE_KEY_NOTIFY. n->watch.subtype will indicate the type of event, such as NOTIFY_KEY_REVOKED. n->watch.info & WATCH_INFO_LENGTH will indicate the length of the record. n->watch.info & WATCH_INFO_ID will be the second argument to keyctl_watch_key(), shifted. n->key will be the ID of the affected key. n->aux will hold subtype-dependent information, such as the key being linked into the keyring specified by n->key in the case of NOTIFY_KEY_LINKED. Note that it is permissible for event records to be of variable length - or, at least, the length may be dependent on the subtype. Note also that the queue can be shared between multiple notifications of various types. Signed-off-by: David Howells Reviewed-by: James Morris --- Documentation/security/keys/core.rst | 57 +++++++++++++++++++++ include/linux/key.h | 3 ++ include/uapi/linux/keyctl.h | 2 + include/uapi/linux/watch_queue.h | 28 +++++++++- security/keys/Kconfig | 9 ++++ security/keys/compat.c | 3 ++ security/keys/gc.c | 5 ++ security/keys/internal.h | 30 ++++++++++- security/keys/key.c | 38 +++++++++----- security/keys/keyctl.c | 99 ++++++++++++++++++++++++++++++++++-- security/keys/keyring.c | 20 +++++--- security/keys/request_key.c | 4 +- 12 files changed, 270 insertions(+), 28 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/security/keys/core.rst b/Documentation/security/keys/core.rst index d9b0b859018b..6cff2b5f88ed 100644 --- a/Documentation/security/keys/core.rst +++ b/Documentation/security/keys/core.rst @@ -1026,6 +1026,63 @@ The keyctl syscall functions are: written into the output buffer. Verification returns 0 on success. + * Watch a key or keyring for changes:: + + long keyctl(KEYCTL_WATCH_KEY, key_serial_t key, int queue_fd, + const struct watch_notification_filter *filter); + + This will set or remove a watch for changes on the specified key or + keyring. + + "key" is the ID of the key to be watched. + + "queue_fd" is a file descriptor referring to an open "/dev/watch_queue" + which manages the buffer into which notifications will be delivered. + + "filter" is either NULL to remove a watch or a filter specification to + indicate what events are required from the key. + + See Documentation/watch_queue.rst for more information. + + Note that only one watch may be emplaced for any particular { key, + queue_fd } combination. + + Notification records look like:: + + struct key_notification { + struct watch_notification watch; + __u32 key_id; + __u32 aux; + }; + + In this, watch::type will be "WATCH_TYPE_KEY_NOTIFY" and subtype will be + one of:: + + NOTIFY_KEY_INSTANTIATED + NOTIFY_KEY_UPDATED + NOTIFY_KEY_LINKED + NOTIFY_KEY_UNLINKED + NOTIFY_KEY_CLEARED + NOTIFY_KEY_REVOKED + NOTIFY_KEY_INVALIDATED + NOTIFY_KEY_SETATTR + + Where these indicate a key being instantiated/rejected, updated, a link + being made in a keyring, a link being removed from a keyring, a keyring + being cleared, a key being revoked, a key being invalidated or a key + having one of its attributes changed (user, group, perm, timeout, + restriction). + + If a watched key is deleted, a basic watch_notification will be issued + with "type" set to WATCH_TYPE_META and "subtype" set to + watch_meta_removal_notification. The watchpoint ID will be set in the + "info" field. + + This needs to be configured by enabling: + + "Provide key/keyring change notifications" (KEY_NOTIFICATIONS) + + Kernel Services =============== diff --git a/include/linux/key.h b/include/linux/key.h index 6cf8e71cf8b7..b99b40db08fc 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -176,6 +176,9 @@ struct key { struct list_head graveyard_link; struct rb_node serial_node; }; +#ifdef CONFIG_KEY_NOTIFICATIONS + struct watch_list *watchers; /* Entities watching this key for changes */ +#endif struct rw_semaphore sem; /* change vs change sem */ struct key_user *user; /* owner of this key */ void *security; /* security data for this key */ diff --git a/include/uapi/linux/keyctl.h b/include/uapi/linux/keyctl.h index ed3d5893830d..4c8884eea808 100644 --- a/include/uapi/linux/keyctl.h +++ b/include/uapi/linux/keyctl.h @@ -69,6 +69,7 @@ #define KEYCTL_RESTRICT_KEYRING 29 /* Restrict keys allowed to link to a keyring */ #define KEYCTL_MOVE 30 /* Move keys between keyrings */ #define KEYCTL_CAPABILITIES 31 /* Find capabilities of keyrings subsystem */ +#define KEYCTL_WATCH_KEY 32 /* Watch a key or ring of keys for changes */ /* keyctl structures */ struct keyctl_dh_params { @@ -130,5 +131,6 @@ struct keyctl_pkey_params { #define KEYCTL_CAPS0_MOVE 0x80 /* KEYCTL_MOVE supported */ #define KEYCTL_CAPS1_NS_KEYRING_NAME 0x01 /* Keyring names are per-user_namespace */ #define KEYCTL_CAPS1_NS_KEY_TAG 0x02 /* Key indexing can include a namespace tag */ +#define KEYCTL_CAPS1_NOTIFICATIONS 0x04 /* Keys generate watchable notifications */ #endif /* _LINUX_KEYCTL_H */ diff --git a/include/uapi/linux/watch_queue.h b/include/uapi/linux/watch_queue.h index 3a5790f1f05d..c3d8320b5d3a 100644 --- a/include/uapi/linux/watch_queue.h +++ b/include/uapi/linux/watch_queue.h @@ -13,7 +13,8 @@ enum watch_notification_type { WATCH_TYPE_META = 0, /* Special record */ - WATCH_TYPE__NR = 1 + WATCH_TYPE_KEY_NOTIFY = 1, /* Key change event notification */ + WATCH_TYPE__NR = 2 }; enum watch_meta_notification_subtype { @@ -75,4 +76,29 @@ struct watch_notification_removal { __u64 id; /* Type-dependent identifier */ }; +/* + * Type of key/keyring change notification. + */ +enum key_notification_subtype { + NOTIFY_KEY_INSTANTIATED = 0, /* Key was instantiated (aux is error code) */ + NOTIFY_KEY_UPDATED = 1, /* Key was updated */ + NOTIFY_KEY_LINKED = 2, /* Key (aux) was added to watched keyring */ + NOTIFY_KEY_UNLINKED = 3, /* Key (aux) was removed from watched keyring */ + NOTIFY_KEY_CLEARED = 4, /* Keyring was cleared */ + NOTIFY_KEY_REVOKED = 5, /* Key was revoked */ + NOTIFY_KEY_INVALIDATED = 6, /* Key was invalidated */ + NOTIFY_KEY_SETATTR = 7, /* Key's attributes got changed */ +}; + +/* + * Key/keyring notification record. + * - watch.type = WATCH_TYPE_KEY_NOTIFY + * - watch.subtype = enum key_notification_type + */ +struct key_notification { + struct watch_notification watch; + __u32 key_id; /* The key/keyring affected */ + __u32 aux; /* Per-type auxiliary data */ +}; + #endif /* _UAPI_LINUX_WATCH_QUEUE_H */ diff --git a/security/keys/Kconfig b/security/keys/Kconfig index 47c041563d41..d4dc5ea208af 100644 --- a/security/keys/Kconfig +++ b/security/keys/Kconfig @@ -116,3 +116,12 @@ config KEY_DH_OPERATIONS in the kernel. If you are unsure as to whether this is required, answer N. + +config KEY_NOTIFICATIONS + bool "Provide key/keyring change notifications" + depends on KEYS && WATCH_QUEUE + help + This option provides support for getting change notifications on keys + and keyrings on which the caller has View permission. This makes use + of the /dev/watch_queue misc device to handle the notification + buffer and provides KEYCTL_WATCH_KEY to enable/disable watches. diff --git a/security/keys/compat.c b/security/keys/compat.c index b975f8f11124..6ee9d8f6a4a5 100644 --- a/security/keys/compat.c +++ b/security/keys/compat.c @@ -156,6 +156,9 @@ COMPAT_SYSCALL_DEFINE5(keyctl, u32, option, case KEYCTL_CAPABILITIES: return keyctl_capabilities(compat_ptr(arg2), arg3); + case KEYCTL_WATCH_KEY: + return keyctl_watch_key(arg2, arg3, arg4); + default: return -EOPNOTSUPP; } diff --git a/security/keys/gc.c b/security/keys/gc.c index 671dd730ecfc..3c90807476eb 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -131,6 +131,11 @@ static noinline void key_gc_unused_keys(struct list_head *keys) kdebug("- %u", key->serial); key_check(key); +#ifdef CONFIG_KEY_NOTIFICATIONS + remove_watch_list(key->watchers, key->serial); + key->watchers = NULL; +#endif + /* Throw away the key data if the key is instantiated */ if (state == KEY_IS_POSITIVE && key->type->destroy) key->type->destroy(key); diff --git a/security/keys/internal.h b/security/keys/internal.h index 6d0ca48ae9a5..28e17f4f3328 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -99,7 +100,8 @@ extern int __key_link_begin(struct key *keyring, const struct keyring_index_key *index_key, struct assoc_array_edit **_edit); extern int __key_link_check_live_key(struct key *keyring, struct key *key); -extern void __key_link(struct key *key, struct assoc_array_edit **_edit); +extern void __key_link(struct key *keyring, struct key *key, + struct assoc_array_edit **_edit); extern void __key_link_end(struct key *keyring, const struct keyring_index_key *index_key, struct assoc_array_edit *edit); @@ -183,6 +185,23 @@ extern int key_task_permission(const key_ref_t key_ref, const struct cred *cred, key_perm_t perm); +static inline void notify_key(struct key *key, + enum key_notification_subtype subtype, u32 aux) +{ +#ifdef CONFIG_KEY_NOTIFICATIONS + struct key_notification n = { + .watch.type = WATCH_TYPE_KEY_NOTIFY, + .watch.subtype = subtype, + .watch.info = watch_sizeof(n), + .key_id = key_serial(key), + .aux = aux, + }; + + post_watch_notification(key->watchers, &n.watch, current_cred(), + n.key_id); +#endif +} + /* * Check to see whether permission is granted to use a key in the desired way. */ @@ -333,6 +352,15 @@ static inline long keyctl_pkey_e_d_s(int op, extern long keyctl_capabilities(unsigned char __user *_buffer, size_t buflen); +#ifdef CONFIG_KEY_NOTIFICATIONS +extern long keyctl_watch_key(key_serial_t, int, int); +#else +static inline long keyctl_watch_key(key_serial_t key_id, int watch_fd, int watch_id) +{ + return -EOPNOTSUPP; +} +#endif + /* * Debugging key validation */ diff --git a/security/keys/key.c b/security/keys/key.c index e959b3c96b48..e282c6179b21 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -444,6 +444,7 @@ static int __key_instantiate_and_link(struct key *key, /* mark the key as being instantiated */ atomic_inc(&key->user->nikeys); mark_key_instantiated(key, 0); + notify_key(key, NOTIFY_KEY_INSTANTIATED, 0); if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) awaken = 1; @@ -453,7 +454,7 @@ static int __key_instantiate_and_link(struct key *key, if (test_bit(KEY_FLAG_KEEP, &keyring->flags)) set_bit(KEY_FLAG_KEEP, &key->flags); - __key_link(key, _edit); + __key_link(keyring, key, _edit); } /* disable the authorisation key */ @@ -601,6 +602,7 @@ int key_reject_and_link(struct key *key, /* mark the key as being negatively instantiated */ atomic_inc(&key->user->nikeys); mark_key_instantiated(key, -error); + notify_key(key, NOTIFY_KEY_INSTANTIATED, -error); key->expiry = ktime_get_real_seconds() + timeout; key_schedule_gc(key->expiry + key_gc_delay); @@ -611,7 +613,7 @@ int key_reject_and_link(struct key *key, /* and link it into the destination keyring */ if (keyring && link_ret == 0) - __key_link(key, &edit); + __key_link(keyring, key, &edit); /* disable the authorisation key */ if (authkey) @@ -764,9 +766,11 @@ static inline key_ref_t __key_update(key_ref_t key_ref, down_write(&key->sem); ret = key->type->update(key, prep); - if (ret == 0) + if (ret == 0) { /* Updating a negative key positively instantiates it */ mark_key_instantiated(key, 0); + notify_key(key, NOTIFY_KEY_UPDATED, 0); + } up_write(&key->sem); @@ -1023,9 +1027,11 @@ int key_update(key_ref_t key_ref, const void *payload, size_t plen) down_write(&key->sem); ret = key->type->update(key, &prep); - if (ret == 0) + if (ret == 0) { /* Updating a negative key positively instantiates it */ mark_key_instantiated(key, 0); + notify_key(key, NOTIFY_KEY_UPDATED, 0); + } up_write(&key->sem); @@ -1057,15 +1063,17 @@ void key_revoke(struct key *key) * instantiated */ down_write_nested(&key->sem, 1); - if (!test_and_set_bit(KEY_FLAG_REVOKED, &key->flags) && - key->type->revoke) - key->type->revoke(key); - - /* set the death time to no more than the expiry time */ - time = ktime_get_real_seconds(); - if (key->revoked_at == 0 || key->revoked_at > time) { - key->revoked_at = time; - key_schedule_gc(key->revoked_at + key_gc_delay); + if (!test_and_set_bit(KEY_FLAG_REVOKED, &key->flags)) { + notify_key(key, NOTIFY_KEY_REVOKED, 0); + if (key->type->revoke) + key->type->revoke(key); + + /* set the death time to no more than the expiry time */ + time = ktime_get_real_seconds(); + if (key->revoked_at == 0 || key->revoked_at > time) { + key->revoked_at = time; + key_schedule_gc(key->revoked_at + key_gc_delay); + } } up_write(&key->sem); @@ -1087,8 +1095,10 @@ void key_invalidate(struct key *key) if (!test_bit(KEY_FLAG_INVALIDATED, &key->flags)) { down_write_nested(&key->sem, 1); - if (!test_and_set_bit(KEY_FLAG_INVALIDATED, &key->flags)) + if (!test_and_set_bit(KEY_FLAG_INVALIDATED, &key->flags)) { + notify_key(key, NOTIFY_KEY_INVALIDATED, 0); key_schedule_gc_links(); + } up_write(&key->sem); } } diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 5e01192e222a..7d8de1c9a478 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -37,7 +37,9 @@ static const unsigned char keyrings_capabilities[2] = { KEYCTL_CAPS0_MOVE ), [1] = (KEYCTL_CAPS1_NS_KEYRING_NAME | - KEYCTL_CAPS1_NS_KEY_TAG), + KEYCTL_CAPS1_NS_KEY_TAG | + (IS_ENABLED(CONFIG_KEY_NOTIFICATIONS) ? KEYCTL_CAPS1_NOTIFICATIONS : 0) + ), }; static int key_get_type_from_user(char *type, @@ -1039,6 +1041,7 @@ long keyctl_chown_key(key_serial_t id, uid_t user, gid_t group) if (group != (gid_t) -1) key->gid = gid; + notify_key(key, NOTIFY_KEY_SETATTR, 0); ret = 0; error_put: @@ -1089,6 +1092,7 @@ long keyctl_setperm_key(key_serial_t id, key_perm_t perm) /* if we're not the sysadmin, we can only change a key that we own */ if (capable(CAP_SYS_ADMIN) || uid_eq(key->uid, current_fsuid())) { key->perm = perm; + notify_key(key, NOTIFY_KEY_SETATTR, 0); ret = 0; } @@ -1480,10 +1484,12 @@ long keyctl_set_timeout(key_serial_t id, unsigned timeout) okay: key = key_ref_to_ptr(key_ref); ret = 0; - if (test_bit(KEY_FLAG_KEEP, &key->flags)) + if (test_bit(KEY_FLAG_KEEP, &key->flags)) { ret = -EPERM; - else + } else { key_set_timeout(key, timeout); + notify_key(key, NOTIFY_KEY_SETATTR, 0); + } key_put(key); error: @@ -1757,6 +1763,90 @@ error: return ret; } +#ifdef CONFIG_KEY_NOTIFICATIONS +/* + * Watch for changes to a key. + * + * The caller must have View permission to watch a key or keyring. + */ +long keyctl_watch_key(key_serial_t id, int watch_queue_fd, int watch_id) +{ + struct watch_queue *wqueue; + struct watch_list *wlist = NULL; + struct watch *watch = NULL; + struct key *key; + key_ref_t key_ref; + long ret; + + if (watch_id < -1 || watch_id > 0xff) + return -EINVAL; + + key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE, KEY_NEED_VIEW); + if (IS_ERR(key_ref)) + return PTR_ERR(key_ref); + key = key_ref_to_ptr(key_ref); + + wqueue = get_watch_queue(watch_queue_fd); + if (IS_ERR(wqueue)) { + ret = PTR_ERR(wqueue); + goto err_key; + } + + if (watch_id >= 0) { + ret = -ENOMEM; + if (!key->watchers) { + wlist = kzalloc(sizeof(*wlist), GFP_KERNEL); + if (!wlist) + goto err_wqueue; + init_watch_list(wlist, NULL); + } + + watch = kzalloc(sizeof(*watch), GFP_KERNEL); + if (!watch) + goto err_wlist; + + init_watch(watch, wqueue); + watch->id = key->serial; + watch->info_id = (u32)watch_id << WATCH_INFO_ID__SHIFT; + + ret = security_watch_key(key); + if (ret < 0) + goto err_watch; + + down_write(&key->sem); + if (!key->watchers) { + key->watchers = wlist; + wlist = NULL; + } + + ret = add_watch_to_object(watch, key->watchers); + up_write(&key->sem); + + if (ret == 0) + watch = NULL; + } else { + ret = -EBADSLT; + if (key->watchers) { + down_write(&key->sem); + ret = remove_watch_from_object(key->watchers, + wqueue, key_serial(key), + false); + up_write(&key->sem); + } + } + +err_watch: + kfree(watch); +err_wlist: + kfree(wlist); +err_wqueue: + put_watch_queue(wqueue); +err_key: + key_put(key); + return ret; +} +#endif /* CONFIG_KEY_NOTIFICATIONS */ + /* * Get keyrings subsystem capabilities. */ @@ -1926,6 +2016,9 @@ SYSCALL_DEFINE5(keyctl, int, option, unsigned long, arg2, unsigned long, arg3, case KEYCTL_CAPABILITIES: return keyctl_capabilities((unsigned char __user *)arg2, (size_t)arg3); + case KEYCTL_WATCH_KEY: + return keyctl_watch_key((key_serial_t)arg2, (int)arg3, (int)arg4); + default: return -EOPNOTSUPP; } diff --git a/security/keys/keyring.c b/security/keys/keyring.c index 5ca620d31cd3..14abfe765b7e 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -1056,12 +1056,14 @@ int keyring_restrict(key_ref_t keyring_ref, const char *type, down_write(&keyring->sem); down_write(&keyring_serialise_restrict_sem); - if (keyring->restrict_link) + if (keyring->restrict_link) { ret = -EEXIST; - else if (keyring_detect_restriction_cycle(keyring, restrict_link)) + } else if (keyring_detect_restriction_cycle(keyring, restrict_link)) { ret = -EDEADLK; - else + } else { keyring->restrict_link = restrict_link; + notify_key(keyring, NOTIFY_KEY_SETATTR, 0); + } up_write(&keyring_serialise_restrict_sem); up_write(&keyring->sem); @@ -1362,12 +1364,14 @@ int __key_link_check_live_key(struct key *keyring, struct key *key) * holds at most one link to any given key of a particular type+description * combination. */ -void __key_link(struct key *key, struct assoc_array_edit **_edit) +void __key_link(struct key *keyring, struct key *key, + struct assoc_array_edit **_edit) { __key_get(key); assoc_array_insert_set_object(*_edit, keyring_key_to_ptr(key)); assoc_array_apply_edit(*_edit); *_edit = NULL; + notify_key(keyring, NOTIFY_KEY_LINKED, key_serial(key)); } /* @@ -1451,7 +1455,7 @@ int key_link(struct key *keyring, struct key *key) if (ret == 0) ret = __key_link_check_live_key(keyring, key); if (ret == 0) - __key_link(key, &edit); + __key_link(keyring, key, &edit); error_end: __key_link_end(keyring, &key->index_key, edit); @@ -1483,7 +1487,7 @@ static int __key_unlink_begin(struct key *keyring, struct key *key, struct assoc_array_edit *edit; BUG_ON(*_edit != NULL); - + edit = assoc_array_delete(&keyring->keys, &keyring_assoc_array_ops, &key->index_key); if (IS_ERR(edit)) @@ -1503,6 +1507,7 @@ static void __key_unlink(struct key *keyring, struct key *key, struct assoc_array_edit **_edit) { assoc_array_apply_edit(*_edit); + notify_key(keyring, NOTIFY_KEY_UNLINKED, key_serial(key)); *_edit = NULL; key_payload_reserve(keyring, keyring->datalen - KEYQUOTA_LINK_BYTES); } @@ -1621,7 +1626,7 @@ int key_move(struct key *key, goto error; __key_unlink(from_keyring, key, &from_edit); - __key_link(key, &to_edit); + __key_link(to_keyring, key, &to_edit); error: __key_link_end(to_keyring, &key->index_key, to_edit); __key_unlink_end(from_keyring, key, from_edit); @@ -1655,6 +1660,7 @@ int keyring_clear(struct key *keyring) } else { if (edit) assoc_array_apply_edit(edit); + notify_key(keyring, NOTIFY_KEY_CLEARED, 0); key_payload_reserve(keyring, 0); ret = 0; } diff --git a/security/keys/request_key.c b/security/keys/request_key.c index 957b9e3e1492..e1b9f1a80676 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -418,7 +418,7 @@ static int construct_alloc_key(struct keyring_search_context *ctx, goto key_already_present; if (dest_keyring) - __key_link(key, &edit); + __key_link(dest_keyring, key, &edit); mutex_unlock(&key_construction_mutex); if (dest_keyring) @@ -437,7 +437,7 @@ key_already_present: if (dest_keyring) { ret = __key_link_check_live_key(dest_keyring, key); if (ret == 0) - __key_link(key, &edit); + __key_link(dest_keyring, key, &edit); __key_link_end(dest_keyring, &ctx->index_key, edit); if (ret < 0) goto link_check_failed; -- cgit v1.2.3 From e3b1078bedd323df343894a27eb3b3c34944dfd1 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 15 May 2020 13:41:41 -0700 Subject: fscrypt: add support for IV_INO_LBLK_32 policies The eMMC inline crypto standard will only specify 32 DUN bits (a.k.a. IV bits), unlike UFS's 64. IV_INO_LBLK_64 is therefore not applicable, but an encryption format which uses one key per policy and permits the moving of encrypted file contents (as f2fs's garbage collector requires) is still desirable. To support such hardware, add a new encryption format IV_INO_LBLK_32 that makes the best use of the 32 bits: the IV is set to 'SipHash-2-4(inode_number) + file_logical_block_number mod 2^32', where the SipHash key is derived from the fscrypt master key. We hash only the inode number and not also the block number, because we need to maintain contiguity of DUNs to merge bios. Unlike with IV_INO_LBLK_64, with this format IV reuse is possible; this is unavoidable given the size of the DUN. This means this format should only be used where the requirements of the first paragraph apply. However, the hash spreads out the IVs in the whole usable range, and the use of a keyed hash makes it difficult for an attacker to determine which files use which IVs. Besides the above differences, this flag works like IV_INO_LBLK_64 in that on ext4 it is only allowed if the stable_inodes feature has been enabled to prevent inode numbers and the filesystem UUID from changing. Link: https://lore.kernel.org/r/20200515204141.251098-1-ebiggers@kernel.org Reviewed-by: Theodore Ts'o Reviewed-by: Paul Crowley Signed-off-by: Eric Biggers --- Documentation/filesystems/fscrypt.rst | 33 ++++++++++++-- fs/crypto/crypto.c | 6 ++- fs/crypto/fscrypt_private.h | 20 ++++++--- fs/crypto/keyring.c | 5 ++- fs/crypto/keysetup.c | 85 +++++++++++++++++++++++++++-------- fs/crypto/policy.c | 51 +++++++++++++++------ include/uapi/linux/fscrypt.h | 3 +- 7 files changed, 157 insertions(+), 46 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index aa072112cfff..f517af8ec11c 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -292,8 +292,22 @@ files' data differently, inode numbers are included in the IVs. Consequently, shrinking the filesystem may not be allowed. This format is optimized for use with inline encryption hardware -compliant with the UFS or eMMC standards, which support only 64 IV -bits per I/O request and may have only a small number of keyslots. +compliant with the UFS standard, which supports only 64 IV bits per +I/O request and may have only a small number of keyslots. + +IV_INO_LBLK_32 policies +----------------------- + +IV_INO_LBLK_32 policies work like IV_INO_LBLK_64, except that for +IV_INO_LBLK_32, the inode number is hashed with SipHash-2-4 (where the +SipHash key is derived from the master key) and added to the file +logical block number mod 2^32 to produce a 32-bit IV. + +This format is optimized for use with inline encryption hardware +compliant with the eMMC v5.2 standard, which supports only 32 IV bits +per I/O request and may have only a small number of keyslots. This +format results in some level of IV reuse, so it should only be used +when necessary due to hardware limitations. Key identifiers --------------- @@ -369,6 +383,10 @@ a little endian number, except that: to 32 bits and is placed in bits 0-31 of the IV. The inode number (which is also limited to 32 bits) is placed in bits 32-63. +- With `IV_INO_LBLK_32 policies`_, the logical block number is limited + to 32 bits and is placed in bits 0-31 of the IV. The inode number + is then hashed and added mod 2^32. + Note that because file logical block numbers are included in the IVs, filesystems must enforce that blocks are never shifted around within encrypted files, e.g. via "collapse range" or "insert range". @@ -465,8 +483,15 @@ This structure must be initialized as follows: (0x3). - FSCRYPT_POLICY_FLAG_DIRECT_KEY: See `DIRECT_KEY policies`_. - FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64: See `IV_INO_LBLK_64 - policies`_. This is mutually exclusive with DIRECT_KEY and is not - supported on v1 policies. + policies`_. + - FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32: See `IV_INO_LBLK_32 + policies`_. + + v1 encryption policies only support the PAD_* and DIRECT_KEY flags. + The other flags are only supported by v2 encryption policies. + + The DIRECT_KEY, IV_INO_LBLK_64, and IV_INO_LBLK_32 flags are + mutually exclusive. - For v2 encryption policies, ``__reserved`` must be zeroed. diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 40c2821a341e..ed015cb66c7c 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -77,8 +77,12 @@ void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, memset(iv, 0, ci->ci_mode->ivsize); if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) { - WARN_ON_ONCE((u32)lblk_num != lblk_num); + WARN_ON_ONCE(lblk_num > U32_MAX); + WARN_ON_ONCE(ci->ci_inode->i_ino > U32_MAX); lblk_num |= (u64)ci->ci_inode->i_ino << 32; + } else if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) { + WARN_ON_ONCE(lblk_num > U32_MAX); + lblk_num = (u32)(ci->ci_hashed_ino + lblk_num); } else if (flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) { memcpy(iv->nonce, ci->ci_nonce, FS_KEY_DERIVATION_NONCE_SIZE); } diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 855ea935f5a6..eb7fcd2b7fb8 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -222,6 +222,9 @@ struct fscrypt_info { /* This inode's nonce, copied from the fscrypt_context */ u8 ci_nonce[FS_KEY_DERIVATION_NONCE_SIZE]; + + /* Hashed inode number. Only set for IV_INO_LBLK_32 */ + u32 ci_hashed_ino; }; typedef enum { @@ -290,6 +293,8 @@ int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key, #define HKDF_CONTEXT_DIRECT_KEY 3 #define HKDF_CONTEXT_IV_INO_LBLK_64_KEY 4 #define HKDF_CONTEXT_DIRHASH_KEY 5 +#define HKDF_CONTEXT_IV_INO_LBLK_32_KEY 6 +#define HKDF_CONTEXT_INODE_HASH_KEY 7 int fscrypt_hkdf_expand(const struct fscrypt_hkdf *hkdf, u8 context, const u8 *info, unsigned int infolen, @@ -386,14 +391,17 @@ struct fscrypt_master_key { struct list_head mk_decrypted_inodes; spinlock_t mk_decrypted_inodes_lock; - /* Crypto API transforms for DIRECT_KEY policies, allocated on-demand */ - struct crypto_skcipher *mk_direct_tfms[__FSCRYPT_MODE_MAX + 1]; - /* - * Crypto API transforms for filesystem-layer implementation of - * IV_INO_LBLK_64 policies, allocated on-demand. + * Per-mode encryption keys for the various types of encryption policies + * that use them. Allocated and derived on-demand. */ - struct crypto_skcipher *mk_iv_ino_lblk_64_tfms[__FSCRYPT_MODE_MAX + 1]; + struct crypto_skcipher *mk_direct_keys[__FSCRYPT_MODE_MAX + 1]; + struct crypto_skcipher *mk_iv_ino_lblk_64_keys[__FSCRYPT_MODE_MAX + 1]; + struct crypto_skcipher *mk_iv_ino_lblk_32_keys[__FSCRYPT_MODE_MAX + 1]; + + /* Hash key for inode numbers. Initialized only when needed. */ + siphash_key_t mk_ino_hash_key; + bool mk_ino_hash_key_initialized; } __randomize_layout; diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index c983ddfde8ad..e24eb48bfbe1 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -45,8 +45,9 @@ static void free_master_key(struct fscrypt_master_key *mk) wipe_master_key_secret(&mk->mk_secret); for (i = 0; i <= __FSCRYPT_MODE_MAX; i++) { - crypto_free_skcipher(mk->mk_direct_tfms[i]); - crypto_free_skcipher(mk->mk_iv_ino_lblk_64_tfms[i]); + crypto_free_skcipher(mk->mk_direct_keys[i]); + crypto_free_skcipher(mk->mk_iv_ino_lblk_64_keys[i]); + crypto_free_skcipher(mk->mk_iv_ino_lblk_32_keys[i]); } key_put(mk->mk_users); diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index 675479f8e6f3..1129adfa097d 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -46,6 +46,8 @@ struct fscrypt_mode fscrypt_modes[] = { }, }; +static DEFINE_MUTEX(fscrypt_mode_key_setup_mutex); + static struct fscrypt_mode * select_encryption_mode(const union fscrypt_policy *policy, const struct inode *inode) @@ -130,7 +132,7 @@ static int setup_per_mode_enc_key(struct fscrypt_info *ci, const struct super_block *sb = inode->i_sb; struct fscrypt_mode *mode = ci->ci_mode; const u8 mode_num = mode - fscrypt_modes; - struct crypto_skcipher *tfm, *prev_tfm; + struct crypto_skcipher *tfm; u8 mode_key[FSCRYPT_MAX_KEY_SIZE]; u8 hkdf_info[sizeof(mode_num) + sizeof(sb->s_uuid)]; unsigned int hkdf_infolen = 0; @@ -139,10 +141,17 @@ static int setup_per_mode_enc_key(struct fscrypt_info *ci, if (WARN_ON(mode_num > __FSCRYPT_MODE_MAX)) return -EINVAL; - /* pairs with cmpxchg() below */ + /* pairs with smp_store_release() below */ tfm = READ_ONCE(tfms[mode_num]); - if (likely(tfm != NULL)) - goto done; + if (likely(tfm != NULL)) { + ci->ci_ctfm = tfm; + return 0; + } + + mutex_lock(&fscrypt_mode_key_setup_mutex); + + if (tfms[mode_num]) + goto done_unlock; BUILD_BUG_ON(sizeof(mode_num) != 1); BUILD_BUG_ON(sizeof(sb->s_uuid) != 16); @@ -157,21 +166,21 @@ static int setup_per_mode_enc_key(struct fscrypt_info *ci, hkdf_context, hkdf_info, hkdf_infolen, mode_key, mode->keysize); if (err) - return err; + goto out_unlock; tfm = fscrypt_allocate_skcipher(mode, mode_key, inode); memzero_explicit(mode_key, mode->keysize); - if (IS_ERR(tfm)) - return PTR_ERR(tfm); - - /* pairs with READ_ONCE() above */ - prev_tfm = cmpxchg(&tfms[mode_num], NULL, tfm); - if (prev_tfm != NULL) { - crypto_free_skcipher(tfm); - tfm = prev_tfm; + if (IS_ERR(tfm)) { + err = PTR_ERR(tfm); + goto out_unlock; } -done: + /* pairs with READ_ONCE() above */ + smp_store_release(&tfms[mode_num], tfm); +done_unlock: ci->ci_ctfm = tfm; - return 0; + err = 0; +out_unlock: + mutex_unlock(&fscrypt_mode_key_setup_mutex); + return err; } int fscrypt_derive_dirhash_key(struct fscrypt_info *ci, @@ -189,6 +198,43 @@ int fscrypt_derive_dirhash_key(struct fscrypt_info *ci, return 0; } +static int fscrypt_setup_iv_ino_lblk_32_key(struct fscrypt_info *ci, + struct fscrypt_master_key *mk) +{ + int err; + + err = setup_per_mode_enc_key(ci, mk, mk->mk_iv_ino_lblk_32_keys, + HKDF_CONTEXT_IV_INO_LBLK_32_KEY, true); + if (err) + return err; + + /* pairs with smp_store_release() below */ + if (!smp_load_acquire(&mk->mk_ino_hash_key_initialized)) { + + mutex_lock(&fscrypt_mode_key_setup_mutex); + + if (mk->mk_ino_hash_key_initialized) + goto unlock; + + err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf, + HKDF_CONTEXT_INODE_HASH_KEY, NULL, 0, + (u8 *)&mk->mk_ino_hash_key, + sizeof(mk->mk_ino_hash_key)); + if (err) + goto unlock; + /* pairs with smp_load_acquire() above */ + smp_store_release(&mk->mk_ino_hash_key_initialized, true); +unlock: + mutex_unlock(&fscrypt_mode_key_setup_mutex); + if (err) + return err; + } + + ci->ci_hashed_ino = (u32)siphash_1u64(ci->ci_inode->i_ino, + &mk->mk_ino_hash_key); + return 0; +} + static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci, struct fscrypt_master_key *mk) { @@ -203,7 +249,7 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci, * encryption key. This ensures that the master key is * consistently used only for HKDF, avoiding key reuse issues. */ - err = setup_per_mode_enc_key(ci, mk, mk->mk_direct_tfms, + err = setup_per_mode_enc_key(ci, mk, mk->mk_direct_keys, HKDF_CONTEXT_DIRECT_KEY, false); } else if (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) { @@ -211,11 +257,14 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci, * IV_INO_LBLK_64: encryption keys are derived from (master_key, * mode_num, filesystem_uuid), and inode number is included in * the IVs. This format is optimized for use with inline - * encryption hardware compliant with the UFS or eMMC standards. + * encryption hardware compliant with the UFS standard. */ - err = setup_per_mode_enc_key(ci, mk, mk->mk_iv_ino_lblk_64_tfms, + err = setup_per_mode_enc_key(ci, mk, mk->mk_iv_ino_lblk_64_keys, HKDF_CONTEXT_IV_INO_LBLK_64_KEY, true); + } else if (ci->ci_policy.v2.flags & + FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) { + err = fscrypt_setup_iv_ino_lblk_32_key(ci, mk); } else { u8 derived_key[FSCRYPT_MAX_KEY_SIZE]; diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index a15aec8e068c..d23ff162c78b 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -69,18 +69,14 @@ static bool supported_direct_key_modes(const struct inode *inode, return true; } -static bool supported_iv_ino_lblk_64_policy( - const struct fscrypt_policy_v2 *policy, - const struct inode *inode) +static bool supported_iv_ino_lblk_policy(const struct fscrypt_policy_v2 *policy, + const struct inode *inode, + const char *type, + int max_ino_bits, int max_lblk_bits) { struct super_block *sb = inode->i_sb; int ino_bits = 64, lblk_bits = 64; - if (policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) { - fscrypt_warn(inode, - "The DIRECT_KEY and IV_INO_LBLK_64 flags are mutually exclusive"); - return false; - } /* * It's unsafe to include inode numbers in the IVs if the filesystem can * potentially renumber inodes, e.g. via filesystem shrinking. @@ -88,16 +84,22 @@ static bool supported_iv_ino_lblk_64_policy( if (!sb->s_cop->has_stable_inodes || !sb->s_cop->has_stable_inodes(sb)) { fscrypt_warn(inode, - "Can't use IV_INO_LBLK_64 policy on filesystem '%s' because it doesn't have stable inode numbers", - sb->s_id); + "Can't use %s policy on filesystem '%s' because it doesn't have stable inode numbers", + type, sb->s_id); return false; } if (sb->s_cop->get_ino_and_lblk_bits) sb->s_cop->get_ino_and_lblk_bits(sb, &ino_bits, &lblk_bits); - if (ino_bits > 32 || lblk_bits > 32) { + if (ino_bits > max_ino_bits) { + fscrypt_warn(inode, + "Can't use %s policy on filesystem '%s' because its inode numbers are too long", + type, sb->s_id); + return false; + } + if (lblk_bits > max_lblk_bits) { fscrypt_warn(inode, - "Can't use IV_INO_LBLK_64 policy on filesystem '%s' because it doesn't use 32-bit inode and block numbers", - sb->s_id); + "Can't use %s policy on filesystem '%s' because its block numbers are too long", + type, sb->s_id); return false; } return true; @@ -140,6 +142,8 @@ static bool fscrypt_supported_v1_policy(const struct fscrypt_policy_v1 *policy, static bool fscrypt_supported_v2_policy(const struct fscrypt_policy_v2 *policy, const struct inode *inode) { + int count = 0; + if (!fscrypt_valid_enc_modes(policy->contents_encryption_mode, policy->filenames_encryption_mode)) { fscrypt_warn(inode, @@ -155,13 +159,29 @@ static bool fscrypt_supported_v2_policy(const struct fscrypt_policy_v2 *policy, return false; } + count += !!(policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY); + count += !!(policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64); + count += !!(policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32); + if (count > 1) { + fscrypt_warn(inode, "Mutually exclusive encryption flags (0x%02x)", + policy->flags); + return false; + } + if ((policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) && !supported_direct_key_modes(inode, policy->contents_encryption_mode, policy->filenames_encryption_mode)) return false; if ((policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) && - !supported_iv_ino_lblk_64_policy(policy, inode)) + !supported_iv_ino_lblk_policy(policy, inode, "IV_INO_LBLK_64", + 32, 32)) + return false; + + if ((policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) && + /* This uses hashed inode numbers, so ino_bits doesn't matter. */ + !supported_iv_ino_lblk_policy(policy, inode, "IV_INO_LBLK_32", + INT_MAX, 32)) return false; if (memchr_inv(policy->__reserved, 0, sizeof(policy->__reserved))) { @@ -366,6 +386,9 @@ static int set_encryption_policy(struct inode *inode, policy->v2.master_key_identifier); if (err) return err; + if (policy->v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) + pr_warn_once("%s (pid %d) is setting an IV_INO_LBLK_32 encryption policy. This should only be used if there are certain hardware limitations.\n", + current->comm, current->pid); break; default: WARN_ON(1); diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h index a10e3cdc2839..7875709ccfeb 100644 --- a/include/uapi/linux/fscrypt.h +++ b/include/uapi/linux/fscrypt.h @@ -19,7 +19,8 @@ #define FSCRYPT_POLICY_FLAGS_PAD_MASK 0x03 #define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04 #define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 0x08 -#define FSCRYPT_POLICY_FLAGS_VALID 0x0F +#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32 0x10 +#define FSCRYPT_POLICY_FLAGS_VALID 0x1F /* Encryption algorithms */ #define FSCRYPT_MODE_AES_256_XTS 1 -- cgit v1.2.3 From 1b66d253610c7f8f257103808a9460223a087469 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 19 May 2020 00:45:45 +0200 Subject: bpf: Add get{peer, sock}name attach types for sock_addr As stated in 983695fa6765 ("bpf: fix unconnected udp hooks"), the objective for the existing cgroup connect/sendmsg/recvmsg/bind BPF hooks is to be transparent to applications. In Cilium we make use of these hooks [0] in order to enable E-W load balancing for existing Kubernetes service types for all Cilium managed nodes in the cluster. Those backends can be local or remote. The main advantage of this approach is that it operates as close as possible to the socket, and therefore allows to avoid packet-based NAT given in connect/sendmsg/recvmsg hooks we only need to xlate sock addresses. This also allows to expose NodePort services on loopback addresses in the host namespace, for example. As another advantage, this also efficiently blocks bind requests for applications in the host namespace for exposed ports. However, one missing item is that we also need to perform reverse xlation for inet{,6}_getname() hooks such that we can return the service IP/port tuple back to the application instead of the remote peer address. The vast majority of applications does not bother about getpeername(), but in a few occasions we've seen breakage when validating the peer's address since it returns unexpectedly the backend tuple instead of the service one. Therefore, this trivial patch allows to customise and adds a getpeername() as well as getsockname() BPF cgroup hook for both IPv4 and IPv6 in order to address this situation. Simple example: # ./cilium/cilium service list ID Frontend Service Type Backend 1 1.2.3.4:80 ClusterIP 1 => 10.0.0.10:80 Before; curl's verbose output example, no getpeername() reverse xlation: # curl --verbose 1.2.3.4 * Rebuilt URL to: 1.2.3.4/ * Trying 1.2.3.4... * TCP_NODELAY set * Connected to 1.2.3.4 (10.0.0.10) port 80 (#0) > GET / HTTP/1.1 > Host: 1.2.3.4 > User-Agent: curl/7.58.0 > Accept: */* [...] After; with getpeername() reverse xlation: # curl --verbose 1.2.3.4 * Rebuilt URL to: 1.2.3.4/ * Trying 1.2.3.4... * TCP_NODELAY set * Connected to 1.2.3.4 (1.2.3.4) port 80 (#0) > GET / HTTP/1.1 > Host: 1.2.3.4 > User-Agent: curl/7.58.0 > Accept: */* [...] Originally, I had both under a BPF_CGROUP_INET{4,6}_GETNAME type and exposed peer to the context similar as in inet{,6}_getname() fashion, but API-wise this is suboptimal as it always enforces programs having to test for ctx->peer which can easily be missed, hence BPF_CGROUP_INET{4,6}_GET{PEER,SOCK}NAME split. Similarly, the checked return code is on tnum_range(1, 1), but if a use case comes up in future, it can easily be changed to return an error code instead. Helper and ctx member access is the same as with connect/sendmsg/etc hooks. [0] https://github.com/cilium/cilium/blob/master/bpf/bpf_sock.c Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Andrey Ignatov Link: https://lore.kernel.org/bpf/61a479d759b2482ae3efb45546490bacd796a220.1589841594.git.daniel@iogearbox.net --- include/linux/bpf-cgroup.h | 1 + include/uapi/linux/bpf.h | 4 ++++ kernel/bpf/syscall.c | 12 ++++++++++++ kernel/bpf/verifier.c | 6 +++++- net/core/filter.c | 4 ++++ net/ipv4/af_inet.c | 8 ++++++-- net/ipv6/af_inet6.c | 9 ++++++--- tools/include/uapi/linux/bpf.h | 4 ++++ 8 files changed, 42 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 272626cc3fc9..c66c545e161a 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -396,6 +396,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, } #define cgroup_bpf_enabled (0) +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) ({ 0; }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b9b8a0f63b91..97e1fd19ff58 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -220,6 +220,10 @@ enum bpf_attach_type { BPF_MODIFY_RETURN, BPF_LSM_MAC, BPF_TRACE_ITER, + BPF_CGROUP_INET4_GETPEERNAME, + BPF_CGROUP_INET6_GETPEERNAME, + BPF_CGROUP_INET4_GETSOCKNAME, + BPF_CGROUP_INET6_GETSOCKNAME, __MAX_BPF_ATTACH_TYPE }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 57dfc98289d5..431241c74614 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1978,6 +1978,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_INET4_GETPEERNAME: + case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_INET4_GETSOCKNAME: + case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: @@ -2767,6 +2771,10 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_INET4_GETPEERNAME: + case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_INET4_GETSOCKNAME: + case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: @@ -2912,6 +2920,10 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_INET6_POST_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_INET4_GETPEERNAME: + case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_INET4_GETSOCKNAME: + case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9c7d67d65d8c..2ed8351f47a4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7094,7 +7094,11 @@ static int check_return_code(struct bpf_verifier_env *env) switch (env->prog->type) { case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || - env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG) + env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG || + env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME || + env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME || + env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME || + env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME) range = tnum_range(1, 1); break; case BPF_PROG_TYPE_CGROUP_SKB: diff --git a/net/core/filter.c b/net/core/filter.c index 822d662f97ef..bd2853d23b50 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7049,6 +7049,8 @@ static bool sock_addr_is_valid_access(int off, int size, switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET4_CONNECT: + case BPF_CGROUP_INET4_GETPEERNAME: + case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: break; @@ -7060,6 +7062,8 @@ static bool sock_addr_is_valid_access(int off, int size, switch (prog->expected_attach_type) { case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP6_RECVMSG: break; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index fcf0d12a407a..8f5c8c9409d3 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -755,12 +755,11 @@ do_err: } EXPORT_SYMBOL(inet_accept); - /* * This does both peername and sockname. */ int inet_getname(struct socket *sock, struct sockaddr *uaddr, - int peer) + int peer) { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); @@ -781,6 +780,11 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; } + if (cgroup_bpf_enabled) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, + peer ? BPF_CGROUP_INET4_GETPEERNAME : + BPF_CGROUP_INET4_GETSOCKNAME, + NULL); memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); return sizeof(*sin); } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 771a462a8322..3b6fcc0c321a 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -504,9 +504,8 @@ EXPORT_SYMBOL_GPL(inet6_destroy_sock); /* * This does both peername and sockname. */ - int inet6_getname(struct socket *sock, struct sockaddr *uaddr, - int peer) + int peer) { struct sockaddr_in6 *sin = (struct sockaddr_in6 *)uaddr; struct sock *sk = sock->sk; @@ -531,9 +530,13 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin6_addr = np->saddr; else sin->sin6_addr = sk->sk_v6_rcv_saddr; - sin->sin6_port = inet->inet_sport; } + if (cgroup_bpf_enabled) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, + peer ? BPF_CGROUP_INET6_GETPEERNAME : + BPF_CGROUP_INET6_GETSOCKNAME, + NULL); sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, sk->sk_bound_dev_if); return sizeof(*sin); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 146c742f1d49..1cddc398404a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -220,6 +220,10 @@ enum bpf_attach_type { BPF_MODIFY_RETURN, BPF_LSM_MAC, BPF_TRACE_ITER, + BPF_CGROUP_INET4_GETPEERNAME, + BPF_CGROUP_INET6_GETPEERNAME, + BPF_CGROUP_INET4_GETSOCKNAME, + BPF_CGROUP_INET6_GETSOCKNAME, __MAX_BPF_ATTACH_TYPE }; -- cgit v1.2.3 From faf1d25440d6ad06d509dada4b6fe62fea844370 Mon Sep 17 00:00:00 2001 From: Martijn Coenen Date: Wed, 13 May 2020 15:38:44 +0200 Subject: loop: Clean up LOOP_SET_STATUS lo_flags handling LOOP_SET_STATUS(64) will actually allow some lo_flags to be modified; in particular, LO_FLAGS_AUTOCLEAR can be set and cleared, whereas LO_FLAGS_PARTSCAN can be set to request a partition scan. Make this explicit by updating the UAPI to include the flags that can be set/cleared using this ioctl. The implementation can then blindly take over the passed in flags, and use the previous flags for those flags that can't be set / cleared using LOOP_SET_STATUS. Signed-off-by: Martijn Coenen Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/block/loop.c | 19 +++++++++++++------ include/uapi/linux/loop.h | 10 ++++++++-- 2 files changed, 21 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 31f10da4945e..13518ba191f5 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1036,9 +1036,7 @@ loop_set_status_from_info(struct loop_device *lo, lo->transfer = xfer->transfer; lo->ioctl = xfer->ioctl; - if ((lo->lo_flags & LO_FLAGS_AUTOCLEAR) != - (info->lo_flags & LO_FLAGS_AUTOCLEAR)) - lo->lo_flags ^= LO_FLAGS_AUTOCLEAR; + lo->lo_flags = info->lo_flags; lo->lo_encrypt_key_size = info->lo_encrypt_key_size; lo->lo_init[0] = info->lo_init[0]; @@ -1323,6 +1321,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) int err; struct block_device *bdev; kuid_t uid = current_uid(); + int prev_lo_flags; bool partscan = false; bool size_changed = false; @@ -1359,10 +1358,19 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) goto out_unfreeze; } + prev_lo_flags = lo->lo_flags; + err = loop_set_status_from_info(lo, info); if (err) goto out_unfreeze; + /* Mask out flags that can't be set using LOOP_SET_STATUS. */ + lo->lo_flags &= ~LOOP_SET_STATUS_SETTABLE_FLAGS; + /* For those flags, use the previous values instead */ + lo->lo_flags |= prev_lo_flags & ~LOOP_SET_STATUS_SETTABLE_FLAGS; + /* For flags that can't be cleared, use previous values too */ + lo->lo_flags |= prev_lo_flags & ~LOOP_SET_STATUS_CLEARABLE_FLAGS; + if (size_changed) { loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit, lo->lo_backing_file); @@ -1377,9 +1385,8 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) out_unfreeze: blk_mq_unfreeze_queue(lo->lo_queue); - if (!err && (info->lo_flags & LO_FLAGS_PARTSCAN) && - !(lo->lo_flags & LO_FLAGS_PARTSCAN)) { - lo->lo_flags |= LO_FLAGS_PARTSCAN; + if (!err && (lo->lo_flags & LO_FLAGS_PARTSCAN) && + !(prev_lo_flags & LO_FLAGS_PARTSCAN)) { lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN; bdev = lo->lo_device; partscan = true; diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index 080a8df134ef..6b32fee80ce0 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -25,6 +25,12 @@ enum { LO_FLAGS_DIRECT_IO = 16, }; +/* LO_FLAGS that can be set using LOOP_SET_STATUS(64) */ +#define LOOP_SET_STATUS_SETTABLE_FLAGS (LO_FLAGS_AUTOCLEAR | LO_FLAGS_PARTSCAN) + +/* LO_FLAGS that can be cleared using LOOP_SET_STATUS(64) */ +#define LOOP_SET_STATUS_CLEARABLE_FLAGS (LO_FLAGS_AUTOCLEAR) + #include /* for __kernel_old_dev_t */ #include /* for __u64 */ @@ -37,7 +43,7 @@ struct loop_info { int lo_offset; int lo_encrypt_type; int lo_encrypt_key_size; /* ioctl w/o */ - int lo_flags; /* ioctl r/o */ + int lo_flags; char lo_name[LO_NAME_SIZE]; unsigned char lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */ unsigned long lo_init[2]; @@ -53,7 +59,7 @@ struct loop_info64 { __u32 lo_number; /* ioctl r/o */ __u32 lo_encrypt_type; __u32 lo_encrypt_key_size; /* ioctl w/o */ - __u32 lo_flags; /* ioctl r/o */ + __u32 lo_flags; __u8 lo_file_name[LO_NAME_SIZE]; __u8 lo_crypt_name[LO_NAME_SIZE]; __u8 lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */ -- cgit v1.2.3 From 3448914e8cc550ba792d4ccc74471d1ca4293aae Mon Sep 17 00:00:00 2001 From: Martijn Coenen Date: Wed, 13 May 2020 15:38:45 +0200 Subject: loop: Add LOOP_CONFIGURE ioctl This allows userspace to completely setup a loop device with a single ioctl, removing the in-between state where the device can be partially configured - eg the loop device has a backing file associated with it, but is reading from the wrong offset. Besides removing the intermediate state, another big benefit of this ioctl is that LOOP_SET_STATUS can be slow; the main reason for this slowness is that LOOP_SET_STATUS(64) calls blk_mq_freeze_queue() to freeze the associated queue; this requires waiting for RCU synchronization, which I've measured can take about 15-20ms on this device on average. In addition to doing what LOOP_SET_STATUS can do, LOOP_CONFIGURE can also be used to: - Set the correct block size immediately by setting loop_config.block_size (avoids LOOP_SET_BLOCK_SIZE) - Explicitly request direct I/O mode by setting LO_FLAGS_DIRECT_IO in loop_config.info.lo_flags (avoids LOOP_SET_DIRECT_IO) - Explicitly request read-only mode by setting LO_FLAGS_READ_ONLY in loop_config.info.lo_flags Here's setting up ~70 regular loop devices with an offset on an x86 Android device, using LOOP_SET_FD and LOOP_SET_STATUS: vsoc_x86:/system/apex # time for i in `seq 30 100`; do losetup -r -o 4096 /dev/block/loop$i com.android.adbd.apex; done 0m03.40s real 0m00.02s user 0m00.03s system Here's configuring ~70 devices in the same way, but using a modified losetup that uses the new LOOP_CONFIGURE ioctl: vsoc_x86:/system/apex # time for i in `seq 30 100`; do losetup -r -o 4096 /dev/block/loop$i com.android.adbd.apex; done 0m01.94s real 0m00.01s user 0m00.01s system Signed-off-by: Martijn Coenen Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/block/loop.c | 104 +++++++++++++++++++++++++++++++++------------- include/uapi/linux/loop.h | 21 ++++++++++ 2 files changed, 97 insertions(+), 28 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 13518ba191f5..a565c5aafa52 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -228,6 +228,19 @@ static void __loop_update_dio(struct loop_device *lo, bool dio) blk_mq_unfreeze_queue(lo->lo_queue); } +/** + * loop_validate_block_size() - validates the passed in block size + * @bsize: size to validate + */ +static int +loop_validate_block_size(unsigned short bsize) +{ + if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) + return -EINVAL; + + return 0; +} + /** * loop_set_size() - sets device size and notifies userspace * @lo: struct loop_device to set the size for @@ -1050,23 +1063,24 @@ loop_set_status_from_info(struct loop_device *lo, return 0; } -static int loop_set_fd(struct loop_device *lo, fmode_t mode, - struct block_device *bdev, unsigned int arg) +static int loop_configure(struct loop_device *lo, fmode_t mode, + struct block_device *bdev, + const struct loop_config *config) { struct file *file; struct inode *inode; struct address_space *mapping; struct block_device *claimed_bdev = NULL; - int lo_flags = 0; int error; loff_t size; bool partscan; + unsigned short bsize; /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); error = -EBADF; - file = fget(arg); + file = fget(config->fd); if (!file) goto out; @@ -1075,7 +1089,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, * here to avoid changing device under exclusive owner. */ if (!(mode & FMODE_EXCL)) { - claimed_bdev = bd_start_claiming(bdev, loop_set_fd); + claimed_bdev = bd_start_claiming(bdev, loop_configure); if (IS_ERR(claimed_bdev)) { error = PTR_ERR(claimed_bdev); goto out_putf; @@ -1097,11 +1111,26 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, mapping = file->f_mapping; inode = mapping->host; + size = get_loop_size(lo, file); + + if ((config->info.lo_flags & ~LOOP_CONFIGURE_SETTABLE_FLAGS) != 0) { + error = -EINVAL; + goto out_unlock; + } + + if (config->block_size) { + error = loop_validate_block_size(config->block_size); + if (error) + goto out_unlock; + } + + error = loop_set_status_from_info(lo, &config->info); + if (error) + goto out_unlock; + if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) || !file->f_op->write_iter) - lo_flags |= LO_FLAGS_READ_ONLY; - - size = get_loop_size(lo, file); + lo->lo_flags |= LO_FLAGS_READ_ONLY; error = loop_prepare_queue(lo); if (error) @@ -1109,30 +1138,28 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, error = 0; - set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0); + set_device_ro(bdev, (lo->lo_flags & LO_FLAGS_READ_ONLY) != 0); - lo->use_dio = false; + lo->use_dio = lo->lo_flags & LO_FLAGS_DIRECT_IO; lo->lo_device = bdev; - lo->lo_flags = lo_flags; lo->lo_backing_file = file; - lo->transfer = NULL; - lo->ioctl = NULL; - lo->lo_sizelimit = 0; lo->old_gfp_mask = mapping_gfp_mask(mapping); mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); - if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) + if (!(lo->lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) blk_queue_write_cache(lo->lo_queue, true, false); - if (io_is_direct(lo->lo_backing_file) && inode->i_sb->s_bdev) { + if (config->block_size) + bsize = config->block_size; + else if (io_is_direct(lo->lo_backing_file) && inode->i_sb->s_bdev) /* In case of direct I/O, match underlying block size */ - unsigned short bsize = bdev_logical_block_size( - inode->i_sb->s_bdev); + bsize = bdev_logical_block_size(inode->i_sb->s_bdev); + else + bsize = 512; - blk_queue_logical_block_size(lo->lo_queue, bsize); - blk_queue_physical_block_size(lo->lo_queue, bsize); - blk_queue_io_min(lo->lo_queue, bsize); - } + blk_queue_logical_block_size(lo->lo_queue, bsize); + blk_queue_physical_block_size(lo->lo_queue, bsize); + blk_queue_io_min(lo->lo_queue, bsize); loop_update_rotational(lo); loop_update_dio(lo); @@ -1155,14 +1182,14 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, if (partscan) loop_reread_partitions(lo, bdev); if (claimed_bdev) - bd_abort_claiming(bdev, claimed_bdev, loop_set_fd); + bd_abort_claiming(bdev, claimed_bdev, loop_configure); return 0; out_unlock: mutex_unlock(&loop_ctl_mutex); out_bdev: if (claimed_bdev) - bd_abort_claiming(bdev, claimed_bdev, loop_set_fd); + bd_abort_claiming(bdev, claimed_bdev, loop_configure); out_putf: fput(file); out: @@ -1582,8 +1609,9 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg) if (lo->lo_state != Lo_bound) return -ENXIO; - if (arg < 512 || arg > PAGE_SIZE || !is_power_of_2(arg)) - return -EINVAL; + err = loop_validate_block_size(arg); + if (err) + return err; if (lo->lo_queue->limits.logical_block_size == arg) return 0; @@ -1645,8 +1673,27 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, int err; switch (cmd) { - case LOOP_SET_FD: - return loop_set_fd(lo, mode, bdev, arg); + case LOOP_SET_FD: { + /* + * Legacy case - pass in a zeroed out struct loop_config with + * only the file descriptor set , which corresponds with the + * default parameters we'd have used otherwise. + */ + struct loop_config config; + + memset(&config, 0, sizeof(config)); + config.fd = arg; + + return loop_configure(lo, mode, bdev, &config); + } + case LOOP_CONFIGURE: { + struct loop_config config; + + if (copy_from_user(&config, argp, sizeof(config))) + return -EFAULT; + + return loop_configure(lo, mode, bdev, &config); + } case LOOP_CHANGE_FD: return loop_change_fd(lo, bdev, arg); case LOOP_CLR_FD: @@ -1818,6 +1865,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, case LOOP_CLR_FD: case LOOP_GET_STATUS64: case LOOP_SET_STATUS64: + case LOOP_CONFIGURE: arg = (unsigned long) compat_ptr(arg); /* fall through */ case LOOP_SET_FD: diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index 6b32fee80ce0..24a1c45bd1ae 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -31,6 +31,10 @@ enum { /* LO_FLAGS that can be cleared using LOOP_SET_STATUS(64) */ #define LOOP_SET_STATUS_CLEARABLE_FLAGS (LO_FLAGS_AUTOCLEAR) +/* LO_FLAGS that can be set using LOOP_CONFIGURE */ +#define LOOP_CONFIGURE_SETTABLE_FLAGS (LO_FLAGS_READ_ONLY | LO_FLAGS_AUTOCLEAR \ + | LO_FLAGS_PARTSCAN | LO_FLAGS_DIRECT_IO) + #include /* for __kernel_old_dev_t */ #include /* for __u64 */ @@ -66,6 +70,22 @@ struct loop_info64 { __u64 lo_init[2]; }; +/** + * struct loop_config - Complete configuration for a loop device. + * @fd: fd of the file to be used as a backing file for the loop device. + * @block_size: block size to use; ignored if 0. + * @info: struct loop_info64 to configure the loop device with. + * + * This structure is used with the LOOP_CONFIGURE ioctl, and can be used to + * atomically setup and configure all loop device parameters at once. + */ +struct loop_config { + __u32 fd; + __u32 block_size; + struct loop_info64 info; + __u64 __reserved[8]; +}; + /* * Loop filter types */ @@ -96,6 +116,7 @@ struct loop_info64 { #define LOOP_SET_CAPACITY 0x4C07 #define LOOP_SET_DIRECT_IO 0x4C08 #define LOOP_SET_BLOCK_SIZE 0x4C09 +#define LOOP_CONFIGURE 0x4C0A /* /dev/loop-control interface */ #define LOOP_CTL_ADD 0x4C80 -- cgit v1.2.3 From d8bed686ab96169ac80b497d1cbed89300d97f83 Mon Sep 17 00:00:00 2001 From: Chris Mi Date: Tue, 19 May 2020 22:45:20 +0800 Subject: net: psample: Add tunnel support Currently, psample can only send the packet bits after decapsulation. The tunnel information is lost. Add the tunnel support. If the sampled packet has no tunnel info, the behavior is the same as before. If it has, add a nested metadata field named PSAMPLE_ATTR_TUNNEL and include the tunnel subfields if applicable. Increase the metadata length for sampled packet with the tunnel info. If new subfields of tunnel info should be included, update the metadata length accordingly. Signed-off-by: Chris Mi Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/psample.h | 22 ++++++ net/psample/psample.c | 157 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 179 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h index ce1116cff53d..aea26ab1431c 100644 --- a/include/uapi/linux/psample.h +++ b/include/uapi/linux/psample.h @@ -11,6 +11,7 @@ enum { PSAMPLE_ATTR_GROUP_SEQ, PSAMPLE_ATTR_SAMPLE_RATE, PSAMPLE_ATTR_DATA, + PSAMPLE_ATTR_TUNNEL, /* commands attributes */ PSAMPLE_ATTR_GROUP_REFCOUNT, @@ -25,6 +26,27 @@ enum psample_command { PSAMPLE_CMD_DEL_GROUP, }; +enum psample_tunnel_key_attr { + PSAMPLE_TUNNEL_KEY_ATTR_ID, /* be64 Tunnel ID */ + PSAMPLE_TUNNEL_KEY_ATTR_IPV4_SRC, /* be32 src IP address. */ + PSAMPLE_TUNNEL_KEY_ATTR_IPV4_DST, /* be32 dst IP address. */ + PSAMPLE_TUNNEL_KEY_ATTR_TOS, /* u8 Tunnel IP ToS. */ + PSAMPLE_TUNNEL_KEY_ATTR_TTL, /* u8 Tunnel IP TTL. */ + PSAMPLE_TUNNEL_KEY_ATTR_DONT_FRAGMENT, /* No argument, set DF. */ + PSAMPLE_TUNNEL_KEY_ATTR_CSUM, /* No argument. CSUM packet. */ + PSAMPLE_TUNNEL_KEY_ATTR_OAM, /* No argument. OAM frame. */ + PSAMPLE_TUNNEL_KEY_ATTR_GENEVE_OPTS, /* Array of Geneve options. */ + PSAMPLE_TUNNEL_KEY_ATTR_TP_SRC, /* be16 src Transport Port. */ + PSAMPLE_TUNNEL_KEY_ATTR_TP_DST, /* be16 dst Transport Port. */ + PSAMPLE_TUNNEL_KEY_ATTR_VXLAN_OPTS, /* Nested VXLAN opts* */ + PSAMPLE_TUNNEL_KEY_ATTR_IPV6_SRC, /* struct in6_addr src IPv6 address. */ + PSAMPLE_TUNNEL_KEY_ATTR_IPV6_DST, /* struct in6_addr dst IPv6 address. */ + PSAMPLE_TUNNEL_KEY_ATTR_PAD, + PSAMPLE_TUNNEL_KEY_ATTR_ERSPAN_OPTS, /* struct erspan_metadata */ + PSAMPLE_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE, /* No argument. IPV4_INFO_BRIDGE mode.*/ + __PSAMPLE_TUNNEL_KEY_ATTR_MAX +}; + /* Can be overridden at runtime by module option */ #define PSAMPLE_ATTR_MAX (__PSAMPLE_ATTR_MAX - 1) diff --git a/net/psample/psample.c b/net/psample/psample.c index 6f2fbc6b9eb2..34a74043840b 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -14,6 +14,8 @@ #include #include #include +#include +#include #define PSAMPLE_MAX_PACKET_SIZE 0xffff @@ -207,10 +209,155 @@ void psample_group_put(struct psample_group *group) } EXPORT_SYMBOL_GPL(psample_group_put); +static int __psample_ip_tun_to_nlattr(struct sk_buff *skb, + struct ip_tunnel_info *tun_info) +{ + unsigned short tun_proto = ip_tunnel_info_af(tun_info); + const void *tun_opts = ip_tunnel_info_opts(tun_info); + const struct ip_tunnel_key *tun_key = &tun_info->key; + int tun_opts_len = tun_info->options_len; + + if (tun_key->tun_flags & TUNNEL_KEY && + nla_put_be64(skb, PSAMPLE_TUNNEL_KEY_ATTR_ID, tun_key->tun_id, + PSAMPLE_TUNNEL_KEY_ATTR_PAD)) + return -EMSGSIZE; + + if (tun_info->mode & IP_TUNNEL_INFO_BRIDGE && + nla_put_flag(skb, PSAMPLE_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE)) + return -EMSGSIZE; + + switch (tun_proto) { + case AF_INET: + if (tun_key->u.ipv4.src && + nla_put_in_addr(skb, PSAMPLE_TUNNEL_KEY_ATTR_IPV4_SRC, + tun_key->u.ipv4.src)) + return -EMSGSIZE; + if (tun_key->u.ipv4.dst && + nla_put_in_addr(skb, PSAMPLE_TUNNEL_KEY_ATTR_IPV4_DST, + tun_key->u.ipv4.dst)) + return -EMSGSIZE; + break; + case AF_INET6: + if (!ipv6_addr_any(&tun_key->u.ipv6.src) && + nla_put_in6_addr(skb, PSAMPLE_TUNNEL_KEY_ATTR_IPV6_SRC, + &tun_key->u.ipv6.src)) + return -EMSGSIZE; + if (!ipv6_addr_any(&tun_key->u.ipv6.dst) && + nla_put_in6_addr(skb, PSAMPLE_TUNNEL_KEY_ATTR_IPV6_DST, + &tun_key->u.ipv6.dst)) + return -EMSGSIZE; + break; + } + if (tun_key->tos && + nla_put_u8(skb, PSAMPLE_TUNNEL_KEY_ATTR_TOS, tun_key->tos)) + return -EMSGSIZE; + if (nla_put_u8(skb, PSAMPLE_TUNNEL_KEY_ATTR_TTL, tun_key->ttl)) + return -EMSGSIZE; + if ((tun_key->tun_flags & TUNNEL_DONT_FRAGMENT) && + nla_put_flag(skb, PSAMPLE_TUNNEL_KEY_ATTR_DONT_FRAGMENT)) + return -EMSGSIZE; + if ((tun_key->tun_flags & TUNNEL_CSUM) && + nla_put_flag(skb, PSAMPLE_TUNNEL_KEY_ATTR_CSUM)) + return -EMSGSIZE; + if (tun_key->tp_src && + nla_put_be16(skb, PSAMPLE_TUNNEL_KEY_ATTR_TP_SRC, tun_key->tp_src)) + return -EMSGSIZE; + if (tun_key->tp_dst && + nla_put_be16(skb, PSAMPLE_TUNNEL_KEY_ATTR_TP_DST, tun_key->tp_dst)) + return -EMSGSIZE; + if ((tun_key->tun_flags & TUNNEL_OAM) && + nla_put_flag(skb, PSAMPLE_TUNNEL_KEY_ATTR_OAM)) + return -EMSGSIZE; + if (tun_opts_len) { + if (tun_key->tun_flags & TUNNEL_GENEVE_OPT && + nla_put(skb, PSAMPLE_TUNNEL_KEY_ATTR_GENEVE_OPTS, + tun_opts_len, tun_opts)) + return -EMSGSIZE; + else if (tun_key->tun_flags & TUNNEL_ERSPAN_OPT && + nla_put(skb, PSAMPLE_TUNNEL_KEY_ATTR_ERSPAN_OPTS, + tun_opts_len, tun_opts)) + return -EMSGSIZE; + } + + return 0; +} + +static int psample_ip_tun_to_nlattr(struct sk_buff *skb, + struct ip_tunnel_info *tun_info) +{ + struct nlattr *nla; + int err; + + nla = nla_nest_start_noflag(skb, PSAMPLE_ATTR_TUNNEL); + if (!nla) + return -EMSGSIZE; + + err = __psample_ip_tun_to_nlattr(skb, tun_info); + if (err) { + nla_nest_cancel(skb, nla); + return err; + } + + nla_nest_end(skb, nla); + + return 0; +} + +static int psample_tunnel_meta_len(struct ip_tunnel_info *tun_info) +{ + unsigned short tun_proto = ip_tunnel_info_af(tun_info); + const struct ip_tunnel_key *tun_key = &tun_info->key; + int tun_opts_len = tun_info->options_len; + int sum = 0; + + if (tun_key->tun_flags & TUNNEL_KEY) + sum += nla_total_size(sizeof(u64)); + + if (tun_info->mode & IP_TUNNEL_INFO_BRIDGE) + sum += nla_total_size(0); + + switch (tun_proto) { + case AF_INET: + if (tun_key->u.ipv4.src) + sum += nla_total_size(sizeof(u32)); + if (tun_key->u.ipv4.dst) + sum += nla_total_size(sizeof(u32)); + break; + case AF_INET6: + if (!ipv6_addr_any(&tun_key->u.ipv6.src)) + sum += nla_total_size(sizeof(struct in6_addr)); + if (!ipv6_addr_any(&tun_key->u.ipv6.dst)) + sum += nla_total_size(sizeof(struct in6_addr)); + break; + } + if (tun_key->tos) + sum += nla_total_size(sizeof(u8)); + sum += nla_total_size(sizeof(u8)); /* TTL */ + if (tun_key->tun_flags & TUNNEL_DONT_FRAGMENT) + sum += nla_total_size(0); + if (tun_key->tun_flags & TUNNEL_CSUM) + sum += nla_total_size(0); + if (tun_key->tp_src) + sum += nla_total_size(sizeof(u16)); + if (tun_key->tp_dst) + sum += nla_total_size(sizeof(u16)); + if (tun_key->tun_flags & TUNNEL_OAM) + sum += nla_total_size(0); + if (tun_opts_len) { + if (tun_key->tun_flags & TUNNEL_GENEVE_OPT) + sum += nla_total_size(tun_opts_len); + else if (tun_key->tun_flags & TUNNEL_ERSPAN_OPT) + sum += nla_total_size(tun_opts_len); + } + + return sum; +} + void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, u32 trunc_size, int in_ifindex, int out_ifindex, u32 sample_rate) { + struct ip_tunnel_info *tun_info; struct sk_buff *nl_skb; int data_len; int meta_len; @@ -224,6 +371,10 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, nla_total_size(sizeof(u32)) + /* group_num */ nla_total_size(sizeof(u32)); /* seq */ + tun_info = skb_tunnel_info(skb); + if (tun_info) + meta_len += psample_tunnel_meta_len(tun_info); + data_len = min(skb->len, trunc_size); if (meta_len + nla_total_size(data_len) > PSAMPLE_MAX_PACKET_SIZE) data_len = PSAMPLE_MAX_PACKET_SIZE - meta_len - NLA_HDRLEN @@ -278,6 +429,12 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, goto error; } + if (tun_info) { + ret = psample_ip_tun_to_nlattr(nl_skb, tun_info); + if (unlikely(ret < 0)) + goto error; + } + genlmsg_end(nl_skb, data); genlmsg_multicast_netns(&psample_nl_family, group->net, nl_skb, 0, PSAMPLE_NL_MCGRP_SAMPLE, GFP_ATOMIC); -- cgit v1.2.3 From 8066021915924f58ed338bf38208215f5a7355f6 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Wed, 20 May 2020 08:29:14 +0200 Subject: ethtool: provide UAPI for PHY Signal Quality Index (SQI) Signal Quality Index is a mandatory value required by "OPEN Alliance SIG" for the 100Base-T1 PHYs [1]. This indicator can be used for cable integrity diagnostic and investigating other noise sources and implement by at least two vendors: NXP[2] and TI[3]. [1] http://www.opensig.org/download/document/218/Advanced_PHY_features_for_automotive_Ethernet_V1.0.pdf [2] https://www.nxp.com/docs/en/data-sheet/TJA1100.pdf [3] https://www.ti.com/product/DP83TC811R-Q1 Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Reviewed-by: Michal Kubecek Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 6 ++- include/linux/phy.h | 2 + include/uapi/linux/ethtool_netlink.h | 2 + net/ethtool/linkstate.c | 75 +++++++++++++++++++++++++++- 4 files changed, 82 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index eed46b6aa07d..7e651ea33eab 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -454,10 +454,12 @@ Request contents: Kernel response contents: - ==================================== ====== ========================== + ==================================== ====== ============================ ``ETHTOOL_A_LINKSTATE_HEADER`` nested reply header ``ETHTOOL_A_LINKSTATE_LINK`` bool link state (up/down) - ==================================== ====== ========================== + ``ETHTOOL_A_LINKSTATE_SQI`` u32 Current Signal Quality Index + ``ETHTOOL_A_LINKSTATE_SQI_MAX`` u32 Max support SQI value + ==================================== ====== ============================ For most NIC drivers, the value of ``ETHTOOL_A_LINKSTATE_LINK`` returns carrier flag provided by ``netif_carrier_ok()`` but there are drivers which diff --git a/include/linux/phy.h b/include/linux/phy.h index 467aa8bf9f64..2bcdf19ed3b4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -723,6 +723,8 @@ struct phy_driver { struct ethtool_tunable *tuna, const void *data); int (*set_loopback)(struct phy_device *dev, bool enable); + int (*get_sqi)(struct phy_device *dev); + int (*get_sqi_max)(struct phy_device *dev); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 2881af411f76..e6f109b76c9a 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -232,6 +232,8 @@ enum { ETHTOOL_A_LINKSTATE_UNSPEC, ETHTOOL_A_LINKSTATE_HEADER, /* nest - _A_HEADER_* */ ETHTOOL_A_LINKSTATE_LINK, /* u8 */ + ETHTOOL_A_LINKSTATE_SQI, /* u32 */ + ETHTOOL_A_LINKSTATE_SQI_MAX, /* u32 */ /* add new constants above here */ __ETHTOOL_A_LINKSTATE_CNT, diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c index 2740cde0a182..7f47ba89054e 100644 --- a/net/ethtool/linkstate.c +++ b/net/ethtool/linkstate.c @@ -2,6 +2,7 @@ #include "netlink.h" #include "common.h" +#include struct linkstate_req_info { struct ethnl_req_info base; @@ -10,6 +11,8 @@ struct linkstate_req_info { struct linkstate_reply_data { struct ethnl_reply_data base; int link; + int sqi; + int sqi_max; }; #define LINKSTATE_REPDATA(__reply_base) \ @@ -20,8 +23,46 @@ linkstate_get_policy[ETHTOOL_A_LINKSTATE_MAX + 1] = { [ETHTOOL_A_LINKSTATE_UNSPEC] = { .type = NLA_REJECT }, [ETHTOOL_A_LINKSTATE_HEADER] = { .type = NLA_NESTED }, [ETHTOOL_A_LINKSTATE_LINK] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKSTATE_SQI] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKSTATE_SQI_MAX] = { .type = NLA_REJECT }, }; +static int linkstate_get_sqi(struct net_device *dev) +{ + struct phy_device *phydev = dev->phydev; + int ret; + + if (!phydev) + return -EOPNOTSUPP; + + mutex_lock(&phydev->lock); + if (!phydev->drv || !phydev->drv->get_sqi) + ret = -EOPNOTSUPP; + else + ret = phydev->drv->get_sqi(phydev); + mutex_unlock(&phydev->lock); + + return ret; +} + +static int linkstate_get_sqi_max(struct net_device *dev) +{ + struct phy_device *phydev = dev->phydev; + int ret; + + if (!phydev) + return -EOPNOTSUPP; + + mutex_lock(&phydev->lock); + if (!phydev->drv || !phydev->drv->get_sqi_max) + ret = -EOPNOTSUPP; + else + ret = phydev->drv->get_sqi_max(phydev); + mutex_unlock(&phydev->lock); + + return ret; +} + static int linkstate_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, struct genl_info *info) @@ -34,6 +75,19 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, if (ret < 0) return ret; data->link = __ethtool_get_link(dev); + + ret = linkstate_get_sqi(dev); + if (ret < 0 && ret != -EOPNOTSUPP) + return ret; + + data->sqi = ret; + + ret = linkstate_get_sqi_max(dev); + if (ret < 0 && ret != -EOPNOTSUPP) + return ret; + + data->sqi_max = ret; + ethnl_ops_complete(dev); return 0; @@ -42,8 +96,19 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, static int linkstate_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { - return nla_total_size(sizeof(u8)) /* LINKSTATE_LINK */ + struct linkstate_reply_data *data = LINKSTATE_REPDATA(reply_base); + int len; + + len = nla_total_size(sizeof(u8)) /* LINKSTATE_LINK */ + 0; + + if (data->sqi != -EOPNOTSUPP) + len += nla_total_size(sizeof(u32)); + + if (data->sqi_max != -EOPNOTSUPP) + len += nla_total_size(sizeof(u32)); + + return len; } static int linkstate_fill_reply(struct sk_buff *skb, @@ -56,6 +121,14 @@ static int linkstate_fill_reply(struct sk_buff *skb, nla_put_u8(skb, ETHTOOL_A_LINKSTATE_LINK, !!data->link)) return -EMSGSIZE; + if (data->sqi != -EOPNOTSUPP && + nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI, data->sqi)) + return -EMSGSIZE; + + if (data->sqi_max != -EOPNOTSUPP && + nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX, data->sqi_max)) + return -EMSGSIZE; + return 0; } -- cgit v1.2.3 From 38428d68719c454d269cb03b776d8a4b0ad66111 Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Thu, 21 May 2020 22:26:13 -0700 Subject: nexthop: support for fdb ecmp nexthops This patch introduces ecmp nexthops and nexthop groups for mac fdb entries. In subsequent patches this is used by the vxlan driver fdb entries. The use case is E-VPN multihoming [1,2,3] which requires bridged vxlan traffic to be load balanced to remote switches (vteps) belonging to the same multi-homed ethernet segment (This is analogous to a multi-homed LAG but over vxlan). Changes include new nexthop flag NHA_FDB for nexthops referenced by fdb entries. These nexthops only have ip. This patch includes appropriate checks to avoid routes referencing such nexthops. example: $ip nexthop add id 12 via 172.16.1.2 fdb $ip nexthop add id 13 via 172.16.1.3 fdb $ip nexthop add id 102 group 12/13 fdb $bridge fdb add 02:02:00:00:00:13 dev vxlan1000 nhid 101 self [1] E-VPN https://tools.ietf.org/html/rfc7432 [2] E-VPN VxLAN: https://tools.ietf.org/html/rfc8365 [3] LPC talk with mention of nexthop groups for L2 ecmp http://vger.kernel.org/lpc_net2018_talks/scaling_bridge_fdb_database_slidesV3.pdf v4 - fixed uninitialized variable reported by kernel test robot Reported-by: kernel test robot Signed-off-by: Roopa Prabhu Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 1 + include/net/nexthop.h | 32 +++++++++++ include/uapi/linux/nexthop.h | 3 + net/ipv4/nexthop.c | 132 +++++++++++++++++++++++++++++++++++-------- net/ipv6/route.c | 5 ++ 5 files changed, 148 insertions(+), 25 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index fdaf975e3331..3f615a29766e 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -65,6 +65,7 @@ struct fib6_config { struct nl_info fc_nlinfo; struct nlattr *fc_encap; u16 fc_encap_type; + bool fc_is_fdb; }; struct fib6_node { diff --git a/include/net/nexthop.h b/include/net/nexthop.h index c440ccc861fc..d929c98931ad 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -26,6 +26,7 @@ struct nh_config { u8 nh_family; u8 nh_protocol; u8 nh_blackhole; + u8 nh_fdb; u32 nh_flags; int nh_ifindex; @@ -52,6 +53,7 @@ struct nh_info { u8 family; bool reject_nh; + bool fdb_nh; union { struct fib_nh_common fib_nhc; @@ -80,6 +82,7 @@ struct nexthop { struct rb_node rb_node; /* entry on netns rbtree */ struct list_head fi_list; /* v4 entries using nh */ struct list_head f6i_list; /* v6 entries using nh */ + struct list_head fdb_list; /* fdb entries using this nh */ struct list_head grp_list; /* nh group entries using this nh */ struct net *net; @@ -88,6 +91,7 @@ struct nexthop { u8 protocol; /* app managing this nh */ u8 nh_flags; bool is_group; + bool is_fdb_nh; refcount_t refcnt; struct rcu_head rcu; @@ -304,4 +308,32 @@ static inline void nexthop_path_fib6_result(struct fib6_result *res, int hash) int nexthop_for_each_fib6_nh(struct nexthop *nh, int (*cb)(struct fib6_nh *nh, void *arg), void *arg); + +static inline int nexthop_get_family(struct nexthop *nh) +{ + struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info); + + return nhi->family; +} + +static inline +struct fib_nh_common *nexthop_fdb_nhc(struct nexthop *nh) +{ + struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info); + + return &nhi->fib_nhc; +} + +static inline struct fib_nh_common *nexthop_path_fdb_result(struct nexthop *nh, + int hash) +{ + struct nh_info *nhi; + struct nexthop *nhp; + + nhp = nexthop_select_path(nh, hash); + if (unlikely(!nhp)) + return NULL; + nhi = rcu_dereference(nhp->nh_info); + return &nhi->fib_nhc; +} #endif diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h index 7b61867e9848..2d4a1e784cf0 100644 --- a/include/uapi/linux/nexthop.h +++ b/include/uapi/linux/nexthop.h @@ -49,6 +49,9 @@ enum { NHA_GROUPS, /* flag; only return nexthop groups in dump */ NHA_MASTER, /* u32; only return nexthops with given master dev */ + NHA_FDB, /* flag; nexthop belongs to a bridge fdb */ + /* if NHA_FDB is added, OIF, BLACKHOLE, ENCAP cannot be set */ + __NHA_MAX, }; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 3957364d556c..bf91edc04631 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -33,6 +33,7 @@ static const struct nla_policy rtm_nh_policy[NHA_MAX + 1] = { [NHA_ENCAP] = { .type = NLA_NESTED }, [NHA_GROUPS] = { .type = NLA_FLAG }, [NHA_MASTER] = { .type = NLA_U32 }, + [NHA_FDB] = { .type = NLA_FLAG }, }; static unsigned int nh_dev_hashfn(unsigned int val) @@ -107,6 +108,7 @@ static struct nexthop *nexthop_alloc(void) INIT_LIST_HEAD(&nh->fi_list); INIT_LIST_HEAD(&nh->f6i_list); INIT_LIST_HEAD(&nh->grp_list); + INIT_LIST_HEAD(&nh->fdb_list); } return nh; } @@ -227,6 +229,9 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, if (nla_put_u32(skb, NHA_ID, nh->id)) goto nla_put_failure; + if (nh->is_fdb_nh && nla_put_flag(skb, NHA_FDB)) + goto nla_put_failure; + if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); @@ -241,7 +246,7 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, if (nla_put_flag(skb, NHA_BLACKHOLE)) goto nla_put_failure; goto out; - } else { + } else if (!nh->is_fdb_nh) { const struct net_device *dev; dev = nhi->fib_nhc.nhc_dev; @@ -387,12 +392,35 @@ static bool valid_group_nh(struct nexthop *nh, unsigned int npaths, return true; } +static int nh_check_attr_fdb_group(struct nexthop *nh, u8 *nh_family, + struct netlink_ext_ack *extack) +{ + struct nh_info *nhi; + + if (!nh->is_fdb_nh) { + NL_SET_ERR_MSG(extack, "FDB nexthop group can only have fdb nexthops"); + return -EINVAL; + } + + nhi = rtnl_dereference(nh->nh_info); + if (*nh_family == AF_UNSPEC) { + *nh_family = nhi->family; + } else if (*nh_family != nhi->family) { + NL_SET_ERR_MSG(extack, "FDB nexthop group cannot have mixed family nexthops"); + return -EINVAL; + } + + return 0; +} + static int nh_check_attr_group(struct net *net, struct nlattr *tb[], struct netlink_ext_ack *extack) { unsigned int len = nla_len(tb[NHA_GROUP]); + u8 nh_family = AF_UNSPEC; struct nexthop_grp *nhg; unsigned int i, j; + u8 nhg_fdb = 0; if (len & (sizeof(struct nexthop_grp) - 1)) { NL_SET_ERR_MSG(extack, @@ -421,6 +449,8 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[], } } + if (tb[NHA_FDB]) + nhg_fdb = 1; nhg = nla_data(tb[NHA_GROUP]); for (i = 0; i < len; ++i) { struct nexthop *nh; @@ -432,11 +462,20 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[], } if (!valid_group_nh(nh, len, extack)) return -EINVAL; + + if (nhg_fdb && nh_check_attr_fdb_group(nh, &nh_family, extack)) + return -EINVAL; + + if (!nhg_fdb && nh->is_fdb_nh) { + NL_SET_ERR_MSG(extack, "Non FDB nexthop group cannot have fdb nexthops"); + return -EINVAL; + } } for (i = NHA_GROUP + 1; i < __NHA_MAX; ++i) { if (!tb[i]) continue; - + if (tb[NHA_FDB]) + continue; NL_SET_ERR_MSG(extack, "No other attributes can be set in nexthop groups"); return -EINVAL; @@ -495,6 +534,9 @@ struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) if (hash > atomic_read(&nhge->upper_bound)) continue; + if (nhge->nh->is_fdb_nh) + return nhge->nh; + /* nexthops always check if it is good and does * not rely on a sysctl for this behavior */ @@ -564,6 +606,11 @@ int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, { struct nh_info *nhi; + if (nh->is_fdb_nh) { + NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); + return -EINVAL; + } + /* fib6_src is unique to a fib6_info and limits the ability to cache * routes in fib6_nh within a nexthop that is potentially shared * across multiple fib entries. If the config wants to use source @@ -640,6 +687,12 @@ int fib_check_nexthop(struct nexthop *nh, u8 scope, { int err = 0; + if (nh->is_fdb_nh) { + NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); + err = -EINVAL; + goto out; + } + if (nh->is_group) { struct nh_group *nhg; @@ -1125,6 +1178,9 @@ static struct nexthop *nexthop_create_group(struct net *net, nh_group_rebalance(nhg); } + if (cfg->nh_fdb) + nh->is_fdb_nh = 1; + rcu_assign_pointer(nh->nh_grp, nhg); return nh; @@ -1152,7 +1208,7 @@ static int nh_create_ipv4(struct net *net, struct nexthop *nh, .fc_encap = cfg->nh_encap, .fc_encap_type = cfg->nh_encap_type, }; - u32 tb_id = l3mdev_fib_table(cfg->dev); + u32 tb_id = (cfg->dev ? l3mdev_fib_table(cfg->dev) : RT_TABLE_MAIN); int err; err = fib_nh_init(net, fib_nh, &fib_cfg, 1, extack); @@ -1161,6 +1217,9 @@ static int nh_create_ipv4(struct net *net, struct nexthop *nh, goto out; } + if (nh->is_fdb_nh) + goto out; + /* sets nh_dev if successful */ err = fib_check_nh(net, fib_nh, tb_id, 0, extack); if (!err) { @@ -1186,6 +1245,7 @@ static int nh_create_ipv6(struct net *net, struct nexthop *nh, .fc_flags = cfg->nh_flags, .fc_encap = cfg->nh_encap, .fc_encap_type = cfg->nh_encap_type, + .fc_is_fdb = cfg->nh_fdb, }; int err; @@ -1227,6 +1287,9 @@ static struct nexthop *nexthop_create(struct net *net, struct nh_config *cfg, nhi->family = cfg->nh_family; nhi->fib_nhc.nhc_scope = RT_SCOPE_LINK; + if (cfg->nh_fdb) + nh->is_fdb_nh = 1; + if (cfg->nh_blackhole) { nhi->reject_nh = 1; cfg->nh_ifindex = net->loopback_dev->ifindex; @@ -1248,7 +1311,8 @@ static struct nexthop *nexthop_create(struct net *net, struct nh_config *cfg, } /* add the entry to the device based hash */ - nexthop_devhash_add(net, nhi); + if (!nh->is_fdb_nh) + nexthop_devhash_add(net, nhi); rcu_assign_pointer(nh->nh_info, nhi); @@ -1352,6 +1416,19 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, if (tb[NHA_ID]) cfg->nh_id = nla_get_u32(tb[NHA_ID]); + if (tb[NHA_FDB]) { + if (tb[NHA_OIF] || tb[NHA_BLACKHOLE] || + tb[NHA_ENCAP] || tb[NHA_ENCAP_TYPE]) { + NL_SET_ERR_MSG(extack, "Fdb attribute can not be used with encap, oif or blackhole"); + goto out; + } + if (nhm->nh_flags) { + NL_SET_ERR_MSG(extack, "Unsupported nexthop flags in ancillary header"); + goto out; + } + cfg->nh_fdb = nla_get_flag(tb[NHA_FDB]); + } + if (tb[NHA_GROUP]) { if (nhm->nh_family != AF_UNSPEC) { NL_SET_ERR_MSG(extack, "Invalid family for group"); @@ -1375,8 +1452,8 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, if (tb[NHA_BLACKHOLE]) { if (tb[NHA_GATEWAY] || tb[NHA_OIF] || - tb[NHA_ENCAP] || tb[NHA_ENCAP_TYPE]) { - NL_SET_ERR_MSG(extack, "Blackhole attribute can not be used with gateway or oif"); + tb[NHA_ENCAP] || tb[NHA_ENCAP_TYPE] || tb[NHA_FDB]) { + NL_SET_ERR_MSG(extack, "Blackhole attribute can not be used with gateway, oif, encap or fdb"); goto out; } @@ -1385,26 +1462,28 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, goto out; } - if (!tb[NHA_OIF]) { - NL_SET_ERR_MSG(extack, "Device attribute required for non-blackhole nexthops"); + if (!cfg->nh_fdb && !tb[NHA_OIF]) { + NL_SET_ERR_MSG(extack, "Device attribute required for non-blackhole and non-fdb nexthops"); goto out; } - cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]); - if (cfg->nh_ifindex) - cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex); + if (!cfg->nh_fdb && tb[NHA_OIF]) { + cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]); + if (cfg->nh_ifindex) + cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex); - if (!cfg->dev) { - NL_SET_ERR_MSG(extack, "Invalid device index"); - goto out; - } else if (!(cfg->dev->flags & IFF_UP)) { - NL_SET_ERR_MSG(extack, "Nexthop device is not up"); - err = -ENETDOWN; - goto out; - } else if (!netif_carrier_ok(cfg->dev)) { - NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down"); - err = -ENETDOWN; - goto out; + if (!cfg->dev) { + NL_SET_ERR_MSG(extack, "Invalid device index"); + goto out; + } else if (!(cfg->dev->flags & IFF_UP)) { + NL_SET_ERR_MSG(extack, "Nexthop device is not up"); + err = -ENETDOWN; + goto out; + } else if (!netif_carrier_ok(cfg->dev)) { + NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down"); + err = -ENETDOWN; + goto out; + } } err = -EINVAL; @@ -1633,7 +1712,7 @@ static bool nh_dump_filtered(struct nexthop *nh, int dev_idx, int master_idx, static int nh_valid_dump_req(const struct nlmsghdr *nlh, int *dev_idx, int *master_idx, bool *group_filter, - struct netlink_callback *cb) + bool *fdb_filter, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[NHA_MAX + 1]; @@ -1670,6 +1749,9 @@ static int nh_valid_dump_req(const struct nlmsghdr *nlh, int *dev_idx, case NHA_GROUPS: *group_filter = true; break; + case NHA_FDB: + *fdb_filter = true; + break; default: NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request"); return -EINVAL; @@ -1688,17 +1770,17 @@ static int nh_valid_dump_req(const struct nlmsghdr *nlh, int *dev_idx, /* rtnl */ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) { + bool group_filter = false, fdb_filter = false; struct nhmsg *nhm = nlmsg_data(cb->nlh); int dev_filter_idx = 0, master_idx = 0; struct net *net = sock_net(skb->sk); struct rb_root *root = &net->nexthop.rb_root; - bool group_filter = false; struct rb_node *node; int idx = 0, s_idx; int err; err = nh_valid_dump_req(cb->nlh, &dev_filter_idx, &master_idx, - &group_filter, cb); + &group_filter, &fdb_filter, cb); if (err < 0) return err; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a52ec1b86432..82cbb46a2a4f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3421,6 +3421,11 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, #ifdef CONFIG_IPV6_ROUTER_PREF fib6_nh->last_probe = jiffies; #endif + if (cfg->fc_is_fdb) { + fib6_nh->fib_nh_gw6 = cfg->fc_gateway; + fib6_nh->fib_nh_gw_family = AF_INET6; + return 0; + } err = -ENODEV; if (cfg->fc_ifindex) { -- cgit v1.2.3 From 1274e1cc42264d4e629841e4f182795cb0becfd2 Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Thu, 21 May 2020 22:26:14 -0700 Subject: vxlan: ecmp support for mac fdb entries Todays vxlan mac fdb entries can point to multiple remote ips (rdsts) with the sole purpose of replicating broadcast-multicast and unknown unicast packets to those remote ips. E-VPN multihoming [1,2,3] requires bridged vxlan traffic to be load balanced to remote switches (vteps) belonging to the same multi-homed ethernet segment (E-VPN multihoming is analogous to multi-homed LAG implementations, but with the inter-switch peerlink replaced with a vxlan tunnel). In other words it needs support for mac ecmp. Furthermore, for faster convergence, E-VPN multihoming needs the ability to update fdb ecmp nexthops independent of the fdb entries. New route nexthop API is perfect for this usecase. This patch extends the vxlan fdb code to take a nexthop id pointing to an ecmp nexthop group. Changes include: - New NDA_NH_ID attribute for fdbs - Use the newly added fdb nexthop groups - makes vxlan rdsts and nexthop handling code mutually exclusive - since this is a new use-case and the requirement is for ecmp nexthop groups, the fdb add and update path checks that the nexthop is really an ecmp nexthop group. This check can be relaxed in the future, if we want to introduce replication fdb nexthop groups and allow its use in lieu of current rdst lists. - fdb update requests with nexthop id's only allowed for existing fdb's that have nexthop id's - learning will not override an existing fdb entry with nexthop group - I have wrapped the switchdev offload code around the presence of rdst [1] E-VPN RFC https://tools.ietf.org/html/rfc7432 [2] E-VPN with vxlan https://tools.ietf.org/html/rfc8365 [3] http://vger.kernel.org/lpc_net2018_talks/scaling_bridge_fdb_database_slidesV3.pdf Includes a null check fix in vxlan_xmit from Nikolay v2 - Fixed build issue: Reported-by: kbuild test robot Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 306 +++++++++++++++++++++++++++++++++-------- include/net/vxlan.h | 25 ++++ include/uapi/linux/neighbour.h | 1 + net/core/neighbour.c | 2 + 4 files changed, 275 insertions(+), 59 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index a5b415fed11e..754e00240eea 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -26,6 +26,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_IPV6) #include @@ -78,6 +79,8 @@ struct vxlan_fdb { u16 state; /* see ndm_state */ __be32 vni; u16 flags; /* see ndm_flags and below */ + struct list_head nh_list; + struct nexthop __rcu *nh; }; #define NTF_VXLAN_ADDED_BY_USER 0x100 @@ -174,11 +177,15 @@ static inline struct hlist_head *vs_head(struct net *net, __be16 port) */ static inline struct vxlan_rdst *first_remote_rcu(struct vxlan_fdb *fdb) { + if (rcu_access_pointer(fdb->nh)) + return NULL; return list_entry_rcu(fdb->remotes.next, struct vxlan_rdst, list); } static inline struct vxlan_rdst *first_remote_rtnl(struct vxlan_fdb *fdb) { + if (rcu_access_pointer(fdb->nh)) + return NULL; return list_first_entry(&fdb->remotes, struct vxlan_rdst, list); } @@ -251,9 +258,10 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, { unsigned long now = jiffies; struct nda_cacheinfo ci; + bool send_ip, send_eth; struct nlmsghdr *nlh; + struct nexthop *nh; struct ndmsg *ndm; - bool send_ip, send_eth; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) @@ -264,16 +272,21 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, send_eth = send_ip = true; + nh = rcu_dereference_rtnl(fdb->nh); if (type == RTM_GETNEIGH) { - send_ip = !vxlan_addr_any(&rdst->remote_ip); + if (rdst) { + send_ip = !vxlan_addr_any(&rdst->remote_ip); + ndm->ndm_family = send_ip ? rdst->remote_ip.sa.sa_family : AF_INET; + } else if (nh) { + ndm->ndm_family = nexthop_get_family(nh); + } send_eth = !is_zero_ether_addr(fdb->eth_addr); - ndm->ndm_family = send_ip ? rdst->remote_ip.sa.sa_family : AF_INET; } else ndm->ndm_family = AF_BRIDGE; ndm->ndm_state = fdb->state; ndm->ndm_ifindex = vxlan->dev->ifindex; ndm->ndm_flags = fdb->flags; - if (rdst->offloaded) + if (rdst && rdst->offloaded) ndm->ndm_flags |= NTF_OFFLOADED; ndm->ndm_type = RTN_UNICAST; @@ -284,23 +297,30 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr)) goto nla_put_failure; + if (nh) { + if (nla_put_u32(skb, NDA_NH_ID, nh->id)) + goto nla_put_failure; + } else if (rdst) { + if (send_ip && vxlan_nla_put_addr(skb, NDA_DST, + &rdst->remote_ip)) + goto nla_put_failure; + + if (rdst->remote_port && + rdst->remote_port != vxlan->cfg.dst_port && + nla_put_be16(skb, NDA_PORT, rdst->remote_port)) + goto nla_put_failure; + if (rdst->remote_vni != vxlan->default_dst.remote_vni && + nla_put_u32(skb, NDA_VNI, be32_to_cpu(rdst->remote_vni))) + goto nla_put_failure; + if (rdst->remote_ifindex && + nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex)) + goto nla_put_failure; + } - if (send_ip && vxlan_nla_put_addr(skb, NDA_DST, &rdst->remote_ip)) - goto nla_put_failure; - - if (rdst->remote_port && rdst->remote_port != vxlan->cfg.dst_port && - nla_put_be16(skb, NDA_PORT, rdst->remote_port)) - goto nla_put_failure; - if (rdst->remote_vni != vxlan->default_dst.remote_vni && - nla_put_u32(skb, NDA_VNI, be32_to_cpu(rdst->remote_vni))) - goto nla_put_failure; if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && fdb->vni && nla_put_u32(skb, NDA_SRC_VNI, be32_to_cpu(fdb->vni))) goto nla_put_failure; - if (rdst->remote_ifindex && - nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex)) - goto nla_put_failure; ci.ndm_used = jiffies_to_clock_t(now - fdb->used); ci.ndm_confirmed = 0; @@ -401,7 +421,7 @@ static int vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, { int err; - if (swdev_notify) { + if (swdev_notify && rd) { switch (type) { case RTM_NEWNEIGH: err = vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, @@ -805,6 +825,8 @@ static struct vxlan_fdb *vxlan_fdb_alloc(const u8 *mac, __u16 state, f->flags = ndm_flags; f->updated = f->used = jiffies; f->vni = src_vni; + f->nh = NULL; + INIT_LIST_HEAD(&f->nh_list); INIT_LIST_HEAD(&f->remotes); memcpy(f->eth_addr, mac, ETH_ALEN); @@ -819,11 +841,78 @@ static void vxlan_fdb_insert(struct vxlan_dev *vxlan, const u8 *mac, vxlan_fdb_head(vxlan, mac, src_vni)); } +static int vxlan_fdb_nh_update(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, + u32 nhid, struct netlink_ext_ack *extack) +{ + struct nexthop *old_nh = rtnl_dereference(fdb->nh); + struct nh_group *nhg; + struct nexthop *nh; + int err = -EINVAL; + + if (old_nh && old_nh->id == nhid) + return 0; + + nh = nexthop_find_by_id(vxlan->net, nhid); + if (!nh) { + NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); + goto err_inval; + } + + if (nh) { + if (!nexthop_get(nh)) { + NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); + nh = NULL; + goto err_inval; + } + if (!nh->is_fdb_nh) { + NL_SET_ERR_MSG(extack, "Nexthop is not a fdb nexthop"); + goto err_inval; + } + + if (!nh->is_group || !nh->nh_grp->mpath) { + NL_SET_ERR_MSG(extack, "Nexthop is not a multipath group"); + goto err_inval; + } + + /* check nexthop group family */ + nhg = rtnl_dereference(nh->nh_grp); + switch (vxlan->default_dst.remote_ip.sa.sa_family) { + case AF_INET: + if (!nhg->has_v4) { + err = -EAFNOSUPPORT; + NL_SET_ERR_MSG(extack, "Nexthop group family not supported"); + goto err_inval; + } + break; + case AF_INET6: + if (nhg->has_v4) { + err = -EAFNOSUPPORT; + NL_SET_ERR_MSG(extack, "Nexthop group family not supported"); + goto err_inval; + } + } + } + + if (old_nh) { + list_del_rcu(&fdb->nh_list); + nexthop_put(old_nh); + } + rcu_assign_pointer(fdb->nh, nh); + list_add_tail_rcu(&fdb->nh_list, &nh->fdb_list); + return 1; + +err_inval: + if (nh) + nexthop_put(nh); + return err; +} + static int vxlan_fdb_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, - struct vxlan_fdb **fdb) + u32 nhid, struct vxlan_fdb **fdb, + struct netlink_ext_ack *extack) { struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; @@ -838,20 +927,33 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, if (!f) return -ENOMEM; - rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); - if (rc < 0) { - kfree(f); - return rc; - } + if (nhid) + rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack); + else + rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); + if (rc < 0) + goto errout; *fdb = f; return 0; + +errout: + kfree(f); + return rc; } static void __vxlan_fdb_free(struct vxlan_fdb *f) { struct vxlan_rdst *rd, *nd; + struct nexthop *nh; + + nh = rcu_dereference_raw(f->nh); + if (nh) { + rcu_assign_pointer(f->nh, NULL); + list_del_rcu(&f->nh_list); + nexthop_put(nh); + } list_for_each_entry_safe(rd, nd, &f->remotes, list) { dst_cache_destroy(&rd->dst_cache); @@ -875,10 +977,15 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, netdev_dbg(vxlan->dev, "delete %pM\n", f->eth_addr); --vxlan->addrcnt; - if (do_notify) - list_for_each_entry(rd, &f->remotes, list) - vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, + if (do_notify) { + if (rcu_access_pointer(f->nh)) + vxlan_fdb_notify(vxlan, f, NULL, RTM_DELNEIGH, swdev_notify, NULL); + else + list_for_each_entry(rd, &f->remotes, list) + vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, + swdev_notify, NULL); + } hlist_del_rcu(&f->hlist); call_rcu(&f->rcu, vxlan_fdb_free); @@ -897,7 +1004,7 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, __u16 state, __u16 flags, __be16 port, __be32 vni, __u32 ifindex, __u16 ndm_flags, - struct vxlan_fdb *f, + struct vxlan_fdb *f, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { @@ -908,6 +1015,18 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, int rc = 0; int err; + if (nhid && !rcu_access_pointer(f->nh)) { + NL_SET_ERR_MSG(extack, + "Cannot replace an existing non nexthop fdb with a nexthop"); + return -EOPNOTSUPP; + } + + if (nhid && (flags & NLM_F_APPEND)) { + NL_SET_ERR_MSG(extack, + "Cannot append to a nexthop fdb"); + return -EOPNOTSUPP; + } + /* Do not allow an externally learned entry to take over an entry added * by the user. */ @@ -929,10 +1048,17 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, /* Only change unicasts */ if (!(is_multicast_ether_addr(f->eth_addr) || is_zero_ether_addr(f->eth_addr))) { - rc = vxlan_fdb_replace(f, ip, port, vni, - ifindex, &oldrd); + if (nhid) { + rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack); + if (rc < 0) + return rc; + } else { + rc = vxlan_fdb_replace(f, ip, port, vni, + ifindex, &oldrd); + } notify |= rc; } else { + NL_SET_ERR_MSG(extack, "Cannot replace non-unicast fdb entries"); return -EOPNOTSUPP; } } @@ -962,6 +1088,8 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, return 0; err_notify: + if (nhid) + return err; if ((flags & NLM_F_REPLACE) && rc) *rd = oldrd; else if ((flags & NLM_F_APPEND) && rc) { @@ -975,7 +1103,7 @@ static int vxlan_fdb_update_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, - __u32 ifindex, __u16 ndm_flags, + __u32 ifindex, __u16 ndm_flags, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { @@ -990,7 +1118,7 @@ static int vxlan_fdb_update_create(struct vxlan_dev *vxlan, netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni, - vni, ifindex, fdb_flags, &f); + vni, ifindex, fdb_flags, nhid, &f, extack); if (rc < 0) return rc; @@ -1012,7 +1140,7 @@ static int vxlan_fdb_update(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, - __u32 ifindex, __u16 ndm_flags, + __u32 ifindex, __u16 ndm_flags, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { @@ -1028,14 +1156,15 @@ static int vxlan_fdb_update(struct vxlan_dev *vxlan, return vxlan_fdb_update_existing(vxlan, ip, state, flags, port, vni, ifindex, ndm_flags, f, - swdev_notify, extack); + nhid, swdev_notify, extack); } else { if (!(flags & NLM_F_CREATE)) return -ENOENT; return vxlan_fdb_update_create(vxlan, mac, ip, state, flags, port, src_vni, vni, ifindex, - ndm_flags, swdev_notify, extack); + ndm_flags, nhid, swdev_notify, + extack); } } @@ -1049,7 +1178,7 @@ static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, union vxlan_addr *ip, __be16 *port, __be32 *src_vni, - __be32 *vni, u32 *ifindex) + __be32 *vni, u32 *ifindex, u32 *nhid) { struct net *net = dev_net(vxlan->dev); int err; @@ -1109,6 +1238,11 @@ static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, *ifindex = 0; } + if (tb[NDA_NH_ID]) + *nhid = nla_get_u32(tb[NDA_NH_ID]); + else + *nhid = 0; + return 0; } @@ -1123,7 +1257,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], union vxlan_addr ip; __be16 port; __be32 src_vni, vni; - u32 ifindex; + u32 ifindex, nhid; u32 hash_index; int err; @@ -1133,10 +1267,11 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], return -EINVAL; } - if (tb[NDA_DST] == NULL) + if (!tb || (!tb[NDA_DST] && !tb[NDA_NH_ID])) return -EINVAL; - err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex); + err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex, + &nhid); if (err) return err; @@ -1148,7 +1283,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags, port, src_vni, vni, ifindex, ndm->ndm_flags | NTF_VXLAN_ADDED_BY_USER, - true, extack); + nhid, true, extack); spin_unlock_bh(&vxlan->hash_lock[hash_index]); return err; @@ -1159,8 +1294,8 @@ static int __vxlan_fdb_delete(struct vxlan_dev *vxlan, __be16 port, __be32 src_vni, __be32 vni, u32 ifindex, bool swdev_notify) { - struct vxlan_fdb *f; struct vxlan_rdst *rd = NULL; + struct vxlan_fdb *f; int err = -ENOENT; f = vxlan_find_mac(vxlan, addr, src_vni); @@ -1195,12 +1330,13 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct vxlan_dev *vxlan = netdev_priv(dev); union vxlan_addr ip; __be32 src_vni, vni; - __be16 port; - u32 ifindex; + u32 ifindex, nhid; u32 hash_index; + __be16 port; int err; - err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex); + err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex, + &nhid); if (err) return err; @@ -1228,6 +1364,17 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) { struct vxlan_rdst *rd; + if (rcu_access_pointer(f->nh)) { + err = vxlan_fdb_info(skb, vxlan, f, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, + NLM_F_MULTI, NULL); + if (err < 0) + goto out; + continue; + } + list_for_each_entry_rcu(rd, &f->remotes, list) { if (*idx < cb->args[2]) goto skip; @@ -1311,6 +1458,10 @@ static bool vxlan_snoop(struct net_device *dev, if (f->state & (NUD_PERMANENT | NUD_NOARP)) return true; + /* Don't override an fdb with nexthop with a learnt entry */ + if (rcu_access_pointer(f->nh)) + return true; + if (net_ratelimit()) netdev_info(dev, "%pM migrated from %pIS to %pIS\n", @@ -1333,7 +1484,7 @@ static bool vxlan_snoop(struct net_device *dev, vxlan->cfg.dst_port, vni, vxlan->default_dst.remote_vni, - ifindex, NTF_SELF, true, NULL); + ifindex, NTF_SELF, 0, true, NULL); spin_unlock(&vxlan->hash_lock[hash_index]); } @@ -2616,6 +2767,38 @@ tx_error: kfree_skb(skb); } +static void vxlan_xmit_nh(struct sk_buff *skb, struct net_device *dev, + struct vxlan_fdb *f, __be32 vni, bool did_rsc) +{ + struct vxlan_rdst nh_rdst; + struct nexthop *nh; + bool do_xmit; + u32 hash; + + memset(&nh_rdst, 0, sizeof(struct vxlan_rdst)); + hash = skb_get_hash(skb); + + rcu_read_lock(); + nh = rcu_dereference(f->nh); + if (!nh) { + rcu_read_unlock(); + goto drop; + } + do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst); + rcu_read_unlock(); + + if (likely(do_xmit)) + vxlan_xmit_one(skb, dev, vni, &nh_rdst, did_rsc); + else + goto drop; + + return; + +drop: + dev->stats.tx_dropped++; + dev_kfree_skb(skb); +} + /* Transmit local packets over Vxlan * * Outer IP header inherits ECN and DF from inner header. @@ -2692,22 +2875,27 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) } } - list_for_each_entry_rcu(rdst, &f->remotes, list) { - struct sk_buff *skb1; + if (rcu_access_pointer(f->nh)) { + vxlan_xmit_nh(skb, dev, f, + (vni ? : vxlan->default_dst.remote_vni), did_rsc); + } else { + list_for_each_entry_rcu(rdst, &f->remotes, list) { + struct sk_buff *skb1; - if (!fdst) { - fdst = rdst; - continue; + if (!fdst) { + fdst = rdst; + continue; + } + skb1 = skb_clone(skb, GFP_ATOMIC); + if (skb1) + vxlan_xmit_one(skb1, dev, vni, rdst, did_rsc); } - skb1 = skb_clone(skb, GFP_ATOMIC); - if (skb1) - vxlan_xmit_one(skb1, dev, vni, rdst, did_rsc); + if (fdst) + vxlan_xmit_one(skb, dev, vni, fdst, did_rsc); + else + kfree_skb(skb); } - if (fdst) - vxlan_xmit_one(skb, dev, vni, fdst, did_rsc); - else - kfree_skb(skb); return NETDEV_TX_OK; } @@ -3615,7 +3803,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, - NTF_SELF, &f); + NTF_SELF, 0, &f, extack); if (err) return err; } @@ -4013,7 +4201,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], vxlan->cfg.dst_port, conf.vni, conf.vni, conf.remote_ifindex, - NTF_SELF, true, extack); + NTF_SELF, 0, true, extack); if (err) { spin_unlock_bh(&vxlan->hash_lock[hash_index]); netdev_adjacent_change_abort(dst->remote_dev, @@ -4335,7 +4523,7 @@ vxlan_fdb_external_learn_add(struct net_device *dev, fdb_info->remote_vni, fdb_info->remote_ifindex, NTF_USE | NTF_SELF | NTF_EXT_LEARNED, - false, extack); + 0, false, extack); spin_unlock_bh(&vxlan->hash_lock[hash_index]); return err; diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 373aadcfea21..3a41627cbdfe 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -7,6 +7,7 @@ #include #include #include +#include #define IANA_VXLAN_UDP_PORT 4789 @@ -487,4 +488,28 @@ static inline void vxlan_flag_attr_error(int attrtype, #undef VXLAN_FLAG } +static inline bool vxlan_fdb_nh_path_select(struct nexthop *nh, + int hash, + struct vxlan_rdst *rdst) +{ + struct fib_nh_common *nhc; + + nhc = nexthop_path_fdb_result(nh, hash); + if (unlikely(!nhc)) + return false; + + switch (nhc->nhc_gw_family) { + case AF_INET: + rdst->remote_ip.sin.sin_addr.s_addr = nhc->nhc_gw.ipv4; + rdst->remote_ip.sa.sa_family = AF_INET; + break; + case AF_INET6: + rdst->remote_ip.sin6.sin6_addr = nhc->nhc_gw.ipv6; + rdst->remote_ip.sa.sa_family = AF_INET6; + break; + } + + return true; +} + #endif diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index cd144e3099a3..eefcda8ca44e 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -29,6 +29,7 @@ enum { NDA_LINK_NETNSID, NDA_SRC_VNI, NDA_PROTOCOL, /* Originator of entry */ + NDA_NH_ID, __NDA_MAX }; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index b607ea602774..37e4dba62460 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1771,6 +1771,7 @@ static struct neigh_table *neigh_find_table(int family) } const struct nla_policy nda_policy[NDA_MAX+1] = { + [NDA_UNSPEC] = { .strict_start_type = NDA_NH_ID }, [NDA_DST] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, [NDA_LLADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, [NDA_CACHEINFO] = { .len = sizeof(struct nda_cacheinfo) }, @@ -1781,6 +1782,7 @@ const struct nla_policy nda_policy[NDA_MAX+1] = { [NDA_IFINDEX] = { .type = NLA_U32 }, [NDA_MASTER] = { .type = NLA_U32 }, [NDA_PROTOCOL] = { .type = NLA_U8 }, + [NDA_NH_ID] = { .type = NLA_U32 }, }; static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, -- cgit v1.2.3 From 31344b2fcead3239c5b801016d9bae82506b92c2 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Mon, 11 May 2020 14:49:10 +0200 Subject: btrfs: remove more obsolete v0 extent ref declarations The extent references v0 have been superseded long time go, there are some unused declarations of access helpers. We can safely remove them now. The struct btrfs_extent_ref_v0 is not used anywhere, but struct btrfs_extent_item_v0 is still part of a backward compatibility check in relocation.c and thus not removed. Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 9 --------- include/uapi/linux/btrfs_tree.h | 9 --------- 2 files changed, 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0b78ab0213bb..86ec25250ac5 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1648,9 +1648,6 @@ BTRFS_SETGET_FUNCS(extent_generation, struct btrfs_extent_item, generation, 64); BTRFS_SETGET_FUNCS(extent_flags, struct btrfs_extent_item, flags, 64); -BTRFS_SETGET_FUNCS(extent_refs_v0, struct btrfs_extent_item_v0, refs, 32); - - BTRFS_SETGET_FUNCS(tree_block_level, struct btrfs_tree_block_info, level, 8); static inline void btrfs_tree_block_key(struct extent_buffer *eb, @@ -1698,12 +1695,6 @@ static inline u32 btrfs_extent_inline_ref_size(int type) return 0; } -BTRFS_SETGET_FUNCS(ref_root_v0, struct btrfs_extent_ref_v0, root, 64); -BTRFS_SETGET_FUNCS(ref_generation_v0, struct btrfs_extent_ref_v0, - generation, 64); -BTRFS_SETGET_FUNCS(ref_objectid_v0, struct btrfs_extent_ref_v0, objectid, 64); -BTRFS_SETGET_FUNCS(ref_count_v0, struct btrfs_extent_ref_v0, count, 32); - /* struct btrfs_node */ BTRFS_SETGET_FUNCS(key_blockptr, struct btrfs_key_ptr, blockptr, 64); BTRFS_SETGET_FUNCS(key_generation, struct btrfs_key_ptr, generation, 64); diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index 8e322e2c7e78..a3f3975df0de 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -519,15 +519,6 @@ struct btrfs_extent_inline_ref { __le64 offset; } __attribute__ ((__packed__)); -/* old style backrefs item */ -struct btrfs_extent_ref_v0 { - __le64 root; - __le64 generation; - __le64 objectid; - __le32 count; -} __attribute__ ((__packed__)); - - /* dev extents record free space on individual devices. The owner * field points back to the chunk allocation mapping tree that allocated * the extent. The chunk tree uuid field is a way to double check the owner -- cgit v1.2.3 From 61aec25a6db5d0c2e8ab5da6d2d152269d0d9d69 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Tue, 26 May 2020 14:29:04 +0200 Subject: cls_flower: Support filtering on multiple MPLS Label Stack Entries With struct flow_dissector_key_mpls now recording the first FLOW_DIS_MPLS_MAX labels, we can extend Flower to filter on any of these LSEs independently. In order to avoid creating new netlink attributes for every possible depth, let's define a new TCA_FLOWER_KEY_MPLS_OPTS nested attribute that contains the list of LSEs to match. Each LSE is represented by another attribute, TCA_FLOWER_KEY_MPLS_OPTS_LSE, which then contains the attributes representing the depth and the MPLS fields to match at this depth (label, TTL, etc.). For each MPLS field, the mask is always set to all-ones, as this is what the original API did. We could allow user configurable masks in the future if there is demand for more flexibility. The new API also allows to only specify an LSE depth. In that case, Flower only verifies that the MPLS label stack depth is greater or equal to the provided depth (that is, an LSE exists at this depth). Filters that only match on one (or more) fields of the first LSE are dumped using the old netlink attributes, to avoid confusing user space programs that don't understand the new API. Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 23 ++++ net/sched/cls_flower.c | 243 ++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 265 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index fc672b232437..7576209d96f9 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -576,6 +576,8 @@ enum { TCA_FLOWER_KEY_CT_LABELS, /* u128 */ TCA_FLOWER_KEY_CT_LABELS_MASK, /* u128 */ + TCA_FLOWER_KEY_MPLS_OPTS, + __TCA_FLOWER_MAX, }; @@ -640,6 +642,27 @@ enum { #define TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX \ (__TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX - 1) +enum { + TCA_FLOWER_KEY_MPLS_OPTS_UNSPEC, + TCA_FLOWER_KEY_MPLS_OPTS_LSE, + __TCA_FLOWER_KEY_MPLS_OPTS_MAX, +}; + +#define TCA_FLOWER_KEY_MPLS_OPTS_MAX (__TCA_FLOWER_KEY_MPLS_OPTS_MAX - 1) + +enum { + TCA_FLOWER_KEY_MPLS_OPT_LSE_UNSPEC, + TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH, + TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL, + TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS, + TCA_FLOWER_KEY_MPLS_OPT_LSE_TC, + TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL, + __TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX, +}; + +#define TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX \ + (__TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX - 1) + enum { TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0), TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1), diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index f524afe0b7f5..96f5999281e0 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -668,6 +668,7 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_MPLS_BOS] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_MPLS_TC] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_MPLS_LABEL] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_MPLS_OPTS] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_TCP_FLAGS] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_TCP_FLAGS_MASK] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_IP_TOS] = { .type = NLA_U8 }, @@ -726,6 +727,20 @@ erspan_opt_policy[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX + 1] = { [TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID] = { .type = NLA_U8 }, }; +static const struct nla_policy +mpls_opts_policy[TCA_FLOWER_KEY_MPLS_OPTS_MAX + 1] = { + [TCA_FLOWER_KEY_MPLS_OPTS_LSE] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy +mpls_stack_entry_policy[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1] = { + [TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_MPLS_OPT_LSE_TC] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL] = { .type = NLA_U32 }, +}; + static void fl_set_key_val(struct nlattr **tb, void *val, int val_type, void *mask, int mask_type, int len) @@ -776,6 +791,126 @@ static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key, return 0; } +static int fl_set_key_mpls_lse(const struct nlattr *nla_lse, + struct flow_dissector_key_mpls *key_val, + struct flow_dissector_key_mpls *key_mask, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1]; + struct flow_dissector_mpls_lse *lse_mask; + struct flow_dissector_mpls_lse *lse_val; + u8 lse_index; + u8 depth; + int err; + + err = nla_parse_nested(tb, TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX, nla_lse, + mpls_stack_entry_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH]) { + NL_SET_ERR_MSG(extack, "Missing MPLS option \"depth\""); + return -EINVAL; + } + + depth = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH]); + + /* LSE depth starts at 1, for consistency with terminology used by + * RFC 3031 (section 3.9), where depth 0 refers to unlabeled packets. + */ + if (depth < 1 || depth > FLOW_DIS_MPLS_MAX) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH], + "Invalid MPLS depth"); + return -EINVAL; + } + lse_index = depth - 1; + + dissector_set_mpls_lse(key_val, lse_index); + dissector_set_mpls_lse(key_mask, lse_index); + + lse_val = &key_val->ls[lse_index]; + lse_mask = &key_mask->ls[lse_index]; + + if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL]) { + lse_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL]); + lse_mask->mpls_ttl = MPLS_TTL_MASK; + } + if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS]) { + u8 bos = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS]); + + if (bos & ~MPLS_BOS_MASK) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS], + "Bottom Of Stack (BOS) must be 0 or 1"); + return -EINVAL; + } + lse_val->mpls_bos = bos; + lse_mask->mpls_bos = MPLS_BOS_MASK; + } + if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TC]) { + u8 tc = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TC]); + + if (tc & ~MPLS_TC_MASK) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TC], + "Traffic Class (TC) must be between 0 and 7"); + return -EINVAL; + } + lse_val->mpls_tc = tc; + lse_mask->mpls_tc = MPLS_TC_MASK; + } + if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL]) { + u32 label = nla_get_u32(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL]); + + if (label & ~MPLS_LABEL_MASK) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL], + "Label must be between 0 and 1048575"); + return -EINVAL; + } + lse_val->mpls_label = label; + lse_mask->mpls_label = MPLS_LABEL_MASK; + } + + return 0; +} + +static int fl_set_key_mpls_opts(const struct nlattr *nla_mpls_opts, + struct flow_dissector_key_mpls *key_val, + struct flow_dissector_key_mpls *key_mask, + struct netlink_ext_ack *extack) +{ + struct nlattr *nla_lse; + int rem; + int err; + + if (!(nla_mpls_opts->nla_type & NLA_F_NESTED)) { + NL_SET_ERR_MSG_ATTR(extack, nla_mpls_opts, + "NLA_F_NESTED is missing"); + return -EINVAL; + } + + nla_for_each_nested(nla_lse, nla_mpls_opts, rem) { + if (nla_type(nla_lse) != TCA_FLOWER_KEY_MPLS_OPTS_LSE) { + NL_SET_ERR_MSG_ATTR(extack, nla_lse, + "Invalid MPLS option type"); + return -EINVAL; + } + + err = fl_set_key_mpls_lse(nla_lse, key_val, key_mask, extack); + if (err < 0) + return err; + } + if (rem) { + NL_SET_ERR_MSG(extack, + "Bytes leftover after parsing MPLS options"); + return -EINVAL; + } + + return 0; +} + static int fl_set_key_mpls(struct nlattr **tb, struct flow_dissector_key_mpls *key_val, struct flow_dissector_key_mpls *key_mask, @@ -784,6 +919,21 @@ static int fl_set_key_mpls(struct nlattr **tb, struct flow_dissector_mpls_lse *lse_mask; struct flow_dissector_mpls_lse *lse_val; + if (tb[TCA_FLOWER_KEY_MPLS_OPTS]) { + if (tb[TCA_FLOWER_KEY_MPLS_TTL] || + tb[TCA_FLOWER_KEY_MPLS_BOS] || + tb[TCA_FLOWER_KEY_MPLS_TC] || + tb[TCA_FLOWER_KEY_MPLS_LABEL]) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_OPTS], + "MPLS label, Traffic Class, Bottom Of Stack and Time To Live must be encapsulated in the MPLS options attribute"); + return -EBADMSG; + } + + return fl_set_key_mpls_opts(tb[TCA_FLOWER_KEY_MPLS_OPTS], + key_val, key_mask, extack); + } + lse_val = &key_val->ls[0]; lse_mask = &key_mask->ls[0]; @@ -2232,6 +2382,89 @@ static int fl_dump_key_port_range(struct sk_buff *skb, struct fl_flow_key *key, return 0; } +static int fl_dump_key_mpls_opt_lse(struct sk_buff *skb, + struct flow_dissector_key_mpls *mpls_key, + struct flow_dissector_key_mpls *mpls_mask, + u8 lse_index) +{ + struct flow_dissector_mpls_lse *lse_mask = &mpls_mask->ls[lse_index]; + struct flow_dissector_mpls_lse *lse_key = &mpls_key->ls[lse_index]; + int err; + + err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH, + lse_index + 1); + if (err) + return err; + + if (lse_mask->mpls_ttl) { + err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL, + lse_key->mpls_ttl); + if (err) + return err; + } + if (lse_mask->mpls_bos) { + err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS, + lse_key->mpls_bos); + if (err) + return err; + } + if (lse_mask->mpls_tc) { + err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_TC, + lse_key->mpls_tc); + if (err) + return err; + } + if (lse_mask->mpls_label) { + err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL, + lse_key->mpls_label); + if (err) + return err; + } + + return 0; +} + +static int fl_dump_key_mpls_opts(struct sk_buff *skb, + struct flow_dissector_key_mpls *mpls_key, + struct flow_dissector_key_mpls *mpls_mask) +{ + struct nlattr *opts; + struct nlattr *lse; + u8 lse_index; + int err; + + opts = nla_nest_start(skb, TCA_FLOWER_KEY_MPLS_OPTS); + if (!opts) + return -EMSGSIZE; + + for (lse_index = 0; lse_index < FLOW_DIS_MPLS_MAX; lse_index++) { + if (!(mpls_mask->used_lses & 1 << lse_index)) + continue; + + lse = nla_nest_start(skb, TCA_FLOWER_KEY_MPLS_OPTS_LSE); + if (!lse) { + err = -EMSGSIZE; + goto err_opts; + } + + err = fl_dump_key_mpls_opt_lse(skb, mpls_key, mpls_mask, + lse_index); + if (err) + goto err_opts_lse; + nla_nest_end(skb, lse); + } + nla_nest_end(skb, opts); + + return 0; + +err_opts_lse: + nla_nest_cancel(skb, lse); +err_opts: + nla_nest_cancel(skb, opts); + + return err; +} + static int fl_dump_key_mpls(struct sk_buff *skb, struct flow_dissector_key_mpls *mpls_key, struct flow_dissector_key_mpls *mpls_mask) @@ -2240,12 +2473,20 @@ static int fl_dump_key_mpls(struct sk_buff *skb, struct flow_dissector_mpls_lse *lse_key; int err; - if (!memchr_inv(mpls_mask, 0, sizeof(*mpls_mask))) + if (!mpls_mask->used_lses) return 0; lse_mask = &mpls_mask->ls[0]; lse_key = &mpls_key->ls[0]; + /* For backward compatibility, don't use the MPLS nested attributes if + * the rule can be expressed using the old attributes. + */ + if (mpls_mask->used_lses & ~1 || + (!lse_mask->mpls_ttl && !lse_mask->mpls_bos && + !lse_mask->mpls_tc && !lse_mask->mpls_label)) + return fl_dump_key_mpls_opts(skb, mpls_key, mpls_mask); + if (lse_mask->mpls_ttl) { err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_TTL, lse_key->mpls_ttl); -- cgit v1.2.3 From a331172b156b23e83dfb556ade0ca23426c3f149 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 27 May 2020 00:21:37 +0200 Subject: net: ethtool: Add attributes for cable test TDR data Some Ethernet PHYs can return the raw time domain reflectromatry data. Add the attributes to allow this data to be requested and returned via netlink ethtool. Signed-off-by: Andrew Lunn v2: m -> cm Report what the PHY actually used for start/stop/step. Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 81 ++++++++++++++++++++++++++++ include/uapi/linux/ethtool_netlink.h | 63 ++++++++++++++++++++++ 2 files changed, 144 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 7e651ea33eab..dae36227d590 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -205,6 +205,7 @@ Userspace to kernel: ``ETHTOOL_MSG_EEE_SET`` set EEE settings ``ETHTOOL_MSG_TSINFO_GET`` get timestamping info ``ETHTOOL_MSG_CABLE_TEST_ACT`` action start cable test + ``ETHTOOL_MSG_CABLE_TEST_TDR_ACT`` action start raw TDR cable test ===================================== ================================ Kernel to userspace: @@ -237,6 +238,7 @@ Kernel to userspace: ``ETHTOOL_MSG_EEE_NTF`` EEE settings ``ETHTOOL_MSG_TSINFO_GET_REPLY`` timestamping info ``ETHTOOL_MSG_CABLE_TEST_NTF`` Cable test results + ``ETHTOOL_MSG_CABLE_TEST_TDR_NTF`` Cable test TDR results ===================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -1014,6 +1016,84 @@ information. | | | ``ETHTOOL_A_CABLE_FAULT_LENGTH_CM`` | u32 | length in cm | +-+-+-----------------------------------------+--------+---------------------+ +CABLE_TEST TDR +============== + +Start a cable test and report raw TDR data + +Request contents: + + ==================================== ====== ========================== + ``ETHTOOL_A_CABLE_TEST_TDR_HEADER`` nested request header + ==================================== ====== ========================== + +Notification contents: + +Raw TDR data is gathered by sending a pulse down the cable and +recording the amplitude of the reflected pulse for a given distance. + +It can take a number of seconds to collect TDR data, especial if the +full 100 meters is probed at 1 meter intervals. When the test is +started a notification will be sent containing just +ETHTOOL_A_CABLE_TEST_TDR_STATUS with the value +ETHTOOL_A_CABLE_TEST_NTF_STATUS_STARTED. + +When the test has completed a second notification will be sent +containing ETHTOOL_A_CABLE_TEST_TDR_STATUS with the value +ETHTOOL_A_CABLE_TEST_NTF_STATUS_COMPLETED and the TDR data. + +The message may optionally contain the amplitude of the pulse send +down the cable. This is measured in mV. A reflection should not be +bigger than transmitted pulse. + +Before the raw TDR data should be an ETHTOOL_A_CABLE_TDR_NEST_STEP +nest containing information about the distance along the cable for the +first reading, the last reading, and the step between each +reading. Distances are measured in centimeters. These should be the +exact values the PHY used. These may be different to what the user +requested, if the native measurement resolution is greater than 1 cm. + +For each step along the cable, a ETHTOOL_A_CABLE_TDR_NEST_AMPLITUDE is +used to report the amplitude of the reflection for a given pair. + + +---------------------------------------------+--------+----------------------+ + | ``ETHTOOL_A_CABLE_TEST_TDR_HEADER`` | nested | reply header | + +---------------------------------------------+--------+----------------------+ + | ``ETHTOOL_A_CABLE_TEST_TDR_STATUS`` | u8 | completed | + +---------------------------------------------+--------+----------------------+ + | ``ETHTOOL_A_CABLE_TEST_TDR_NTF_NEST`` | nested | all the results | + +-+-------------------------------------------+--------+----------------------+ + | | ``ETHTOOL_A_CABLE_TDR_NEST_PULSE`` | nested | TX Pulse amplitude | + +-+-+-----------------------------------------+--------+----------------------+ + | | | ``ETHTOOL_A_CABLE_PULSE_mV`` | s16 | Pulse amplitude | + +-+-+-----------------------------------------+--------+----------------------+ + | | ``ETHTOOL_A_CABLE_NEST_STEP`` | nested | TDR step info | + +-+-+-----------------------------------------+--------+----------------------+ + | | | ``ETHTOOL_A_CABLE_STEP_FIRST_DISTANCE ``| u32 | First data distance | + +-+-+-----------------------------------------+--------+----------------------+ + | | | ``ETHTOOL_A_CABLE_STEP_LAST_DISTANCE `` | u32 | Last data distance | + +-+-+-----------------------------------------+--------+----------------------+ + | | | ``ETHTOOL_A_CABLE_STEP_STEP_DISTANCE `` | u32 | distance of each step| + +-+-+-----------------------------------------+--------+----------------------+ + | | ``ETHTOOL_A_CABLE_TDR_NEST_AMPLITUDE`` | nested | Reflection amplitude | + +-+-+-----------------------------------------+--------+----------------------+ + | | | ``ETHTOOL_A_CABLE_RESULTS_PAIR`` | u8 | pair number | + +-+-+-----------------------------------------+--------+----------------------+ + | | | ``ETHTOOL_A_CABLE_AMPLITUDE_mV`` | s16 | Reflection amplitude | + +-+-+-----------------------------------------+--------+----------------------+ + | | ``ETHTOOL_A_CABLE_TDR_NEST_AMPLITUDE`` | nested | Reflection amplitude | + +-+-+-----------------------------------------+--------+----------------------+ + | | | ``ETHTOOL_A_CABLE_RESULTS_PAIR`` | u8 | pair number | + +-+-+-----------------------------------------+--------+----------------------+ + | | | ``ETHTOOL_A_CABLE_AMPLITUDE_mV`` | s16 | Reflection amplitude | + +-+-+-----------------------------------------+--------+----------------------+ + | | ``ETHTOOL_A_CABLE_TDR_NEST_AMPLITUDE`` | nested | Reflection amplitude | + +-+-+-----------------------------------------+--------+----------------------+ + | | | ``ETHTOOL_A_CABLE_RESULTS_PAIR`` | u8 | pair number | + +-+-+-----------------------------------------+--------+----------------------+ + | | | ``ETHTOOL_A_CABLE_AMPLITUDE_mV`` | s16 | Reflection amplitude | + +-+-+-----------------------------------------+--------+----------------------+ + Request translation =================== @@ -1110,4 +1190,5 @@ are netlink only. ``ETHTOOL_GFECPARAM`` n/a ``ETHTOOL_SFECPARAM`` n/a n/a ''ETHTOOL_MSG_CABLE_TEST_ACT'' + n/a ''ETHTOOL_MSG_CABLE_TEST_TDR_ACT'' =================================== ===================================== diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index e6f109b76c9a..739faa7070c6 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -40,6 +40,7 @@ enum { ETHTOOL_MSG_EEE_SET, ETHTOOL_MSG_TSINFO_GET, ETHTOOL_MSG_CABLE_TEST_ACT, + ETHTOOL_MSG_CABLE_TEST_TDR_ACT, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -76,6 +77,7 @@ enum { ETHTOOL_MSG_EEE_NTF, ETHTOOL_MSG_TSINFO_GET_REPLY, ETHTOOL_MSG_CABLE_TEST_NTF, + ETHTOOL_MSG_CABLE_TEST_TDR_NTF, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -478,6 +480,67 @@ enum { ETHTOOL_A_CABLE_TEST_NTF_MAX = (__ETHTOOL_A_CABLE_TEST_NTF_CNT - 1) }; +/* CABLE TEST TDR */ + +enum { + ETHTOOL_A_CABLE_TEST_TDR_UNSPEC, + ETHTOOL_A_CABLE_TEST_TDR_HEADER, /* nest - _A_HEADER_* */ + + /* add new constants above here */ + __ETHTOOL_A_CABLE_TEST_TDR_CNT, + ETHTOOL_A_CABLE_TEST_TDR_MAX = __ETHTOOL_A_CABLE_TEST_TDR_CNT - 1 +}; + +/* CABLE TEST TDR NOTIFY */ + +enum { + ETHTOOL_A_CABLE_AMPLITUDE_UNSPEC, + ETHTOOL_A_CABLE_AMPLITUDE_PAIR, /* u8 */ + ETHTOOL_A_CABLE_AMPLITUDE_mV, /* s16 */ + + __ETHTOOL_A_CABLE_AMPLITUDE_CNT, + ETHTOOL_A_CABLE_AMPLITUDE_MAX = (__ETHTOOL_A_CABLE_AMPLITUDE_CNT - 1) +}; + +enum { + ETHTOOL_A_CABLE_PULSE_UNSPEC, + ETHTOOL_A_CABLE_PULSE_mV, /* s16 */ + + __ETHTOOL_A_CABLE_PULSE_CNT, + ETHTOOL_A_CABLE_PULSE_MAX = (__ETHTOOL_A_CABLE_PULSE_CNT - 1) +}; + +enum { + ETHTOOL_A_CABLE_STEP_UNSPEC, + ETHTOOL_A_CABLE_STEP_FIRST_DISTANCE, /* u32 */ + ETHTOOL_A_CABLE_STEP_LAST_DISTANCE, /* u32 */ + ETHTOOL_A_CABLE_STEP_STEP_DISTANCE, /* u32 */ + + __ETHTOOL_A_CABLE_STEP_CNT, + ETHTOOL_A_CABLE_STEP_MAX = (__ETHTOOL_A_CABLE_STEP_CNT - 1) +}; + +enum { + ETHTOOL_A_CABLE_TDR_NEST_UNSPEC, + ETHTOOL_A_CABLE_TDR_NEST_STEP, /* nest - ETHTTOOL_A_CABLE_STEP */ + ETHTOOL_A_CABLE_TDR_NEST_AMPLITUDE, /* nest - ETHTOOL_A_CABLE_AMPLITUDE */ + ETHTOOL_A_CABLE_TDR_NEST_PULSE, /* nest - ETHTOOL_A_CABLE_PULSE */ + + __ETHTOOL_A_CABLE_TDR_NEST_CNT, + ETHTOOL_A_CABLE_TDR_NEST_MAX = (__ETHTOOL_A_CABLE_TDR_NEST_CNT - 1) +}; + +enum { + ETHTOOL_A_CABLE_TEST_TDR_NTF_UNSPEC, + ETHTOOL_A_CABLE_TEST_TDR_NTF_HEADER, /* nest - ETHTOOL_A_HEADER_* */ + ETHTOOL_A_CABLE_TEST_TDR_NTF_STATUS, /* u8 - _STARTED/_COMPLETE */ + ETHTOOL_A_CABLE_TEST_TDR_NTF_NEST, /* nest - of results: */ + + /* add new constants above here */ + __ETHTOOL_A_CABLE_TEST_TDR_NTF_CNT, + ETHTOOL_A_CABLE_TEST_TDR_NTF_MAX = __ETHTOOL_A_CABLE_TEST_TDR_NTF_CNT - 1 +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 -- cgit v1.2.3 From f2bc8ad31a7f814237bc6301d59296d76505a688 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 27 May 2020 00:21:41 +0200 Subject: net: ethtool: Allow PHY cable test TDR data to configured Allow the user to configure where on the cable the TDR data should be retrieved, in terms of first and last sample, and the step between samples. Also add the ability to ask for TDR data for just one pair. If this configuration is not provided, it defaults to 1-150m at 1m intervals for all pairs. Signed-off-by: Andrew Lunn v3: Move the TDR configuration into a structure Add a range check on step Use NL_SET_ERR_MSG_ATTR() when appropriate Move TDR configuration into a nest Document attributes in the request Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 22 +++++- drivers/net/phy/marvell.c | 59 ++++++++++----- drivers/net/phy/phy.c | 5 +- include/linux/phy.h | 21 +++++- include/uapi/linux/ethtool_netlink.h | 13 ++++ net/ethtool/cabletest.c | 104 ++++++++++++++++++++++++++- 6 files changed, 197 insertions(+), 27 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index dae36227d590..d42661b91128 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1023,9 +1023,25 @@ Start a cable test and report raw TDR data Request contents: - ==================================== ====== ========================== - ``ETHTOOL_A_CABLE_TEST_TDR_HEADER`` nested request header - ==================================== ====== ========================== + +--------------------------------------------+--------+-----------------------+ + | ``ETHTOOL_A_CABLE_TEST_TDR_HEADER`` | nested | reply header | + +--------------------------------------------+--------+-----------------------+ + | ``ETHTOOL_A_CABLE_TEST_TDR_CFG`` | nested | test configuration | + +-+------------------------------------------+--------+-----------------------+ + | | ``ETHTOOL_A_CABLE_STEP_FIRST_DISTANCE `` | u32 | first data distance | + +-+-+----------------------------------------+--------+-----------------------+ + | | ``ETHTOOL_A_CABLE_STEP_LAST_DISTANCE `` | u32 | last data distance | + +-+-+----------------------------------------+--------+-----------------------+ + | | ``ETHTOOL_A_CABLE_STEP_STEP_DISTANCE `` | u32 | distance of each step | + +-+-+----------------------------------------+--------+-----------------------+ + | | ``ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR`` | u8 | pair to test | + +-+-+----------------------------------------+--------+-----------------------+ + +The ETHTOOL_A_CABLE_TEST_TDR_CFG is optional, as well as all members +of the nest. All distances are expressed in centimeters. The PHY takes +the distances as a guide, and rounds to the nearest distance it +actually supports. If a pair is passed, only that one pair will be +tested. Otherwise all pairs are tested. Notification contents: diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index e597bee2e966..335e51d6f138 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -198,6 +198,7 @@ #define MII_VCT5_CTRL_PEEK_HYST_DEFAULT 3 #define MII_VCT5_SAMPLE_POINT_DISTANCE 0x18 +#define MII_VCT5_SAMPLE_POINT_DISTANCE_MAX 511 #define MII_VCT5_TX_PULSE_CTRL 0x1c #define MII_VCT5_TX_PULSE_CTRL_DONT_WAIT_LINK_DOWN BIT(12) #define MII_VCT5_TX_PULSE_CTRL_PULSE_WIDTH_128nS (0x0 << 10) @@ -270,6 +271,10 @@ struct marvell_priv { char *hwmon_name; struct device *hwmon_dev; bool cable_test_tdr; + u32 first; + u32 last; + u32 step; + s8 pair; }; static int marvell_read_page(struct phy_device *phydev) @@ -1787,12 +1792,18 @@ static u32 marvell_vct5_distance2cm(int distance) return distance * 805 / 10; } +static u32 marvell_vct5_cm2distance(int cm) +{ + return cm * 10 / 805; +} + static int marvell_vct5_amplitude_distance(struct phy_device *phydev, - int distance) + int distance, int pair) { - int mV_pair0, mV_pair1, mV_pair2, mV_pair3; u16 reg; int err; + int mV; + int i; err = phy_write_paged(phydev, MII_MARVELL_VCT5_PAGE, MII_VCT5_SAMPLE_POINT_DISTANCE, @@ -1814,21 +1825,20 @@ static int marvell_vct5_amplitude_distance(struct phy_device *phydev, if (err) return err; - mV_pair0 = marvell_vct5_amplitude(phydev, 0); - mV_pair1 = marvell_vct5_amplitude(phydev, 1); - mV_pair2 = marvell_vct5_amplitude(phydev, 2); - mV_pair3 = marvell_vct5_amplitude(phydev, 3); + for (i = 0; i < 4; i++) { + if (pair != PHY_PAIR_ALL && i != pair) + continue; - ethnl_cable_test_amplitude(phydev, ETHTOOL_A_CABLE_PAIR_A, mV_pair0); - ethnl_cable_test_amplitude(phydev, ETHTOOL_A_CABLE_PAIR_B, mV_pair1); - ethnl_cable_test_amplitude(phydev, ETHTOOL_A_CABLE_PAIR_C, mV_pair2); - ethnl_cable_test_amplitude(phydev, ETHTOOL_A_CABLE_PAIR_D, mV_pair3); + mV = marvell_vct5_amplitude(phydev, i); + ethnl_cable_test_amplitude(phydev, i, mV); + } return 0; } static int marvell_vct5_amplitude_graph(struct phy_device *phydev) { + struct marvell_priv *priv = phydev->priv; int distance; int err; u16 reg; @@ -1843,8 +1853,11 @@ static int marvell_vct5_amplitude_graph(struct phy_device *phydev) if (err) return err; - for (distance = 0; distance <= 100; distance++) { - err = marvell_vct5_amplitude_distance(phydev, distance); + for (distance = priv->first; + distance <= priv->last; + distance += priv->step) { + err = marvell_vct5_amplitude_distance(phydev, distance, + priv->pair); if (err) return err; } @@ -1918,11 +1931,24 @@ static int marvell_vct7_cable_test_start(struct phy_device *phydev) MII_VCT7_CTRL_CENTIMETERS); } -static int marvell_vct5_cable_test_tdr_start(struct phy_device *phydev) +static int marvell_vct5_cable_test_tdr_start(struct phy_device *phydev, + const struct phy_tdr_config *cfg) { struct marvell_priv *priv = phydev->priv; int ret; + priv->cable_test_tdr = true; + priv->first = marvell_vct5_cm2distance(cfg->first); + priv->last = marvell_vct5_cm2distance(cfg->last); + priv->step = marvell_vct5_cm2distance(cfg->step); + priv->pair = cfg->pair; + + if (priv->first > MII_VCT5_SAMPLE_POINT_DISTANCE_MAX) + return -EINVAL; + + if (priv->last > MII_VCT5_SAMPLE_POINT_DISTANCE_MAX) + return -EINVAL; + /* Disable VCT7 */ ret = phy_write_paged(phydev, MII_MARVELL_VCT7_PAGE, MII_VCT7_CTRL, 0); @@ -1933,15 +1959,14 @@ static int marvell_vct5_cable_test_tdr_start(struct phy_device *phydev) if (ret) return ret; - priv->cable_test_tdr = true; ret = ethnl_cable_test_pulse(phydev, 1000); if (ret) return ret; return ethnl_cable_test_step(phydev, - marvell_vct5_distance2cm(0), - marvell_vct5_distance2cm(100), - marvell_vct5_distance2cm(1)); + marvell_vct5_distance2cm(priv->first), + marvell_vct5_distance2cm(priv->last), + marvell_vct5_distance2cm(priv->step)); } static int marvell_vct7_distance_to_length(int distance, bool meter) diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 495d9ba3d5bf..1de3938628f4 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -553,7 +553,8 @@ out: EXPORT_SYMBOL(phy_start_cable_test); int phy_start_cable_test_tdr(struct phy_device *phydev, - struct netlink_ext_ack *extack) + struct netlink_ext_ack *extack, + const struct phy_tdr_config *config) { struct net_device *dev = phydev->attached_dev; int err = -ENOMEM; @@ -590,7 +591,7 @@ int phy_start_cable_test_tdr(struct phy_device *phydev, phy_link_down(phydev); netif_testing_on(dev); - err = phydev->drv->cable_test_tdr_start(phydev); + err = phydev->drv->cable_test_tdr_start(phydev, config); if (err) { netif_testing_off(dev); phy_link_up(phydev); diff --git a/include/linux/phy.h b/include/linux/phy.h index d3c384f353ca..8c05d0fb5c00 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -548,6 +548,18 @@ struct phy_device { #define to_phy_device(d) container_of(to_mdio_device(d), \ struct phy_device, mdio) +/* A structure containing possible configuration parameters + * for a TDR cable test. The driver does not need to implement + * all the parameters, but should report what is actually used. + */ +struct phy_tdr_config { + u32 first; + u32 last; + u32 step; + s8 pair; +}; +#define PHY_PAIR_ALL -1 + /* struct phy_driver: Driver structure for a particular PHY type * * driver_data: static driver data @@ -701,7 +713,8 @@ struct phy_driver { int (*cable_test_start)(struct phy_device *dev); /* Start a raw TDR cable test */ - int (*cable_test_tdr_start)(struct phy_device *dev); + int (*cable_test_tdr_start)(struct phy_device *dev, + const struct phy_tdr_config *config); /* Once per second, or on interrupt, request the status of the * test. @@ -1256,7 +1269,8 @@ int phy_reset_after_clk_enable(struct phy_device *phydev); int phy_start_cable_test(struct phy_device *phydev, struct netlink_ext_ack *extack); int phy_start_cable_test_tdr(struct phy_device *phydev, - struct netlink_ext_ack *extack); + struct netlink_ext_ack *extack, + const struct phy_tdr_config *config); #else static inline int phy_start_cable_test(struct phy_device *phydev, @@ -1267,7 +1281,8 @@ int phy_start_cable_test(struct phy_device *phydev, } static inline int phy_start_cable_test_tdr(struct phy_device *phydev, - struct netlink_ext_ack *extack) + struct netlink_ext_ack *extack, + const struct phy_tdr_config *config) { NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); return -EOPNOTSUPP; diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 739faa7070c6..fc9051f2eeac 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -482,9 +482,22 @@ enum { /* CABLE TEST TDR */ +enum { + ETHTOOL_A_CABLE_TEST_TDR_CFG_UNSPEC, + ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST, /* u32 */ + ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST, /* u32 */ + ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP, /* u32 */ + ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR, /* u8 */ + + /* add new constants above here */ + __ETHTOOL_A_CABLE_TEST_TDR_CFG_CNT, + ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX = __ETHTOOL_A_CABLE_TEST_TDR_CFG_CNT - 1 +}; + enum { ETHTOOL_A_CABLE_TEST_TDR_UNSPEC, ETHTOOL_A_CABLE_TEST_TDR_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_CABLE_TEST_TDR_CFG, /* nest - *_TDR_CFG_* */ /* add new constants above here */ __ETHTOOL_A_CABLE_TEST_TDR_CNT, diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c index 390d0673ff01..9991688d7d1d 100644 --- a/net/ethtool/cabletest.c +++ b/net/ethtool/cabletest.c @@ -5,7 +5,11 @@ #include "netlink.h" #include "common.h" -/* CABLE_TEST_ACT */ +/* 802.3 standard allows 100 meters for BaseT cables. However longer + * cables might work, depending on the quality of the cables and the + * PHY. So allow testing for up to 150 meters. + */ +#define MAX_CABLE_LENGTH_CM (150 * 100) static const struct nla_policy cable_test_act_policy[ETHTOOL_A_CABLE_TEST_MAX + 1] = { @@ -203,16 +207,107 @@ err: } EXPORT_SYMBOL_GPL(ethnl_cable_test_fault_length); +struct cable_test_tdr_req_info { + struct ethnl_req_info base; +}; + +static const struct nla_policy +cable_test_tdr_act_cfg_policy[ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX + 1] = { + [ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST] = { .type = NLA_U32 }, + [ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST] = { .type = NLA_U32 }, + [ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP] = { .type = NLA_U32 }, + [ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR] = { .type = NLA_U8 }, +}; + static const struct nla_policy cable_test_tdr_act_policy[ETHTOOL_A_CABLE_TEST_TDR_MAX + 1] = { [ETHTOOL_A_CABLE_TEST_TDR_UNSPEC] = { .type = NLA_REJECT }, [ETHTOOL_A_CABLE_TEST_TDR_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_CABLE_TEST_TDR_CFG] = { .type = NLA_NESTED }, }; +/* CABLE_TEST_TDR_ACT */ +int ethnl_act_cable_test_tdr_cfg(const struct nlattr *nest, + struct genl_info *info, + struct phy_tdr_config *cfg) +{ + struct nlattr *tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX + 1]; + int ret; + + ret = nla_parse_nested(tb, ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX, nest, + cable_test_tdr_act_cfg_policy, info->extack); + if (ret < 0) + return ret; + + if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST]) + cfg->first = nla_get_u32( + tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST]); + else + cfg->first = 100; + if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST]) + cfg->last = nla_get_u32(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST]); + else + cfg->last = MAX_CABLE_LENGTH_CM; + + if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP]) + cfg->step = nla_get_u32(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP]); + else + cfg->step = 100; + + if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR]) { + cfg->pair = nla_get_u8(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR]); + if (cfg->pair > ETHTOOL_A_CABLE_PAIR_D) { + NL_SET_ERR_MSG_ATTR( + info->extack, + tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR], + "invalid pair parameter"); + return -EINVAL; + } + } else { + cfg->pair = PHY_PAIR_ALL; + } + + if (cfg->first > MAX_CABLE_LENGTH_CM) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST], + "invalid first parameter"); + return -EINVAL; + } + + if (cfg->last > MAX_CABLE_LENGTH_CM) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST], + "invalid last parameter"); + return -EINVAL; + } + + if (cfg->first > cfg->last) { + NL_SET_ERR_MSG(info->extack, "invalid first/last parameter"); + return -EINVAL; + } + + if (!cfg->step) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP], + "invalid step parameter"); + return -EINVAL; + } + + if (cfg->step > (cfg->last - cfg->first)) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP], + "step parameter too big"); + return -EINVAL; + } + + return 0; +} + int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb[ETHTOOL_A_CABLE_TEST_TDR_MAX + 1]; struct ethnl_req_info req_info = {}; + struct phy_tdr_config cfg; struct net_device *dev; int ret; @@ -235,12 +330,17 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) goto out_dev_put; } + ret = ethnl_act_cable_test_tdr_cfg(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG], + info, &cfg); + if (ret) + goto out_dev_put; + rtnl_lock(); ret = ethnl_ops_begin(dev); if (ret < 0) goto out_rtnl; - ret = phy_start_cable_test_tdr(dev->phydev, info->extack); + ret = phy_start_cable_test_tdr(dev->phydev, info->extack, &cfg); ethnl_ops_complete(dev); -- cgit v1.2.3 From 33462e68231bccfe563a87614f4c4dd5d333837c Mon Sep 17 00:00:00 2001 From: Sergey Matyukevich Date: Fri, 24 Apr 2020 14:29:03 +0300 Subject: cfg80211: add support for TID specific AMSDU configuration This patch adds support to control per TID MSDU aggregation using the NL80211_TID_CONFIG_ATTR_AMSDU_CTRL attribute. Signed-off-by: Sergey Matyukevich Link: https://lore.kernel.org/r/20200424112905.26770-4-sergey.matyukevich.os@quantenna.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 +++- include/uapi/linux/nl80211.h | 10 +++++++--- net/wireless/nl80211.c | 8 ++++++++ 3 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index e71d4f690ef1..5cacf24cc9f0 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -640,8 +640,9 @@ struct cfg80211_chan_def { * @noack: noack configuration value for the TID * @retry_long: retry count value * @retry_short: retry count value - * @ampdu: Enable/Disable aggregation + * @ampdu: Enable/Disable MPDU aggregation * @rtscts: Enable/Disable RTS/CTS + * @amsdu: Enable/Disable MSDU aggregation */ struct cfg80211_tid_cfg { bool config_override; @@ -651,6 +652,7 @@ struct cfg80211_tid_cfg { u8 retry_long, retry_short; enum nl80211_tid_config ampdu; enum nl80211_tid_config rtscts; + enum nl80211_tid_config amsdu; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 9679d561f7d0..1ccb0bf657ec 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4844,12 +4844,15 @@ enum nl80211_tid_config { * &NL80211_CMD_SET_TID_CONFIG. Its type is u8, min value is 1 and * the max value is advertised by the driver in this attribute on * output in wiphy capabilities. - * @NL80211_TID_CONFIG_ATTR_AMPDU_CTRL: Enable/Disable aggregation for the TIDs - * specified in %NL80211_TID_CONFIG_ATTR_TIDS. Its type is u8, using - * the values from &nl80211_tid_config. + * @NL80211_TID_CONFIG_ATTR_AMPDU_CTRL: Enable/Disable MPDU aggregation + * for the TIDs specified in %NL80211_TID_CONFIG_ATTR_TIDS. + * Its type is u8, using the values from &nl80211_tid_config. * @NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL: Enable/Disable RTS_CTS for the TIDs * specified in %NL80211_TID_CONFIG_ATTR_TIDS. It is u8 type, using * the values from &nl80211_tid_config. + * @NL80211_TID_CONFIG_ATTR_AMSDU_CTRL: Enable/Disable MSDU aggregation + * for the TIDs specified in %NL80211_TID_CONFIG_ATTR_TIDS. + * Its type is u8, using the values from &nl80211_tid_config. */ enum nl80211_tid_config_attr { __NL80211_TID_CONFIG_ATTR_INVALID, @@ -4863,6 +4866,7 @@ enum nl80211_tid_config_attr { NL80211_TID_CONFIG_ATTR_RETRY_LONG, NL80211_TID_CONFIG_ATTR_AMPDU_CTRL, NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL, + NL80211_TID_CONFIG_ATTR_AMSDU_CTRL, /* keep last */ __NL80211_TID_CONFIG_ATTR_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index fa66d5b6f557..482a80b78844 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -343,6 +343,8 @@ nl80211_tid_config_attr_policy[NL80211_TID_CONFIG_ATTR_MAX + 1] = { NLA_POLICY_MAX(NLA_U8, NL80211_TID_CONFIG_DISABLE), [NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL] = NLA_POLICY_MAX(NLA_U8, NL80211_TID_CONFIG_DISABLE), + [NL80211_TID_CONFIG_ATTR_AMSDU_CTRL] = + NLA_POLICY_MAX(NLA_U8, NL80211_TID_CONFIG_DISABLE), }; static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { @@ -14080,6 +14082,12 @@ static int parse_tid_conf(struct cfg80211_registered_device *rdev, nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL]); } + if (attrs[NL80211_TID_CONFIG_ATTR_AMSDU_CTRL]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_AMSDU_CTRL); + tid_conf->amsdu = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_AMSDU_CTRL]); + } + if (peer) mask = rdev->wiphy.tid_config_support.peer; else -- cgit v1.2.3 From c03369558c435f7e82f7c06b0173fa73c1ed15c0 Mon Sep 17 00:00:00 2001 From: Sergey Matyukevich Date: Fri, 24 Apr 2020 14:29:04 +0300 Subject: nl80211: simplify peer specific TID configuration Current rule for applying TID configuration for specific peer looks overly complicated. No need to reject new TID configuration when override flag is specified. Another call with the same TID configuration, but without override flag, allows to apply new configuration anyway. Use the same approach as for the 'all peers' case: if override flag is specified, then reset existing TID configuration and immediately apply a new one. Signed-off-by: Sergey Matyukevich Link: https://lore.kernel.org/r/20200424112905.26770-5-sergey.matyukevich.os@quantenna.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 10 ++++------ net/wireless/nl80211.c | 5 +---- 2 files changed, 5 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 1ccb0bf657ec..d1b1d9e49887 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4823,12 +4823,10 @@ enum nl80211_tid_config { * (%NL80211_TID_CONFIG_ATTR_TIDS, %NL80211_TID_CONFIG_ATTR_OVERRIDE). * @NL80211_TID_CONFIG_ATTR_PEER_SUPP: same as the previous per-vif one, but * per peer instead. - * @NL80211_TID_CONFIG_ATTR_OVERRIDE: flag attribue, if no peer - * is selected, if set indicates that the new configuration overrides - * all previous peer configurations, otherwise previous peer specific - * configurations should be left untouched. If peer is selected then - * it will reset particular TID configuration of that peer and it will - * not accept other TID config attributes along with peer. + * @NL80211_TID_CONFIG_ATTR_OVERRIDE: flag attribue, if set indicates + * that the new configuration overrides all previous peer + * configurations, otherwise previous peer specific configurations + * should be left untouched. * @NL80211_TID_CONFIG_ATTR_TIDS: a bitmask value of TIDs (bit 0 to 7) * Its type is u16. * @NL80211_TID_CONFIG_ATTR_NOACK: Configure ack policy for the TID. diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 482a80b78844..258c621f651c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -14036,10 +14036,7 @@ static int parse_tid_conf(struct cfg80211_registered_device *rdev, if (rdev->ops->reset_tid_config) { err = rdev_reset_tid_config(rdev, dev, peer, tid_conf->tids); - /* If peer is there no other configuration will be - * allowed - */ - if (err || peer) + if (err) return err; } else { return -EINVAL; -- cgit v1.2.3 From 942ba88ba9c87f5e225574f1f0d6548f0105ed73 Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Thu, 30 Apr 2020 10:25:51 -0700 Subject: nl80211: add KHz frequency offset for most wifi commands cfg80211 recently gained the ability to understand a frequency offset component in KHz. Expose this in nl80211 through the new attributes NL80211_ATTR_WIPHY_FREQ_OFFSET, NL80211_FREQUENCY_ATTR_OFFSET, NL80211_ATTR_CENTER_FREQ1_OFFSET, and NL80211_BSS_FREQUENCY_OFFSET. These add support to send and receive a KHz offset component with the following NL80211 commands: - NL80211_CMD_FRAME - NL80211_CMD_GET_SCAN - NL80211_CMD_AUTHENTICATE - NL80211_CMD_ASSOCIATE - NL80211_CMD_CONNECT Along with any other command which takes a chandef, ie: - NL80211_CMD_SET_CHANNEL - NL80211_CMD_SET_WIPHY - NL80211_CMD_START_AP - NL80211_CMD_RADAR_DETECT - NL80211_CMD_NOTIFY_RADAR - NL80211_CMD_CHANNEL_SWITCH - NL80211_JOIN_IBSS - NL80211_CMD_REMAIN_ON_CHANNEL - NL80211_CMD_JOIN_OCB - NL80211_CMD_JOIN_MESH - NL80211_CMD_TDLS_CHANNEL_SWITCH If the driver advertises a band containing channels with frequency offset, it must also verify support for frequency offset channels in its cfg80211 ops, or return an error. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200430172554.18383-3-thomas@adapt-ip.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 50 ++++++++++++++++++---------- net/wireless/nl80211.c | 78 ++++++++++++++++++++++++++++++++------------ 2 files changed, 91 insertions(+), 37 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index d1b1d9e49887..b1cd132c1d27 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -296,13 +296,14 @@ * to get a list of all present wiphys. * @NL80211_CMD_SET_WIPHY: set wiphy parameters, needs %NL80211_ATTR_WIPHY or * %NL80211_ATTR_IFINDEX; can be used to set %NL80211_ATTR_WIPHY_NAME, - * %NL80211_ATTR_WIPHY_TXQ_PARAMS, %NL80211_ATTR_WIPHY_FREQ (and the - * attributes determining the channel width; this is used for setting - * monitor mode channel), %NL80211_ATTR_WIPHY_RETRY_SHORT, - * %NL80211_ATTR_WIPHY_RETRY_LONG, %NL80211_ATTR_WIPHY_FRAG_THRESHOLD, - * and/or %NL80211_ATTR_WIPHY_RTS_THRESHOLD. - * However, for setting the channel, see %NL80211_CMD_SET_CHANNEL - * instead, the support here is for backward compatibility only. + * %NL80211_ATTR_WIPHY_TXQ_PARAMS, %NL80211_ATTR_WIPHY_FREQ, + * %NL80211_ATTR_WIPHY_FREQ_OFFSET (and the attributes determining the + * channel width; this is used for setting monitor mode channel), + * %NL80211_ATTR_WIPHY_RETRY_SHORT, %NL80211_ATTR_WIPHY_RETRY_LONG, + * %NL80211_ATTR_WIPHY_FRAG_THRESHOLD, and/or + * %NL80211_ATTR_WIPHY_RTS_THRESHOLD. However, for setting the channel, + * see %NL80211_CMD_SET_CHANNEL instead, the support here is for backward + * compatibility only. * @NL80211_CMD_NEW_WIPHY: Newly created wiphy, response to get request * or rename notification. Has attributes %NL80211_ATTR_WIPHY and * %NL80211_ATTR_WIPHY_NAME. @@ -351,7 +352,8 @@ * %NL80211_ATTR_AUTH_TYPE, %NL80211_ATTR_INACTIVITY_TIMEOUT, * %NL80211_ATTR_ACL_POLICY and %NL80211_ATTR_MAC_ADDRS. * The channel to use can be set on the interface or be given using the - * %NL80211_ATTR_WIPHY_FREQ and the attributes determining channel width. + * %NL80211_ATTR_WIPHY_FREQ and %NL80211_ATTR_WIPHY_FREQ_OFFSET, and the + * attributes determining channel width. * @NL80211_CMD_NEW_BEACON: old alias for %NL80211_CMD_START_AP * @NL80211_CMD_STOP_AP: Stop AP operation on the given interface * @NL80211_CMD_DEL_BEACON: old alias for %NL80211_CMD_STOP_AP @@ -536,11 +538,12 @@ * interface. %NL80211_ATTR_MAC is used to specify PeerSTAAddress (and * BSSID in case of station mode). %NL80211_ATTR_SSID is used to specify * the SSID (mainly for association, but is included in authentication - * request, too, to help BSS selection. %NL80211_ATTR_WIPHY_FREQ is used - * to specify the frequence of the channel in MHz. %NL80211_ATTR_AUTH_TYPE - * is used to specify the authentication type. %NL80211_ATTR_IE is used to - * define IEs (VendorSpecificInfo, but also including RSN IE and FT IEs) - * to be added to the frame. + * request, too, to help BSS selection. %NL80211_ATTR_WIPHY_FREQ + + * %NL80211_ATTR_WIPHY_FREQ_OFFSET is used to specify the frequence of the + * channel in MHz. %NL80211_ATTR_AUTH_TYPE is used to specify the + * authentication type. %NL80211_ATTR_IE is used to define IEs + * (VendorSpecificInfo, but also including RSN IE and FT IEs) to be added + * to the frame. * When used as an event, this reports reception of an Authentication * frame in station and IBSS modes when the local MLME processed the * frame, i.e., it was for the local STA and was received in correct @@ -595,8 +598,9 @@ * requests to connect to a specified network but without separating * auth and assoc steps. For this, you need to specify the SSID in a * %NL80211_ATTR_SSID attribute, and can optionally specify the association - * IEs in %NL80211_ATTR_IE, %NL80211_ATTR_AUTH_TYPE, %NL80211_ATTR_USE_MFP, - * %NL80211_ATTR_MAC, %NL80211_ATTR_WIPHY_FREQ, %NL80211_ATTR_CONTROL_PORT, + * IEs in %NL80211_ATTR_IE, %NL80211_ATTR_AUTH_TYPE, + * %NL80211_ATTR_USE_MFP, %NL80211_ATTR_MAC, %NL80211_ATTR_WIPHY_FREQ, + * %NL80211_ATTR_WIPHY_FREQ_OFFSET, %NL80211_ATTR_CONTROL_PORT, * %NL80211_ATTR_CONTROL_PORT_ETHERTYPE, * %NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT, * %NL80211_ATTR_CONTROL_PORT_OVER_NL80211, %NL80211_ATTR_MAC_HINT, and @@ -1433,7 +1437,8 @@ enum nl80211_commands { * of &enum nl80211_chan_width, describing the channel width. See the * documentation of the enum for more information. * @NL80211_ATTR_CENTER_FREQ1: Center frequency of the first part of the - * channel, used for anything but 20 MHz bandwidth + * channel, used for anything but 20 MHz bandwidth. In S1G this is the + * operating channel center frequency. * @NL80211_ATTR_CENTER_FREQ2: Center frequency of the second part of the * channel, used only for 80+80 MHz bandwidth * @NL80211_ATTR_WIPHY_CHANNEL_TYPE: included with NL80211_ATTR_WIPHY_FREQ @@ -2480,9 +2485,14 @@ enum nl80211_commands { * entry without having to force a disconnection after the PMK timeout. If * no roaming occurs between the reauth threshold and PMK expiration, * disassociation is still forced. - * * @NL80211_ATTR_RECEIVE_MULTICAST: multicast flag for the * %NL80211_CMD_REGISTER_FRAME command, see the description there. + * @NL80211_ATTR_WIPHY_FREQ_OFFSET: offset of the associated + * %NL80211_ATTR_WIPHY_FREQ in positive KHz. Only valid when supplied with + * an %NL80211_ATTR_WIPHY_FREQ_OFFSET. + * @NL80211_ATTR_CENTER_FREQ1_OFFSET: Center frequency offset in KHz for the + * first channel segment specified in %NL80211_ATTR_CENTER_FREQ1. + * * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined @@ -2960,6 +2970,8 @@ enum nl80211_attrs { NL80211_ATTR_PMK_REAUTH_THRESHOLD, NL80211_ATTR_RECEIVE_MULTICAST, + NL80211_ATTR_WIPHY_FREQ_OFFSET, + NL80211_ATTR_CENTER_FREQ1_OFFSET, /* add attributes here, update the policy in nl80211.c */ @@ -3682,6 +3694,7 @@ enum nl80211_wmm_rule { * (see &enum nl80211_wmm_rule) * @NL80211_FREQUENCY_ATTR_NO_HE: HE operation is not allowed on this channel * in current regulatory domain. + * @NL80211_FREQUENCY_ATTR_OFFSET: frequency offset in KHz * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -3712,6 +3725,7 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_NO_10MHZ, NL80211_FREQUENCY_ATTR_WMM, NL80211_FREQUENCY_ATTR_NO_HE, + NL80211_FREQUENCY_ATTR_OFFSET, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, @@ -4482,6 +4496,7 @@ enum nl80211_bss_scan_width { * @NL80211_BSS_CHAIN_SIGNAL: per-chain signal strength of last BSS update. * Contains a nested array of signal strength attributes (u8, dBm), * using the nesting index as the antenna number. + * @NL80211_BSS_FREQUENCY_OFFSET: frequency offset in KHz * @__NL80211_BSS_AFTER_LAST: internal * @NL80211_BSS_MAX: highest BSS attribute */ @@ -4506,6 +4521,7 @@ enum nl80211_bss { NL80211_BSS_PARENT_TSF, NL80211_BSS_PARENT_BSSID, NL80211_BSS_CHAIN_SIGNAL, + NL80211_BSS_FREQUENCY_OFFSET, /* keep last */ __NL80211_BSS_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index f6523f1485a3..87d7efd186d0 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -365,6 +365,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_CHANNEL_WIDTH] = { .type = NLA_U32 }, [NL80211_ATTR_CENTER_FREQ1] = { .type = NLA_U32 }, + [NL80211_ATTR_CENTER_FREQ1_OFFSET] = NLA_POLICY_RANGE(NLA_U32, 0, 999), [NL80211_ATTR_CENTER_FREQ2] = { .type = NLA_U32 }, [NL80211_ATTR_WIPHY_RETRY_SHORT] = NLA_POLICY_MIN(NLA_U8, 1), @@ -638,6 +639,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_PMK_LIFETIME] = NLA_POLICY_MIN(NLA_U32, 1), [NL80211_ATTR_PMK_REAUTH_THRESHOLD] = NLA_POLICY_RANGE(NLA_U8, 1, 100), [NL80211_ATTR_RECEIVE_MULTICAST] = { .type = NLA_FLAG }, + [NL80211_ATTR_WIPHY_FREQ_OFFSET] = NLA_POLICY_RANGE(NLA_U32, 0, 999), }; /* policy for the key attributes */ @@ -904,6 +906,9 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, chan->center_freq)) goto nla_put_failure; + if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_OFFSET, chan->freq_offset)) + goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_DISABLED) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_DISABLED)) goto nla_put_failure; @@ -1309,13 +1314,11 @@ static int nl80211_key_allowed(struct wireless_dev *wdev) } static struct ieee80211_channel *nl80211_get_valid_chan(struct wiphy *wiphy, - struct nlattr *tb) + u32 freq) { struct ieee80211_channel *chan; - if (tb == NULL) - return NULL; - chan = ieee80211_get_channel(wiphy, nla_get_u32(tb)); + chan = ieee80211_get_channel_khz(wiphy, freq); if (!chan || chan->flags & IEEE80211_CHAN_DISABLED) return NULL; return chan; @@ -2770,13 +2773,17 @@ int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, if (!attrs[NL80211_ATTR_WIPHY_FREQ]) return -EINVAL; - control_freq = nla_get_u32(attrs[NL80211_ATTR_WIPHY_FREQ]); + control_freq = MHZ_TO_KHZ( + nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ])); + if (info->attrs[NL80211_ATTR_WIPHY_FREQ_OFFSET]) + control_freq += + nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ_OFFSET]); memset(chandef, 0, sizeof(*chandef)); - - chandef->chan = ieee80211_get_channel(&rdev->wiphy, control_freq); + chandef->chan = ieee80211_get_channel_khz(&rdev->wiphy, control_freq); chandef->width = NL80211_CHAN_WIDTH_20_NOHT; - chandef->center_freq1 = control_freq; + chandef->center_freq1 = KHZ_TO_MHZ(control_freq); + chandef->freq1_offset = control_freq % 1000; chandef->center_freq2 = 0; /* Primary channel not allowed */ @@ -2824,9 +2831,15 @@ int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, } else if (attrs[NL80211_ATTR_CHANNEL_WIDTH]) { chandef->width = nla_get_u32(attrs[NL80211_ATTR_CHANNEL_WIDTH]); - if (attrs[NL80211_ATTR_CENTER_FREQ1]) + if (attrs[NL80211_ATTR_CENTER_FREQ1]) { chandef->center_freq1 = nla_get_u32(attrs[NL80211_ATTR_CENTER_FREQ1]); + if (attrs[NL80211_ATTR_CENTER_FREQ1_OFFSET]) + chandef->freq1_offset = nla_get_u32( + attrs[NL80211_ATTR_CENTER_FREQ1_OFFSET]); + else + chandef->freq1_offset = 0; + } if (attrs[NL80211_ATTR_CENTER_FREQ2]) chandef->center_freq2 = nla_get_u32(attrs[NL80211_ATTR_CENTER_FREQ2]); @@ -3259,6 +3272,9 @@ static int nl80211_send_chandef(struct sk_buff *msg, if (nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, chandef->chan->center_freq)) return -ENOBUFS; + if (nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ_OFFSET, + chandef->chan->freq_offset)) + return -ENOBUFS; switch (chandef->width) { case NL80211_CHAN_WIDTH_20_NOHT: case NL80211_CHAN_WIDTH_20: @@ -8873,6 +8889,8 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, goto nla_put_failure; if (nla_put_u16(msg, NL80211_BSS_CAPABILITY, res->capability) || nla_put_u32(msg, NL80211_BSS_FREQUENCY, res->channel->center_freq) || + nla_put_u32(msg, NL80211_BSS_FREQUENCY_OFFSET, + res->channel->freq_offset) || nla_put_u32(msg, NL80211_BSS_CHAN_WIDTH, res->scan_width) || nla_put_u32(msg, NL80211_BSS_SEEN_MS_AGO, jiffies_to_msecs(jiffies - intbss->ts))) @@ -9141,6 +9159,7 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) enum nl80211_auth_type auth_type; struct key_parse key; bool local_state_change; + u32 freq; if (!info->attrs[NL80211_ATTR_MAC]) return -EINVAL; @@ -9197,8 +9216,12 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) return -EOPNOTSUPP; bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); - chan = nl80211_get_valid_chan(&rdev->wiphy, - info->attrs[NL80211_ATTR_WIPHY_FREQ]); + freq = MHZ_TO_KHZ(nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ])); + if (info->attrs[NL80211_ATTR_WIPHY_FREQ_OFFSET]) + freq += + nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ_OFFSET]); + + chan = nl80211_get_valid_chan(&rdev->wiphy, freq); if (!chan) return -EINVAL; @@ -9388,6 +9411,7 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) struct cfg80211_assoc_request req = {}; const u8 *bssid, *ssid; int err, ssid_len = 0; + u32 freq; if (dev->ieee80211_ptr->conn_owner_nlportid && dev->ieee80211_ptr->conn_owner_nlportid != info->snd_portid) @@ -9407,8 +9431,11 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); - chan = nl80211_get_valid_chan(&rdev->wiphy, - info->attrs[NL80211_ATTR_WIPHY_FREQ]); + freq = MHZ_TO_KHZ(nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ])); + if (info->attrs[NL80211_ATTR_WIPHY_FREQ_OFFSET]) + freq += + nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ_OFFSET]); + chan = nl80211_get_valid_chan(&rdev->wiphy, freq); if (!chan) return -EINVAL; @@ -10088,6 +10115,7 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) struct cfg80211_connect_params connect; struct wiphy *wiphy; struct cfg80211_cached_keys *connkeys = NULL; + u32 freq = 0; int err; memset(&connect, 0, sizeof(connect)); @@ -10158,14 +10186,21 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) connect.prev_bssid = nla_data(info->attrs[NL80211_ATTR_PREV_BSSID]); - if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { - connect.channel = nl80211_get_valid_chan( - wiphy, info->attrs[NL80211_ATTR_WIPHY_FREQ]); + if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) + freq = MHZ_TO_KHZ(nla_get_u32( + info->attrs[NL80211_ATTR_WIPHY_FREQ])); + if (info->attrs[NL80211_ATTR_WIPHY_FREQ_OFFSET]) + freq += + nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ_OFFSET]); + + if (freq) { + connect.channel = nl80211_get_valid_chan(wiphy, freq); if (!connect.channel) return -EINVAL; } else if (info->attrs[NL80211_ATTR_WIPHY_FREQ_HINT]) { - connect.channel_hint = nl80211_get_valid_chan( - wiphy, info->attrs[NL80211_ATTR_WIPHY_FREQ_HINT]); + freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ_HINT]); + freq = MHZ_TO_KHZ(freq); + connect.channel_hint = nl80211_get_valid_chan(wiphy, freq); if (!connect.channel_hint) return -EINVAL; } @@ -16215,6 +16250,7 @@ int nl80211_send_mgmt(struct cfg80211_registered_device *rdev, nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev), NL80211_ATTR_PAD) || nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, KHZ_TO_MHZ(freq)) || + nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ_OFFSET, freq % 1000) || (sig_dbm && nla_put_u32(msg, NL80211_ATTR_RX_SIGNAL_DBM, sig_dbm)) || nla_put(msg, NL80211_ATTR_FRAME, len, buf) || @@ -16864,8 +16900,10 @@ void cfg80211_report_obss_beacon_khz(struct wiphy *wiphy, const u8 *frame, if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || (freq && - nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, - KHZ_TO_MHZ(freq))) || + (nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, + KHZ_TO_MHZ(freq)) || + nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ_OFFSET, + freq % 1000))) || (sig_dbm && nla_put_u32(msg, NL80211_ATTR_RX_SIGNAL_DBM, sig_dbm)) || nla_put(msg, NL80211_ATTR_FRAME, len, frame)) -- cgit v1.2.3 From 2032f3b2f943256ff40df23182913dfc7e73ec6a Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Thu, 30 Apr 2020 10:25:52 -0700 Subject: nl80211: support scan frequencies in KHz If the driver advertises NL80211_EXT_FEATURE_SCAN_FREQ_KHZ userspace can omit NL80211_ATTR_SCAN_FREQUENCIES in favor of an NL80211_ATTR_SCAN_FREQ_KHZ. To get scan results in KHz userspace must also set the NL80211_SCAN_FLAG_FREQ_KHZ. This lets nl80211 remain compatible with older userspaces while not requring and sending redundant (and potentially incorrect) scan frequency sets. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200430172554.18383-4-thomas@adapt-ip.com [use just nla_nest_start() (not _noflag) for NL80211_ATTR_SCAN_FREQ_KHZ] Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 13 ++++++++++- net/mac80211/main.c | 2 ++ net/wireless/nl80211.c | 51 +++++++++++++++++++++++++++++++++----------- 3 files changed, 53 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index b1cd132c1d27..47d39b6a073d 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2492,7 +2492,7 @@ enum nl80211_commands { * an %NL80211_ATTR_WIPHY_FREQ_OFFSET. * @NL80211_ATTR_CENTER_FREQ1_OFFSET: Center frequency offset in KHz for the * first channel segment specified in %NL80211_ATTR_CENTER_FREQ1. - * + * @NL80211_ATTR_SCAN_FREQ_KHZ: nested attribute with KHz frequencies * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined @@ -2972,6 +2972,7 @@ enum nl80211_attrs { NL80211_ATTR_RECEIVE_MULTICAST, NL80211_ATTR_WIPHY_FREQ_OFFSET, NL80211_ATTR_CENTER_FREQ1_OFFSET, + NL80211_ATTR_SCAN_FREQ_KHZ, /* add attributes here, update the policy in nl80211.c */ @@ -5723,6 +5724,11 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_MULTICAST_REGISTRATIONS: management frame registrations * are possible for multicast frames and those will be reported properly. * + * @NL80211_EXT_FEATURE_SCAN_FREQ_KHZ: This driver supports receiving and + * reporting scan request with %NL80211_ATTR_SCAN_FREQ_KHZ. In order to + * report %NL80211_ATTR_SCAN_FREQ_KHZ, %NL80211_SCAN_FLAG_FREQ_KHZ must be + * included in the scan request. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5776,6 +5782,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_DEL_IBSS_STA, NL80211_EXT_FEATURE_MULTICAST_REGISTRATIONS, NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT, + NL80211_EXT_FEATURE_SCAN_FREQ_KHZ, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -5887,6 +5894,9 @@ enum nl80211_timeout_reason { * @NL80211_SCAN_FLAG_MIN_PREQ_CONTENT: minimize probe request content to * only have supported rates and no additional capabilities (unless * added by userspace explicitly.) + * @NL80211_SCAN_FLAG_FREQ_KHZ: report scan results with + * %NL80211_ATTR_SCAN_FREQ_KHZ. This also means + * %NL80211_ATTR_SCAN_FREQUENCIES will not be included. */ enum nl80211_scan_flags { NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0, @@ -5902,6 +5912,7 @@ enum nl80211_scan_flags { NL80211_SCAN_FLAG_HIGH_ACCURACY = 1<<10, NL80211_SCAN_FLAG_RANDOM_SN = 1<<11, NL80211_SCAN_FLAG_MIN_PREQ_CONTENT = 1<<12, + NL80211_SCAN_FLAG_FREQ_KHZ = 1<<13, }; /** diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 06c90d360633..ac74bd780b42 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -596,6 +596,8 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211); wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CONTROL_PORT_NO_PREAUTH); + wiphy_ext_feature_set(wiphy, + NL80211_EXT_FEATURE_SCAN_FREQ_KHZ); if (!ops->hw_scan) { wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN | diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 87d7efd186d0..84bfa147769a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -640,6 +640,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_PMK_REAUTH_THRESHOLD] = NLA_POLICY_RANGE(NLA_U8, 1, 100), [NL80211_ATTR_RECEIVE_MULTICAST] = { .type = NLA_FLAG }, [NL80211_ATTR_WIPHY_FREQ_OFFSET] = NLA_POLICY_RANGE(NLA_U32, 0, 999), + [NL80211_ATTR_SCAN_FREQ_KHZ] = { .type = NLA_NESTED }, }; /* policy for the key attributes */ @@ -7719,6 +7720,8 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct wireless_dev *wdev = info->user_ptr[1]; struct cfg80211_scan_request *request; + struct nlattr *scan_freqs = NULL; + bool scan_freqs_khz = false; struct nlattr *attr; struct wiphy *wiphy; int err, tmp, n_ssids = 0, n_channels, i; @@ -7737,9 +7740,17 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) goto unlock; } - if (info->attrs[NL80211_ATTR_SCAN_FREQUENCIES]) { - n_channels = validate_scan_freqs( - info->attrs[NL80211_ATTR_SCAN_FREQUENCIES]); + if (info->attrs[NL80211_ATTR_SCAN_FREQ_KHZ]) { + if (!wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_SCAN_FREQ_KHZ)) + return -EOPNOTSUPP; + scan_freqs = info->attrs[NL80211_ATTR_SCAN_FREQ_KHZ]; + scan_freqs_khz = true; + } else if (info->attrs[NL80211_ATTR_SCAN_FREQUENCIES]) + scan_freqs = info->attrs[NL80211_ATTR_SCAN_FREQUENCIES]; + + if (scan_freqs) { + n_channels = validate_scan_freqs(scan_freqs); if (!n_channels) { err = -EINVAL; goto unlock; @@ -7787,13 +7798,16 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) } i = 0; - if (info->attrs[NL80211_ATTR_SCAN_FREQUENCIES]) { + if (scan_freqs) { /* user specified, bail out if channel not found */ - nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_FREQUENCIES], tmp) { + nla_for_each_nested(attr, scan_freqs, tmp) { struct ieee80211_channel *chan; + int freq = nla_get_u32(attr); - chan = ieee80211_get_channel(wiphy, nla_get_u32(attr)); + if (!scan_freqs_khz) + freq = MHZ_TO_KHZ(freq); + chan = ieee80211_get_channel_khz(wiphy, freq); if (!chan) { err = -EINVAL; goto out_free; @@ -15231,14 +15245,27 @@ static int nl80211_add_scan_req(struct sk_buff *msg, } nla_nest_end(msg, nest); - nest = nla_nest_start_noflag(msg, NL80211_ATTR_SCAN_FREQUENCIES); - if (!nest) - goto nla_put_failure; - for (i = 0; i < req->n_channels; i++) { - if (nla_put_u32(msg, i, req->channels[i]->center_freq)) + if (req->flags & NL80211_SCAN_FLAG_FREQ_KHZ) { + nest = nla_nest_start(msg, NL80211_ATTR_SCAN_FREQ_KHZ); + if (!nest) + goto nla_put_failure; + for (i = 0; i < req->n_channels; i++) { + if (nla_put_u32(msg, i, + ieee80211_channel_to_khz(req->channels[i]))) + goto nla_put_failure; + } + nla_nest_end(msg, nest); + } else { + nest = nla_nest_start_noflag(msg, + NL80211_ATTR_SCAN_FREQUENCIES); + if (!nest) goto nla_put_failure; + for (i = 0; i < req->n_channels; i++) { + if (nla_put_u32(msg, i, req->channels[i]->center_freq)) + goto nla_put_failure; + } + nla_nest_end(msg, nest); } - nla_nest_end(msg, nest); if (req->ie && nla_put(msg, NL80211_ATTR_IE, req->ie_len, req->ie)) -- cgit v1.2.3 From dca9ca2d588bd2c0989c671f048540b82e57cf1e Mon Sep 17 00:00:00 2001 From: Markus Theil Date: Fri, 8 May 2020 16:42:00 +0200 Subject: nl80211: add ability to report TX status for control port TX This adds the necessary capabilities in nl80211 to allow drivers to assign a cookie to control port TX frames (returned via extack in the netlink ACK message of the command) and then later report the frame's status. Signed-off-by: Markus Theil Link: https://lore.kernel.org/r/20200508144202.7678-2-markus.theil@tu-ilmenau.de [use extack cookie instead of explicit message, recombine patches] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 20 +++++++++++++++++++- include/uapi/linux/nl80211.h | 12 ++++++++++++ net/mac80211/ieee80211_i.h | 3 ++- net/mac80211/tx.c | 3 ++- net/wireless/nl80211.c | 41 +++++++++++++++++++++++++++++++++-------- net/wireless/rdev-ops.h | 9 ++++++--- net/wireless/trace.h | 17 +++++++++++++++++ 7 files changed, 91 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 021366cfb2b0..f842f3652026 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4069,7 +4069,8 @@ struct cfg80211_ops { struct net_device *dev, const u8 *buf, size_t len, const u8 *dest, const __be16 proto, - const bool noencrypt); + const bool noencrypt, + u64 *cookie); int (*get_ftm_responder_stats)(struct wiphy *wiphy, struct net_device *dev, @@ -7049,6 +7050,23 @@ static inline bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, const u8 *buf, size_t len, bool ack, gfp_t gfp); +/** + * cfg80211_control_port_tx_status - notification of TX status for control + * port frames + * @wdev: wireless device receiving the frame + * @cookie: Cookie returned by cfg80211_ops::tx_control_port() + * @buf: Data frame (header + body) + * @len: length of the frame data + * @ack: Whether frame was acknowledged + * @gfp: context flags + * + * This function is called whenever a control port frame was requested to be + * transmitted with cfg80211_ops::tx_control_port() to report the TX status of + * the transmission attempt. + */ +void cfg80211_control_port_tx_status(struct wireless_dev *wdev, u64 cookie, + const u8 *buf, size_t len, bool ack, + gfp_t gfp); /** * cfg80211_rx_control_port - notification about a received control port frame diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 47d39b6a073d..0f324b6b81cc 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1164,6 +1164,12 @@ * dropped because it did not include a valid MME MIC while beacon * protection was enabled (BIGTK configured in station mode). * + * @NL80211_CMD_CONTROL_PORT_FRAME_TX_STATUS: Report TX status of a control + * port frame transmitted with %NL80211_CMD_CONTROL_PORT_FRAME. + * %NL80211_ATTR_COOKIE identifies the TX command and %NL80211_ATTR_FRAME + * includes the contents of the frame. %NL80211_ATTR_ACK flag is included + * if the recipient acknowledged the frame. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1392,6 +1398,8 @@ enum nl80211_commands { NL80211_CMD_UNPROT_BEACON, + NL80211_CMD_CONTROL_PORT_FRAME_TX_STATUS, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -5729,6 +5737,9 @@ enum nl80211_feature_flags { * report %NL80211_ATTR_SCAN_FREQ_KHZ, %NL80211_SCAN_FLAG_FREQ_KHZ must be * included in the scan request. * + * @NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_TX_STATUS: The driver + * can report tx status for control port over nl80211 tx operations. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5783,6 +5794,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_MULTICAST_REGISTRATIONS, NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT, NL80211_EXT_FEATURE_SCAN_FREQ_KHZ, + NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_TX_STATUS, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 2d1b6cb75497..b87dc873825b 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1800,7 +1800,8 @@ void ieee80211_check_fast_xmit_iface(struct ieee80211_sub_if_data *sdata); void ieee80211_clear_fast_xmit(struct sta_info *sta); int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, const u8 *buf, size_t len, - const u8 *dest, __be16 proto, bool unencrypted); + const u8 *dest, __be16 proto, bool unencrypted, + u64 *cookie); int ieee80211_probe_mesh_link(struct wiphy *wiphy, struct net_device *dev, const u8 *buf, size_t len); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 47f460c8bd74..5931128e1855 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -5339,7 +5339,8 @@ void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, const u8 *buf, size_t len, - const u8 *dest, __be16 proto, bool unencrypted) + const u8 *dest, __be16 proto, bool unencrypted, + u64 *cookie) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 84bfa147769a..7ea764865546 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -13866,6 +13866,7 @@ static int nl80211_external_auth(struct sk_buff *skb, struct genl_info *info) static int nl80211_tx_control_port(struct sk_buff *skb, struct genl_info *info) { + bool dont_wait_for_ack = info->attrs[NL80211_ATTR_DONT_WAIT_FOR_ACK]; struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -13874,6 +13875,7 @@ static int nl80211_tx_control_port(struct sk_buff *skb, struct genl_info *info) u8 *dest; u16 proto; bool noencrypt; + u64 cookie = 0; int err; if (!wiphy_ext_feature_isset(&rdev->wiphy, @@ -13918,9 +13920,12 @@ static int nl80211_tx_control_port(struct sk_buff *skb, struct genl_info *info) noencrypt = nla_get_flag(info->attrs[NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT]); - return rdev_tx_control_port(rdev, dev, buf, len, - dest, cpu_to_be16(proto), noencrypt); - + err = rdev_tx_control_port(rdev, dev, buf, len, + dest, cpu_to_be16(proto), noencrypt, + dont_wait_for_ack ? NULL : &cookie); + if (!err && !dont_wait_for_ack) + nl_set_extack_cookie_u64(info->extack, cookie); + return err; out: wdev_unlock(wdev); return err; @@ -16294,8 +16299,9 @@ int nl80211_send_mgmt(struct cfg80211_registered_device *rdev, return -ENOBUFS; } -void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, - const u8 *buf, size_t len, bool ack, gfp_t gfp) +static void nl80211_frame_tx_status(struct wireless_dev *wdev, u64 cookie, + const u8 *buf, size_t len, bool ack, + gfp_t gfp, enum nl80211_commands command) { struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); @@ -16303,13 +16309,16 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, struct sk_buff *msg; void *hdr; - trace_cfg80211_mgmt_tx_status(wdev, cookie, ack); + if (command == NL80211_CMD_FRAME_TX_STATUS) + trace_cfg80211_mgmt_tx_status(wdev, cookie, ack); + else + trace_cfg80211_control_port_tx_status(wdev, cookie, ack); msg = nlmsg_new(100 + len, gfp); if (!msg) return; - hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_FRAME_TX_STATUS); + hdr = nl80211hdr_put(msg, 0, 0, 0, command); if (!hdr) { nlmsg_free(msg); return; @@ -16332,9 +16341,25 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, NL80211_MCGRP_MLME, gfp); return; - nla_put_failure: +nla_put_failure: nlmsg_free(msg); } + +void cfg80211_control_port_tx_status(struct wireless_dev *wdev, u64 cookie, + const u8 *buf, size_t len, bool ack, + gfp_t gfp) +{ + nl80211_frame_tx_status(wdev, cookie, buf, len, ack, gfp, + NL80211_CMD_CONTROL_PORT_FRAME_TX_STATUS); +} +EXPORT_SYMBOL(cfg80211_control_port_tx_status); + +void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, + const u8 *buf, size_t len, bool ack, gfp_t gfp) +{ + nl80211_frame_tx_status(wdev, cookie, buf, len, ack, gfp, + NL80211_CMD_FRAME_TX_STATUS); +} EXPORT_SYMBOL(cfg80211_mgmt_tx_status); static int __nl80211_rx_control_port(struct net_device *dev, diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index df5142e86c4f..950d57494168 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -748,14 +748,17 @@ static inline int rdev_tx_control_port(struct cfg80211_registered_device *rdev, struct net_device *dev, const void *buf, size_t len, const u8 *dest, __be16 proto, - const bool noencrypt) + const bool noencrypt, u64 *cookie) { int ret; trace_rdev_tx_control_port(&rdev->wiphy, dev, buf, len, dest, proto, noencrypt); ret = rdev->ops->tx_control_port(&rdev->wiphy, dev, buf, len, - dest, proto, noencrypt); - trace_rdev_return_int(&rdev->wiphy, ret); + dest, proto, noencrypt, cookie); + if (cookie) + trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); + else + trace_rdev_return_int(&rdev->wiphy, ret); return ret; } diff --git a/net/wireless/trace.h b/net/wireless/trace.h index f2ab44a2a3e4..b23cab016521 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2861,6 +2861,23 @@ TRACE_EVENT(cfg80211_mgmt_tx_status, WDEV_PR_ARG, __entry->cookie, BOOL_TO_STR(__entry->ack)) ); +TRACE_EVENT(cfg80211_control_port_tx_status, + TP_PROTO(struct wireless_dev *wdev, u64 cookie, bool ack), + TP_ARGS(wdev, cookie, ack), + TP_STRUCT__entry( + WDEV_ENTRY + __field(u64, cookie) + __field(bool, ack) + ), + TP_fast_assign( + WDEV_ASSIGN; + __entry->cookie = cookie; + __entry->ack = ack; + ), + TP_printk(WDEV_PR_FMT", cookie: %llu, ack: %s", + WDEV_PR_ARG, __entry->cookie, BOOL_TO_STR(__entry->ack)) +); + TRACE_EVENT(cfg80211_rx_control_port, TP_PROTO(struct net_device *netdev, struct sk_buff *skb, bool unencrypted), -- cgit v1.2.3 From 9a5f6488623730dc16cca0836ade23869761adee Mon Sep 17 00:00:00 2001 From: Tamizh Chelvam Date: Wed, 13 May 2020 13:41:44 +0530 Subject: nl80211: Add support to configure TID specific Tx rate configuration This patch adds support to configure per TID Tx Rate configuration through NL80211_TID_CONFIG_ATTR_TX_RATE* attributes. And it uses nl80211_parse_tx_bitrate_mask api to validate the Tx rate mask. Signed-off-by: Tamizh Chelvam Link: https://lore.kernel.org/r/1589357504-10175-1-git-send-email-tamizhr@codeaurora.org Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 29 +++++++++++++---------- include/uapi/linux/nl80211.h | 21 +++++++++++++++++ net/wireless/nl80211.c | 56 +++++++++++++++++++++++++++++++++----------- 3 files changed, 80 insertions(+), 26 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f842f3652026..e2dbc9c02ef3 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -630,6 +630,19 @@ struct cfg80211_chan_def { u16 freq1_offset; }; +/* + * cfg80211_bitrate_mask - masks for bitrate control + */ +struct cfg80211_bitrate_mask { + struct { + u32 legacy; + u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN]; + u16 vht_mcs[NL80211_VHT_NSS_MAX]; + enum nl80211_txrate_gi gi; + } control[NUM_NL80211_BANDS]; +}; + + /** * struct cfg80211_tid_cfg - TID specific configuration * @config_override: Flag to notify driver to reset TID configuration @@ -643,6 +656,8 @@ struct cfg80211_chan_def { * @ampdu: Enable/Disable MPDU aggregation * @rtscts: Enable/Disable RTS/CTS * @amsdu: Enable/Disable MSDU aggregation + * @txrate_type: Tx bitrate mask type + * @txrate_mask: Tx bitrate to be applied for the TID */ struct cfg80211_tid_cfg { bool config_override; @@ -653,6 +668,8 @@ struct cfg80211_tid_cfg { enum nl80211_tid_config ampdu; enum nl80211_tid_config rtscts; enum nl80211_tid_config amsdu; + enum nl80211_tx_rate_setting txrate_type; + struct cfg80211_bitrate_mask txrate_mask; }; /** @@ -1007,18 +1024,6 @@ struct cfg80211_acl_data { struct mac_address mac_addrs[]; }; -/* - * cfg80211_bitrate_mask - masks for bitrate control - */ -struct cfg80211_bitrate_mask { - struct { - u32 legacy; - u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN]; - u16 vht_mcs[NL80211_VHT_NSS_MAX]; - enum nl80211_txrate_gi gi; - } control[NUM_NL80211_BANDS]; -}; - /** * enum cfg80211_ap_settings_flags - AP settings flags * diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 0f324b6b81cc..c14666b75e57 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4841,6 +4841,17 @@ enum nl80211_tid_config { NL80211_TID_CONFIG_DISABLE, }; +/* enum nl80211_tx_rate_setting - TX rate configuration type + * @NL80211_TX_RATE_AUTOMATIC: automatically determine TX rate + * @NL80211_TX_RATE_LIMITED: limit the TX rate by the TX rate parameter + * @NL80211_TX_RATE_FIXED: fix TX rate to the TX rate parameter + */ +enum nl80211_tx_rate_setting { + NL80211_TX_RATE_AUTOMATIC, + NL80211_TX_RATE_LIMITED, + NL80211_TX_RATE_FIXED, +}; + /* enum nl80211_tid_config_attr - TID specific configuration. * @NL80211_TID_CONFIG_ATTR_PAD: pad attribute for 64-bit values * @NL80211_TID_CONFIG_ATTR_VIF_SUPP: a bitmap (u64) of attributes supported @@ -4876,6 +4887,14 @@ enum nl80211_tid_config { * @NL80211_TID_CONFIG_ATTR_AMSDU_CTRL: Enable/Disable MSDU aggregation * for the TIDs specified in %NL80211_TID_CONFIG_ATTR_TIDS. * Its type is u8, using the values from &nl80211_tid_config. + * @NL80211_TID_CONFIG_ATTR_TX_RATE_TYPE: This attribute will be useful + * to notfiy the driver that what type of txrate should be used + * for the TIDs specified in %NL80211_TID_CONFIG_ATTR_TIDS. using + * the values form &nl80211_tx_rate_setting. + * @NL80211_TID_CONFIG_ATTR_TX_RATE: Data frame TX rate mask should be applied + * with the parameters passed through %NL80211_ATTR_TX_RATES. + * configuration is applied to the data frame for the tid to that connected + * station. */ enum nl80211_tid_config_attr { __NL80211_TID_CONFIG_ATTR_INVALID, @@ -4890,6 +4909,8 @@ enum nl80211_tid_config_attr { NL80211_TID_CONFIG_ATTR_AMPDU_CTRL, NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL, NL80211_TID_CONFIG_ATTR_AMSDU_CTRL, + NL80211_TID_CONFIG_ATTR_TX_RATE_TYPE, + NL80211_TID_CONFIG_ATTR_TX_RATE, /* keep last */ __NL80211_TID_CONFIG_ATTR_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 7ea764865546..22c4d13e28cb 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -329,6 +329,15 @@ he_bss_color_policy[NL80211_HE_BSS_COLOR_ATTR_MAX + 1] = { [NL80211_HE_BSS_COLOR_ATTR_PARTIAL] = { .type = NLA_FLAG }, }; +static const struct nla_policy nl80211_txattr_policy[NL80211_TXRATE_MAX + 1] = { + [NL80211_TXRATE_LEGACY] = { .type = NLA_BINARY, + .len = NL80211_MAX_SUPP_RATES }, + [NL80211_TXRATE_HT] = { .type = NLA_BINARY, + .len = NL80211_MAX_SUPP_HT_RATES }, + [NL80211_TXRATE_VHT] = NLA_POLICY_EXACT_LEN_WARN(sizeof(struct nl80211_txrate_vht)), + [NL80211_TXRATE_GI] = { .type = NLA_U8 }, +}; + static const struct nla_policy nl80211_tid_config_attr_policy[NL80211_TID_CONFIG_ATTR_MAX + 1] = { [NL80211_TID_CONFIG_ATTR_VIF_SUPP] = { .type = NLA_U64 }, @@ -345,6 +354,10 @@ nl80211_tid_config_attr_policy[NL80211_TID_CONFIG_ATTR_MAX + 1] = { NLA_POLICY_MAX(NLA_U8, NL80211_TID_CONFIG_DISABLE), [NL80211_TID_CONFIG_ATTR_AMSDU_CTRL] = NLA_POLICY_MAX(NLA_U8, NL80211_TID_CONFIG_DISABLE), + [NL80211_TID_CONFIG_ATTR_TX_RATE_TYPE] = + NLA_POLICY_MAX(NLA_U8, NL80211_TX_RATE_FIXED), + [NL80211_TID_CONFIG_ATTR_TX_RATE] = + NLA_POLICY_NESTED(nl80211_txattr_policy), }; static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { @@ -4388,16 +4401,9 @@ static bool vht_set_mcs_mask(struct ieee80211_supported_band *sband, return true; } -static const struct nla_policy nl80211_txattr_policy[NL80211_TXRATE_MAX + 1] = { - [NL80211_TXRATE_LEGACY] = { .type = NLA_BINARY, - .len = NL80211_MAX_SUPP_RATES }, - [NL80211_TXRATE_HT] = { .type = NLA_BINARY, - .len = NL80211_MAX_SUPP_HT_RATES }, - [NL80211_TXRATE_VHT] = NLA_POLICY_EXACT_LEN_WARN(sizeof(struct nl80211_txrate_vht)), - [NL80211_TXRATE_GI] = { .type = NLA_U8 }, -}; - static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, + struct nlattr *attrs[], + enum nl80211_attrs attr, struct cfg80211_bitrate_mask *mask) { struct nlattr *tb[NL80211_TXRATE_MAX + 1]; @@ -4428,14 +4434,14 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, } /* if no rates are given set it back to the defaults */ - if (!info->attrs[NL80211_ATTR_TX_RATES]) + if (!attrs[attr]) goto out; /* The nested attribute uses enum nl80211_band as the index. This maps * directly to the enum nl80211_band values used in cfg80211. */ BUILD_BUG_ON(NL80211_MAX_SUPP_HT_RATES > IEEE80211_HT_MCS_MASK_LEN * 8); - nla_for_each_nested(tx_rates, info->attrs[NL80211_ATTR_TX_RATES], rem) { + nla_for_each_nested(tx_rates, attrs[attr], rem) { enum nl80211_band band = nla_type(tx_rates); int err; @@ -4940,7 +4946,9 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) return -EINVAL; if (info->attrs[NL80211_ATTR_TX_RATES]) { - err = nl80211_parse_tx_bitrate_mask(info, ¶ms.beacon_rate); + err = nl80211_parse_tx_bitrate_mask(info, info->attrs, + NL80211_ATTR_TX_RATES, + ¶ms.beacon_rate); if (err) return err; @@ -10753,7 +10761,8 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, if (!rdev->ops->set_bitrate_mask) return -EOPNOTSUPP; - err = nl80211_parse_tx_bitrate_mask(info, &mask); + err = nl80211_parse_tx_bitrate_mask(info, info->attrs, + NL80211_ATTR_TX_RATES, &mask); if (err) return err; @@ -11359,7 +11368,9 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[NL80211_ATTR_TX_RATES]) { - err = nl80211_parse_tx_bitrate_mask(info, &setup.beacon_rate); + err = nl80211_parse_tx_bitrate_mask(info, info->attrs, + NL80211_ATTR_TX_RATES, + &setup.beacon_rate); if (err) return err; @@ -14139,6 +14150,23 @@ static int parse_tid_conf(struct cfg80211_registered_device *rdev, nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_AMSDU_CTRL]); } + if (attrs[NL80211_TID_CONFIG_ATTR_TX_RATE_TYPE]) { + u32 idx = NL80211_TID_CONFIG_ATTR_TX_RATE_TYPE, attr; + + tid_conf->txrate_type = nla_get_u8(attrs[idx]); + + if (tid_conf->txrate_type != NL80211_TX_RATE_AUTOMATIC) { + attr = NL80211_TID_CONFIG_ATTR_TX_RATE; + err = nl80211_parse_tx_bitrate_mask(info, attrs, attr, + &tid_conf->txrate_mask); + if (err) + return err; + + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_TX_RATE); + } + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_TX_RATE_TYPE); + } + if (peer) mask = rdev->wiphy.tid_config_support.peer; else -- cgit v1.2.3 From 1b9ae0c92925ac40489be526d67d0010d0724ce0 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Thu, 21 May 2020 22:14:22 +0200 Subject: wireless: Use linux/stddef.h instead of stddef.h When compiling inside the kernel include linux/stddef.h instead of stddef.h. When I compile this header file in backports for power PC I run into a conflict with ptrdiff_t. I was unable to reproduce this in mainline kernel. I still would like to fix this problem in the kernel. Fixes: 6989310f5d43 ("wireless: Use offsetof instead of custom macro.") Signed-off-by: Hauke Mehrtens Link: https://lore.kernel.org/r/20200521201422.16493-1-hauke@hauke-m.de Signed-off-by: Johannes Berg --- include/uapi/linux/wireless.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/wireless.h b/include/uapi/linux/wireless.h index a2c006a364e0..24f3371ad826 100644 --- a/include/uapi/linux/wireless.h +++ b/include/uapi/linux/wireless.h @@ -74,7 +74,11 @@ #include /* for "struct sockaddr" et al */ #include /* for IFNAMSIZ and co... */ -#include /* for offsetof */ +#ifdef __KERNEL__ +# include /* for offsetof */ +#else +# include /* for offsetof */ +#endif /***************************** VERSION *****************************/ /* -- cgit v1.2.3 From 3234ac664a870e6ea69ae3a57d824cd7edbeacc5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 21 May 2020 14:06:17 -0700 Subject: /dev/mem: Revoke mappings when a driver claims the region Close the hole of holding a mapping over kernel driver takeover event of a given address range. Commit 90a545e98126 ("restrict /dev/mem to idle io memory ranges") introduced CONFIG_IO_STRICT_DEVMEM with the goal of protecting the kernel against scenarios where a /dev/mem user tramples memory that a kernel driver owns. However, this protection only prevents *new* read(), write() and mmap() requests. Established mappings prior to the driver calling request_mem_region() are left alone. Especially with persistent memory, and the core kernel metadata that is stored there, there are plentiful scenarios for a /dev/mem user to violate the expectations of the driver and cause amplified damage. Teach request_mem_region() to find and shoot down active /dev/mem mappings that it believes it has successfully claimed for the exclusive use of the driver. Effectively a driver call to request_mem_region() becomes a hole-punch on the /dev/mem device. The typical usage of unmap_mapping_range() is part of truncate_pagecache() to punch a hole in a file, but in this case the implementation is only doing the "first half" of a hole punch. Namely it is just evacuating current established mappings of the "hole", and it relies on the fact that /dev/mem establishes mappings in terms of absolute physical address offsets. Once existing mmap users are invalidated they can attempt to re-establish the mapping, or attempt to continue issuing read(2) / write(2) to the invalidated extent, but they will then be subject to the CONFIG_IO_STRICT_DEVMEM checking that can block those subsequent accesses. Cc: Arnd Bergmann Cc: Ingo Molnar Cc: Kees Cook Cc: Matthew Wilcox Cc: Russell King Cc: Andrew Morton Cc: Greg Kroah-Hartman Fixes: 90a545e98126 ("restrict /dev/mem to idle io memory ranges") Signed-off-by: Dan Williams Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/159009507306.847224.8502634072429766747.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/char/mem.c | 101 ++++++++++++++++++++++++++++++++++++++++++++- include/linux/ioport.h | 6 +++ include/uapi/linux/magic.h | 1 + kernel/resource.c | 5 +++ 4 files changed, 111 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 43dd0891ca1e..31cae88a730b 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -31,11 +31,15 @@ #include #include #include +#include +#include +#include #ifdef CONFIG_IA64 # include #endif +#define DEVMEM_MINOR 1 #define DEVPORT_MINOR 4 static inline unsigned long size_inside_page(unsigned long start, @@ -805,12 +809,64 @@ static loff_t memory_lseek(struct file *file, loff_t offset, int orig) return ret; } +static struct inode *devmem_inode; + +#ifdef CONFIG_IO_STRICT_DEVMEM +void revoke_devmem(struct resource *res) +{ + struct inode *inode = READ_ONCE(devmem_inode); + + /* + * Check that the initialization has completed. Losing the race + * is ok because it means drivers are claiming resources before + * the fs_initcall level of init and prevent /dev/mem from + * establishing mappings. + */ + if (!inode) + return; + + /* + * The expectation is that the driver has successfully marked + * the resource busy by this point, so devmem_is_allowed() + * should start returning false, however for performance this + * does not iterate the entire resource range. + */ + if (devmem_is_allowed(PHYS_PFN(res->start)) && + devmem_is_allowed(PHYS_PFN(res->end))) { + /* + * *cringe* iomem=relaxed says "go ahead, what's the + * worst that can happen?" + */ + return; + } + + unmap_mapping_range(inode->i_mapping, res->start, resource_size(res), 1); +} +#endif + static int open_port(struct inode *inode, struct file *filp) { + int rc; + if (!capable(CAP_SYS_RAWIO)) return -EPERM; - return security_locked_down(LOCKDOWN_DEV_MEM); + rc = security_locked_down(LOCKDOWN_DEV_MEM); + if (rc) + return rc; + + if (iminor(inode) != DEVMEM_MINOR) + return 0; + + /* + * Use a unified address space to have a single point to manage + * revocations when drivers want to take over a /dev/mem mapped + * range. + */ + inode->i_mapping = devmem_inode->i_mapping; + filp->f_mapping = inode->i_mapping; + + return 0; } #define zero_lseek null_lseek @@ -885,7 +941,7 @@ static const struct memdev { fmode_t fmode; } devlist[] = { #ifdef CONFIG_DEVMEM - [1] = { "mem", 0, &mem_fops, FMODE_UNSIGNED_OFFSET }, + [DEVMEM_MINOR] = { "mem", 0, &mem_fops, FMODE_UNSIGNED_OFFSET }, #endif #ifdef CONFIG_DEVKMEM [2] = { "kmem", 0, &kmem_fops, FMODE_UNSIGNED_OFFSET }, @@ -939,6 +995,45 @@ static char *mem_devnode(struct device *dev, umode_t *mode) static struct class *mem_class; +static int devmem_fs_init_fs_context(struct fs_context *fc) +{ + return init_pseudo(fc, DEVMEM_MAGIC) ? 0 : -ENOMEM; +} + +static struct file_system_type devmem_fs_type = { + .name = "devmem", + .owner = THIS_MODULE, + .init_fs_context = devmem_fs_init_fs_context, + .kill_sb = kill_anon_super, +}; + +static int devmem_init_inode(void) +{ + static struct vfsmount *devmem_vfs_mount; + static int devmem_fs_cnt; + struct inode *inode; + int rc; + + rc = simple_pin_fs(&devmem_fs_type, &devmem_vfs_mount, &devmem_fs_cnt); + if (rc < 0) { + pr_err("Cannot mount /dev/mem pseudo filesystem: %d\n", rc); + return rc; + } + + inode = alloc_anon_inode(devmem_vfs_mount->mnt_sb); + if (IS_ERR(inode)) { + rc = PTR_ERR(inode); + pr_err("Cannot allocate inode for /dev/mem: %d\n", rc); + simple_release_fs(&devmem_vfs_mount, &devmem_fs_cnt); + return rc; + } + + /* publish /dev/mem initialized */ + WRITE_ONCE(devmem_inode, inode); + + return 0; +} + static int __init chr_dev_init(void) { int minor; @@ -960,6 +1055,8 @@ static int __init chr_dev_init(void) */ if ((minor == DEVPORT_MINOR) && !arch_has_dev_port()) continue; + if ((minor == DEVMEM_MINOR) && devmem_init_inode() != 0) + continue; device_create(mem_class, NULL, MKDEV(MEM_MAJOR, minor), NULL, devlist[minor].name); diff --git a/include/linux/ioport.h b/include/linux/ioport.h index a9b9170b5dd2..6c3eca90cbc4 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -301,5 +301,11 @@ struct resource *devm_request_free_mem_region(struct device *dev, struct resource *request_free_mem_region(struct resource *base, unsigned long size, const char *name); +#ifdef CONFIG_IO_STRICT_DEVMEM +void revoke_devmem(struct resource *res); +#else +static inline void revoke_devmem(struct resource *res) { }; +#endif + #endif /* __ASSEMBLY__ */ #endif /* _LINUX_IOPORT_H */ diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index d78064007b17..f3956fc11de6 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -94,6 +94,7 @@ #define BALLOON_KVM_MAGIC 0x13661366 #define ZSMALLOC_MAGIC 0x58295829 #define DMA_BUF_MAGIC 0x444d4142 /* "DMAB" */ +#define DEVMEM_MAGIC 0x454d444d /* "DMEM" */ #define Z3FOLD_MAGIC 0x33 #define PPC_CMM_MAGIC 0xc7571590 diff --git a/kernel/resource.c b/kernel/resource.c index 76036a41143b..841737bbda9e 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1126,6 +1126,7 @@ struct resource * __request_region(struct resource *parent, { DECLARE_WAITQUEUE(wait, current); struct resource *res = alloc_resource(GFP_KERNEL); + struct resource *orig_parent = parent; if (!res) return NULL; @@ -1176,6 +1177,10 @@ struct resource * __request_region(struct resource *parent, break; } write_unlock(&resource_lock); + + if (res && orig_parent == &iomem_resource) + revoke_devmem(res); + return res; } EXPORT_SYMBOL(__request_region); -- cgit v1.2.3 From 20f6a05ef63594feb0c6dfbd629da0448b43124d Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Wed, 27 May 2020 12:34:30 +0000 Subject: bridge: mrp: Rework the MRP netlink interface This patch reworks the MRP netlink interface. Before, each attribute represented a binary structure which made it hard to be extended. Therefore update the MRP netlink interface such that each existing attribute to be a nested attribute which contains the fields of the binary structures. In this way the MRP netlink interface can be extended without breaking the backwards compatibility. It is also using strict checking for attributes under the MRP top attribute. Signed-off-by: Horatiu Vultur Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 64 ++++++++-- net/bridge/br_mrp.c | 8 +- net/bridge/br_mrp_netlink.c | 266 +++++++++++++++++++++++++++++++++++------ net/bridge/br_private_mrp.h | 2 +- 4 files changed, 290 insertions(+), 50 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index bd8c95488f16..5a43eb86c93b 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -169,17 +169,69 @@ enum { __IFLA_BRIDGE_MRP_MAX, }; +#define IFLA_BRIDGE_MRP_MAX (__IFLA_BRIDGE_MRP_MAX - 1) + +enum { + IFLA_BRIDGE_MRP_INSTANCE_UNSPEC, + IFLA_BRIDGE_MRP_INSTANCE_RING_ID, + IFLA_BRIDGE_MRP_INSTANCE_P_IFINDEX, + IFLA_BRIDGE_MRP_INSTANCE_S_IFINDEX, + __IFLA_BRIDGE_MRP_INSTANCE_MAX, +}; + +#define IFLA_BRIDGE_MRP_INSTANCE_MAX (__IFLA_BRIDGE_MRP_INSTANCE_MAX - 1) + +enum { + IFLA_BRIDGE_MRP_PORT_STATE_UNSPEC, + IFLA_BRIDGE_MRP_PORT_STATE_STATE, + __IFLA_BRIDGE_MRP_PORT_STATE_MAX, +}; + +#define IFLA_BRIDGE_MRP_PORT_STATE_MAX (__IFLA_BRIDGE_MRP_PORT_STATE_MAX - 1) + +enum { + IFLA_BRIDGE_MRP_PORT_ROLE_UNSPEC, + IFLA_BRIDGE_MRP_PORT_ROLE_ROLE, + __IFLA_BRIDGE_MRP_PORT_ROLE_MAX, +}; + +#define IFLA_BRIDGE_MRP_PORT_ROLE_MAX (__IFLA_BRIDGE_MRP_PORT_ROLE_MAX - 1) + +enum { + IFLA_BRIDGE_MRP_RING_STATE_UNSPEC, + IFLA_BRIDGE_MRP_RING_STATE_RING_ID, + IFLA_BRIDGE_MRP_RING_STATE_STATE, + __IFLA_BRIDGE_MRP_RING_STATE_MAX, +}; + +#define IFLA_BRIDGE_MRP_RING_STATE_MAX (__IFLA_BRIDGE_MRP_RING_STATE_MAX - 1) + +enum { + IFLA_BRIDGE_MRP_RING_ROLE_UNSPEC, + IFLA_BRIDGE_MRP_RING_ROLE_RING_ID, + IFLA_BRIDGE_MRP_RING_ROLE_ROLE, + __IFLA_BRIDGE_MRP_RING_ROLE_MAX, +}; + +#define IFLA_BRIDGE_MRP_RING_ROLE_MAX (__IFLA_BRIDGE_MRP_RING_ROLE_MAX - 1) + +enum { + IFLA_BRIDGE_MRP_START_TEST_UNSPEC, + IFLA_BRIDGE_MRP_START_TEST_RING_ID, + IFLA_BRIDGE_MRP_START_TEST_INTERVAL, + IFLA_BRIDGE_MRP_START_TEST_MAX_MISS, + IFLA_BRIDGE_MRP_START_TEST_PERIOD, + __IFLA_BRIDGE_MRP_START_TEST_MAX, +}; + +#define IFLA_BRIDGE_MRP_START_TEST_MAX (__IFLA_BRIDGE_MRP_START_TEST_MAX - 1) + struct br_mrp_instance { __u32 ring_id; __u32 p_ifindex; __u32 s_ifindex; }; -struct br_mrp_port_role { - __u32 ring_id; - __u32 role; -}; - struct br_mrp_ring_state { __u32 ring_id; __u32 ring_state; @@ -197,8 +249,6 @@ struct br_mrp_start_test { __u32 period; }; -#define IFLA_BRIDGE_MRP_MAX (__IFLA_BRIDGE_MRP_MAX - 1) - struct bridge_stp_xstats { __u64 transition_blk; __u64 transition_fwd; diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index 528d767eb026..8ea59504ef47 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -376,24 +376,24 @@ int br_mrp_set_port_state(struct net_bridge_port *p, * note: already called with rtnl_lock */ int br_mrp_set_port_role(struct net_bridge_port *p, - struct br_mrp_port_role *role) + enum br_mrp_port_role_type role) { struct br_mrp *mrp; if (!p || !(p->flags & BR_MRP_AWARE)) return -EINVAL; - mrp = br_mrp_find_id(p->br, role->ring_id); + mrp = br_mrp_find_port(p->br, p); if (!mrp) return -EINVAL; - if (role->role == BR_MRP_PORT_ROLE_PRIMARY) + if (role == BR_MRP_PORT_ROLE_PRIMARY) rcu_assign_pointer(mrp->p_port, p); else rcu_assign_pointer(mrp->s_port, p); - br_mrp_port_switchdev_set_role(p, role->role); + br_mrp_port_switchdev_set_role(p, role); return 0; } diff --git a/net/bridge/br_mrp_netlink.c b/net/bridge/br_mrp_netlink.c index 4a08a99519b0..d9de780d2ce0 100644 --- a/net/bridge/br_mrp_netlink.c +++ b/net/bridge/br_mrp_netlink.c @@ -8,19 +8,222 @@ static const struct nla_policy br_mrp_policy[IFLA_BRIDGE_MRP_MAX + 1] = { [IFLA_BRIDGE_MRP_UNSPEC] = { .type = NLA_REJECT }, - [IFLA_BRIDGE_MRP_INSTANCE] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct br_mrp_instance)}, - [IFLA_BRIDGE_MRP_PORT_STATE] = { .type = NLA_U32 }, - [IFLA_BRIDGE_MRP_PORT_ROLE] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct br_mrp_port_role)}, - [IFLA_BRIDGE_MRP_RING_STATE] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct br_mrp_ring_state)}, - [IFLA_BRIDGE_MRP_RING_ROLE] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct br_mrp_ring_role)}, - [IFLA_BRIDGE_MRP_START_TEST] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct br_mrp_start_test)}, + [IFLA_BRIDGE_MRP_INSTANCE] = { .type = NLA_NESTED }, + [IFLA_BRIDGE_MRP_PORT_STATE] = { .type = NLA_NESTED }, + [IFLA_BRIDGE_MRP_PORT_ROLE] = { .type = NLA_NESTED }, + [IFLA_BRIDGE_MRP_RING_STATE] = { .type = NLA_NESTED }, + [IFLA_BRIDGE_MRP_RING_ROLE] = { .type = NLA_NESTED }, + [IFLA_BRIDGE_MRP_START_TEST] = { .type = NLA_NESTED }, }; +static const struct nla_policy +br_mrp_instance_policy[IFLA_BRIDGE_MRP_INSTANCE_MAX + 1] = { + [IFLA_BRIDGE_MRP_INSTANCE_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_MRP_INSTANCE_RING_ID] = { .type = NLA_U32 }, + [IFLA_BRIDGE_MRP_INSTANCE_P_IFINDEX] = { .type = NLA_U32 }, + [IFLA_BRIDGE_MRP_INSTANCE_S_IFINDEX] = { .type = NLA_U32 }, +}; + +static int br_mrp_instance_parse(struct net_bridge *br, struct nlattr *attr, + int cmd, struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_MRP_INSTANCE_MAX + 1]; + struct br_mrp_instance inst; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_MRP_INSTANCE_MAX, attr, + br_mrp_instance_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_MRP_INSTANCE_RING_ID] || + !tb[IFLA_BRIDGE_MRP_INSTANCE_P_IFINDEX] || + !tb[IFLA_BRIDGE_MRP_INSTANCE_S_IFINDEX]) { + NL_SET_ERR_MSG_MOD(extack, + "Missing attribute: RING_ID or P_IFINDEX or S_IFINDEX"); + return -EINVAL; + } + + memset(&inst, 0, sizeof(inst)); + + inst.ring_id = nla_get_u32(tb[IFLA_BRIDGE_MRP_INSTANCE_RING_ID]); + inst.p_ifindex = nla_get_u32(tb[IFLA_BRIDGE_MRP_INSTANCE_P_IFINDEX]); + inst.s_ifindex = nla_get_u32(tb[IFLA_BRIDGE_MRP_INSTANCE_S_IFINDEX]); + + if (cmd == RTM_SETLINK) + return br_mrp_add(br, &inst); + else + return br_mrp_del(br, &inst); + + return 0; +} + +static const struct nla_policy +br_mrp_port_state_policy[IFLA_BRIDGE_MRP_PORT_STATE_MAX + 1] = { + [IFLA_BRIDGE_MRP_PORT_STATE_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_MRP_PORT_STATE_STATE] = { .type = NLA_U32 }, +}; + +static int br_mrp_port_state_parse(struct net_bridge_port *p, + struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_MRP_PORT_STATE_MAX + 1]; + enum br_mrp_port_state_type state; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_MRP_PORT_STATE_MAX, attr, + br_mrp_port_state_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_MRP_PORT_STATE_STATE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing attribute: STATE"); + return -EINVAL; + } + + state = nla_get_u32(tb[IFLA_BRIDGE_MRP_PORT_STATE_STATE]); + + return br_mrp_set_port_state(p, state); +} + +static const struct nla_policy +br_mrp_port_role_policy[IFLA_BRIDGE_MRP_PORT_ROLE_MAX + 1] = { + [IFLA_BRIDGE_MRP_PORT_ROLE_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_MRP_PORT_ROLE_ROLE] = { .type = NLA_U32 }, +}; + +static int br_mrp_port_role_parse(struct net_bridge_port *p, + struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_MRP_PORT_ROLE_MAX + 1]; + enum br_mrp_port_role_type role; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_MRP_PORT_ROLE_MAX, attr, + br_mrp_port_role_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_MRP_PORT_ROLE_ROLE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing attribute: ROLE"); + return -EINVAL; + } + + role = nla_get_u32(tb[IFLA_BRIDGE_MRP_PORT_ROLE_ROLE]); + + return br_mrp_set_port_role(p, role); +} + +static const struct nla_policy +br_mrp_ring_state_policy[IFLA_BRIDGE_MRP_RING_STATE_MAX + 1] = { + [IFLA_BRIDGE_MRP_RING_STATE_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_MRP_RING_STATE_RING_ID] = { .type = NLA_U32 }, + [IFLA_BRIDGE_MRP_RING_STATE_STATE] = { .type = NLA_U32 }, +}; + +static int br_mrp_ring_state_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_MRP_RING_STATE_MAX + 1]; + struct br_mrp_ring_state state; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_MRP_RING_STATE_MAX, attr, + br_mrp_ring_state_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_MRP_RING_STATE_RING_ID] || + !tb[IFLA_BRIDGE_MRP_RING_STATE_STATE]) { + NL_SET_ERR_MSG_MOD(extack, + "Missing attribute: RING_ID or STATE"); + return -EINVAL; + } + + memset(&state, 0x0, sizeof(state)); + + state.ring_id = nla_get_u32(tb[IFLA_BRIDGE_MRP_RING_STATE_RING_ID]); + state.ring_state = nla_get_u32(tb[IFLA_BRIDGE_MRP_RING_STATE_STATE]); + + return br_mrp_set_ring_state(br, &state); +} + +static const struct nla_policy +br_mrp_ring_role_policy[IFLA_BRIDGE_MRP_RING_ROLE_MAX + 1] = { + [IFLA_BRIDGE_MRP_RING_ROLE_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_MRP_RING_ROLE_RING_ID] = { .type = NLA_U32 }, + [IFLA_BRIDGE_MRP_RING_ROLE_ROLE] = { .type = NLA_U32 }, +}; + +static int br_mrp_ring_role_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_MRP_RING_ROLE_MAX + 1]; + struct br_mrp_ring_role role; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_MRP_RING_ROLE_MAX, attr, + br_mrp_ring_role_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_MRP_RING_ROLE_RING_ID] || + !tb[IFLA_BRIDGE_MRP_RING_ROLE_ROLE]) { + NL_SET_ERR_MSG_MOD(extack, + "Missing attribute: RING_ID or ROLE"); + return -EINVAL; + } + + memset(&role, 0x0, sizeof(role)); + + role.ring_id = nla_get_u32(tb[IFLA_BRIDGE_MRP_RING_ROLE_RING_ID]); + role.ring_role = nla_get_u32(tb[IFLA_BRIDGE_MRP_RING_ROLE_ROLE]); + + return br_mrp_set_ring_role(br, &role); +} + +static const struct nla_policy +br_mrp_start_test_policy[IFLA_BRIDGE_MRP_START_TEST_MAX + 1] = { + [IFLA_BRIDGE_MRP_START_TEST_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_MRP_START_TEST_RING_ID] = { .type = NLA_U32 }, + [IFLA_BRIDGE_MRP_START_TEST_INTERVAL] = { .type = NLA_U32 }, + [IFLA_BRIDGE_MRP_START_TEST_MAX_MISS] = { .type = NLA_U32 }, + [IFLA_BRIDGE_MRP_START_TEST_PERIOD] = { .type = NLA_U32 }, +}; + +static int br_mrp_start_test_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_MRP_START_TEST_MAX + 1]; + struct br_mrp_start_test test; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_MRP_START_TEST_MAX, attr, + br_mrp_start_test_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_MRP_START_TEST_RING_ID] || + !tb[IFLA_BRIDGE_MRP_START_TEST_INTERVAL] || + !tb[IFLA_BRIDGE_MRP_START_TEST_MAX_MISS] || + !tb[IFLA_BRIDGE_MRP_START_TEST_PERIOD]) { + NL_SET_ERR_MSG_MOD(extack, + "Missing attribute: RING_ID or INTERVAL or MAX_MISS or PERIOD"); + return -EINVAL; + } + + memset(&test, 0x0, sizeof(test)); + + test.ring_id = nla_get_u32(tb[IFLA_BRIDGE_MRP_START_TEST_RING_ID]); + test.interval = nla_get_u32(tb[IFLA_BRIDGE_MRP_START_TEST_INTERVAL]); + test.max_miss = nla_get_u32(tb[IFLA_BRIDGE_MRP_START_TEST_MAX_MISS]); + test.period = nla_get_u32(tb[IFLA_BRIDGE_MRP_START_TEST_PERIOD]); + + return br_mrp_start_test(br, &test); +} + int br_mrp_parse(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *attr, int cmd, struct netlink_ext_ack *extack) { @@ -44,58 +247,45 @@ int br_mrp_parse(struct net_bridge *br, struct net_bridge_port *p, return err; if (tb[IFLA_BRIDGE_MRP_INSTANCE]) { - struct br_mrp_instance *instance = - nla_data(tb[IFLA_BRIDGE_MRP_INSTANCE]); - - if (cmd == RTM_SETLINK) - err = br_mrp_add(br, instance); - else - err = br_mrp_del(br, instance); + err = br_mrp_instance_parse(br, tb[IFLA_BRIDGE_MRP_INSTANCE], + cmd, extack); if (err) return err; } if (tb[IFLA_BRIDGE_MRP_PORT_STATE]) { - enum br_mrp_port_state_type state = - nla_get_u32(tb[IFLA_BRIDGE_MRP_PORT_STATE]); - - err = br_mrp_set_port_state(p, state); + err = br_mrp_port_state_parse(p, tb[IFLA_BRIDGE_MRP_PORT_STATE], + extack); if (err) return err; } if (tb[IFLA_BRIDGE_MRP_PORT_ROLE]) { - struct br_mrp_port_role *role = - nla_data(tb[IFLA_BRIDGE_MRP_PORT_ROLE]); - - err = br_mrp_set_port_role(p, role); + err = br_mrp_port_role_parse(p, tb[IFLA_BRIDGE_MRP_PORT_ROLE], + extack); if (err) return err; } if (tb[IFLA_BRIDGE_MRP_RING_STATE]) { - struct br_mrp_ring_state *state = - nla_data(tb[IFLA_BRIDGE_MRP_RING_STATE]); - - err = br_mrp_set_ring_state(br, state); + err = br_mrp_ring_state_parse(br, + tb[IFLA_BRIDGE_MRP_RING_STATE], + extack); if (err) return err; } if (tb[IFLA_BRIDGE_MRP_RING_ROLE]) { - struct br_mrp_ring_role *role = - nla_data(tb[IFLA_BRIDGE_MRP_RING_ROLE]); - - err = br_mrp_set_ring_role(br, role); + err = br_mrp_ring_role_parse(br, tb[IFLA_BRIDGE_MRP_RING_ROLE], + extack); if (err) return err; } if (tb[IFLA_BRIDGE_MRP_START_TEST]) { - struct br_mrp_start_test *test = - nla_data(tb[IFLA_BRIDGE_MRP_START_TEST]); - - err = br_mrp_start_test(br, test); + err = br_mrp_start_test_parse(br, + tb[IFLA_BRIDGE_MRP_START_TEST], + extack); if (err) return err; } diff --git a/net/bridge/br_private_mrp.h b/net/bridge/br_private_mrp.h index 2921a4b59f8e..a0f53cc3ab85 100644 --- a/net/bridge/br_private_mrp.h +++ b/net/bridge/br_private_mrp.h @@ -37,7 +37,7 @@ int br_mrp_del(struct net_bridge *br, struct br_mrp_instance *instance); int br_mrp_set_port_state(struct net_bridge_port *p, enum br_mrp_port_state_type state); int br_mrp_set_port_role(struct net_bridge_port *p, - struct br_mrp_port_role *role); + enum br_mrp_port_role_type role); int br_mrp_set_ring_state(struct net_bridge *br, struct br_mrp_ring_state *state); int br_mrp_set_ring_role(struct net_bridge *br, struct br_mrp_ring_role *role); -- cgit v1.2.3 From cb8aa9a3affb7d23b11b11fbed41e2feaabc4b0a Mon Sep 17 00:00:00 2001 From: Romain Bellan Date: Mon, 4 May 2020 21:34:29 +0200 Subject: netfilter: ctnetlink: add kernel side filtering for dump Conntrack dump does not support kernel side filtering (only get exists, but it returns only one entry. And user has to give a full valid tuple) It means that userspace has to implement filtering after receiving many irrelevant entries, consuming resources (conntrack table is sometimes very huge, much more than a routing table for example). This patch adds filtering in kernel side. To achieve this goal, we: * Add a new CTA_FILTER netlink attributes, actually a flag list to parametize filtering * Convert some *nlattr_to_tuple() functions, to allow a partial parsing of CTA_TUPLE_ORIG and CTA_TUPLE_REPLY (so nf_conntrack_tuple it not fully set) Filtering is now possible on: * IP SRC/DST values * Ports for TCP and UDP flows * IMCP(v6) codes types and IDs Filtering is done as an "AND" operator. For example, when flags PROTO_SRC_PORT, PROTO_NUM and IP_SRC are sets, only entries matching all values are dumped. Changes since v1: Set NLM_F_DUMP_FILTERED in nlm flags if entries are filtered Changes since v2: Move several constants to nf_internals.h Move a fix on netlink values check in a separate patch Add a check on not-supported flags Return EOPNOTSUPP if CDA_FILTER is set in ctnetlink_flush_conntrack (not yet implemented) Code style issues Changes since v3: Fix compilation warning reported by kbuild test robot Changes since v4: Fix a regression introduced in v3 (returned EINVAL for valid netlink messages without CTA_MARK) Changes since v5: Change definition of CTA_FILTER_F_ALL Fix a regression when CTA_TUPLE_ZONE is not set Signed-off-by: Romain Bellan Signed-off-by: Florent Fourcot Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 6 +- include/uapi/linux/netfilter/nfnetlink_conntrack.h | 9 + net/netfilter/nf_conntrack_core.c | 19 +- net/netfilter/nf_conntrack_netlink.c | 334 ++++++++++++++++++--- net/netfilter/nf_conntrack_proto_icmp.c | 40 ++- net/netfilter/nf_conntrack_proto_icmpv6.c | 42 ++- net/netfilter/nf_internals.h | 17 ++ 7 files changed, 394 insertions(+), 73 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 4cad1f0a327a..88186b95b3c2 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -42,7 +42,8 @@ struct nf_conntrack_l4proto { /* Calculate tuple nlattr size */ unsigned int (*nlattr_tuple_size)(void); int (*nlattr_to_tuple)(struct nlattr *tb[], - struct nf_conntrack_tuple *t); + struct nf_conntrack_tuple *t, + u_int32_t flags); const struct nla_policy *nla_policy; struct { @@ -152,7 +153,8 @@ const struct nf_conntrack_l4proto *nf_ct_l4proto_find(u8 l4proto); int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple); int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *t); + struct nf_conntrack_tuple *t, + u_int32_t flags); unsigned int nf_ct_port_nlattr_tuple_size(void); extern const struct nla_policy nf_ct_port_nla_policy[]; diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h index 1d41810d17e2..262881792671 100644 --- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h +++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h @@ -55,6 +55,7 @@ enum ctattr_type { CTA_LABELS, CTA_LABELS_MASK, CTA_SYNPROXY, + CTA_FILTER, __CTA_MAX }; #define CTA_MAX (__CTA_MAX - 1) @@ -276,4 +277,12 @@ enum ctattr_expect_stats { }; #define CTA_STATS_EXP_MAX (__CTA_STATS_EXP_MAX - 1) +enum ctattr_filter { + CTA_FILTER_UNSPEC, + CTA_FILTER_ORIG_FLAGS, + CTA_FILTER_REPLY_FLAGS, + __CTA_FILTER_MAX +}; +#define CTA_FILTER_MAX (__CTA_FILTER_MAX - 1) + #endif /* _IPCONNTRACK_NETLINK_H */ diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 1d57b95d3481..8abb1727bcc4 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1974,13 +1974,22 @@ const struct nla_policy nf_ct_port_nla_policy[CTA_PROTO_MAX+1] = { EXPORT_SYMBOL_GPL(nf_ct_port_nla_policy); int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *t) + struct nf_conntrack_tuple *t, + u_int32_t flags) { - if (!tb[CTA_PROTO_SRC_PORT] || !tb[CTA_PROTO_DST_PORT]) - return -EINVAL; + if (flags & CTA_FILTER_FLAG(CTA_PROTO_SRC_PORT)) { + if (!tb[CTA_PROTO_SRC_PORT]) + return -EINVAL; + + t->src.u.tcp.port = nla_get_be16(tb[CTA_PROTO_SRC_PORT]); + } - t->src.u.tcp.port = nla_get_be16(tb[CTA_PROTO_SRC_PORT]); - t->dst.u.tcp.port = nla_get_be16(tb[CTA_PROTO_DST_PORT]); + if (flags & CTA_FILTER_FLAG(CTA_PROTO_DST_PORT)) { + if (!tb[CTA_PROTO_DST_PORT]) + return -EINVAL; + + t->dst.u.tcp.port = nla_get_be16(tb[CTA_PROTO_DST_PORT]); + } return 0; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 9ddfcd002d3b..d7bd8b1f27d5 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -54,6 +54,8 @@ #include #include +#include "nf_internals.h" + MODULE_LICENSE("GPL"); static int ctnetlink_dump_tuples_proto(struct sk_buff *skb, @@ -544,14 +546,16 @@ static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct) static int ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, - struct nf_conn *ct, bool extinfo) + struct nf_conn *ct, bool extinfo, unsigned int flags) { const struct nf_conntrack_zone *zone; struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; struct nlattr *nest_parms; - unsigned int flags = portid ? NLM_F_MULTI : 0, event; + unsigned int event; + if (portid) + flags |= NLM_F_MULTI; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_NEW); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) @@ -847,17 +851,70 @@ static int ctnetlink_done(struct netlink_callback *cb) } struct ctnetlink_filter { + u_int32_t cta_flags; u8 family; + + u_int32_t orig_flags; + u_int32_t reply_flags; + + struct nf_conntrack_tuple orig; + struct nf_conntrack_tuple reply; + struct nf_conntrack_zone zone; + struct { u_int32_t val; u_int32_t mask; } mark; }; +static const struct nla_policy cta_filter_nla_policy[CTA_FILTER_MAX + 1] = { + [CTA_FILTER_ORIG_FLAGS] = { .type = NLA_U32 }, + [CTA_FILTER_REPLY_FLAGS] = { .type = NLA_U32 }, +}; + +static int ctnetlink_parse_filter(const struct nlattr *attr, + struct ctnetlink_filter *filter) +{ + struct nlattr *tb[CTA_FILTER_MAX + 1]; + int ret = 0; + + ret = nla_parse_nested(tb, CTA_FILTER_MAX, attr, cta_filter_nla_policy, + NULL); + if (ret) + return ret; + + if (tb[CTA_FILTER_ORIG_FLAGS]) { + filter->orig_flags = nla_get_u32(tb[CTA_FILTER_ORIG_FLAGS]); + if (filter->orig_flags & ~CTA_FILTER_F_ALL) + return -EOPNOTSUPP; + } + + if (tb[CTA_FILTER_REPLY_FLAGS]) { + filter->reply_flags = nla_get_u32(tb[CTA_FILTER_REPLY_FLAGS]); + if (filter->reply_flags & ~CTA_FILTER_F_ALL) + return -EOPNOTSUPP; + } + + return 0; +} + +static int ctnetlink_parse_zone(const struct nlattr *attr, + struct nf_conntrack_zone *zone); +static int ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], + struct nf_conntrack_tuple *tuple, + u32 type, u_int8_t l3num, + struct nf_conntrack_zone *zone, + u_int32_t flags); + +/* applied on filters */ +#define CTA_FILTER_F_CTA_MARK (1 << 0) +#define CTA_FILTER_F_CTA_MARK_MASK (1 << 1) + static struct ctnetlink_filter * ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) { struct ctnetlink_filter *filter; + int err; #ifndef CONFIG_NF_CONNTRACK_MARK if (cda[CTA_MARK] || cda[CTA_MARK_MASK]) @@ -871,14 +928,65 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) filter->family = family; #ifdef CONFIG_NF_CONNTRACK_MARK - if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) { + if (cda[CTA_MARK]) { filter->mark.val = ntohl(nla_get_be32(cda[CTA_MARK])); - filter->mark.mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK])); + filter->cta_flags |= CTA_FILTER_FLAG(CTA_MARK); + + if (cda[CTA_MARK_MASK]) { + filter->mark.mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK])); + filter->cta_flags |= CTA_FILTER_FLAG(CTA_MARK_MASK); + } else { + filter->mark.mask = 0xffffffff; + } + } else if (cda[CTA_MARK_MASK]) { + return ERR_PTR(-EINVAL); } #endif + if (!cda[CTA_FILTER]) + return filter; + + err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone); + if (err < 0) + return ERR_PTR(err); + + err = ctnetlink_parse_filter(cda[CTA_FILTER], filter); + if (err < 0) + return ERR_PTR(err); + + if (filter->orig_flags) { + if (!cda[CTA_TUPLE_ORIG]) + return ERR_PTR(-EINVAL); + + err = ctnetlink_parse_tuple_filter(cda, &filter->orig, + CTA_TUPLE_ORIG, + filter->family, + &filter->zone, + filter->orig_flags); + if (err < 0) + return ERR_PTR(err); + } + + if (filter->reply_flags) { + if (!cda[CTA_TUPLE_REPLY]) + return ERR_PTR(-EINVAL); + + err = ctnetlink_parse_tuple_filter(cda, &filter->reply, + CTA_TUPLE_REPLY, + filter->family, + &filter->zone, + filter->orig_flags); + if (err < 0) + return ERR_PTR(err); + } + return filter; } +static bool ctnetlink_needs_filter(u8 family, const struct nlattr * const *cda) +{ + return family || cda[CTA_MARK] || cda[CTA_FILTER]; +} + static int ctnetlink_start(struct netlink_callback *cb) { const struct nlattr * const *cda = cb->data; @@ -886,7 +994,7 @@ static int ctnetlink_start(struct netlink_callback *cb) struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u8 family = nfmsg->nfgen_family; - if (family || (cda[CTA_MARK] && cda[CTA_MARK_MASK])) { + if (ctnetlink_needs_filter(family, cda)) { filter = ctnetlink_alloc_filter(cda, family); if (IS_ERR(filter)) return PTR_ERR(filter); @@ -896,9 +1004,79 @@ static int ctnetlink_start(struct netlink_callback *cb) return 0; } +static int ctnetlink_filter_match_tuple(struct nf_conntrack_tuple *filter_tuple, + struct nf_conntrack_tuple *ct_tuple, + u_int32_t flags, int family) +{ + switch (family) { + case NFPROTO_IPV4: + if ((flags & CTA_FILTER_FLAG(CTA_IP_SRC)) && + filter_tuple->src.u3.ip != ct_tuple->src.u3.ip) + return 0; + + if ((flags & CTA_FILTER_FLAG(CTA_IP_DST)) && + filter_tuple->dst.u3.ip != ct_tuple->dst.u3.ip) + return 0; + break; + case NFPROTO_IPV6: + if ((flags & CTA_FILTER_FLAG(CTA_IP_SRC)) && + !ipv6_addr_cmp(&filter_tuple->src.u3.in6, + &ct_tuple->src.u3.in6)) + return 0; + + if ((flags & CTA_FILTER_FLAG(CTA_IP_DST)) && + !ipv6_addr_cmp(&filter_tuple->dst.u3.in6, + &ct_tuple->dst.u3.in6)) + return 0; + break; + } + + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_NUM)) && + filter_tuple->dst.protonum != ct_tuple->dst.protonum) + return 0; + + switch (ct_tuple->dst.protonum) { + case IPPROTO_TCP: + case IPPROTO_UDP: + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_SRC_PORT)) && + filter_tuple->src.u.tcp.port != ct_tuple->src.u.tcp.port) + return 0; + + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_DST_PORT)) && + filter_tuple->dst.u.tcp.port != ct_tuple->dst.u.tcp.port) + return 0; + break; + case IPPROTO_ICMP: + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_TYPE)) && + filter_tuple->dst.u.icmp.type != ct_tuple->dst.u.icmp.type) + return 0; + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_CODE)) && + filter_tuple->dst.u.icmp.code != ct_tuple->dst.u.icmp.code) + return 0; + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_ID)) && + filter_tuple->src.u.icmp.id != ct_tuple->src.u.icmp.id) + return 0; + break; + case IPPROTO_ICMPV6: + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_TYPE)) && + filter_tuple->dst.u.icmp.type != ct_tuple->dst.u.icmp.type) + return 0; + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_CODE)) && + filter_tuple->dst.u.icmp.code != ct_tuple->dst.u.icmp.code) + return 0; + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_ID)) && + filter_tuple->src.u.icmp.id != ct_tuple->src.u.icmp.id) + return 0; + break; + } + + return 1; +} + static int ctnetlink_filter_match(struct nf_conn *ct, void *data) { struct ctnetlink_filter *filter = data; + struct nf_conntrack_tuple *tuple; if (filter == NULL) goto out; @@ -910,8 +1088,28 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data) if (filter->family && nf_ct_l3num(ct) != filter->family) goto ignore_entry; + if (filter->orig_flags) { + tuple = nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL); + if (!ctnetlink_filter_match_tuple(&filter->orig, tuple, + filter->orig_flags, + filter->family)) + goto ignore_entry; + } + + if (filter->reply_flags) { + tuple = nf_ct_tuple(ct, IP_CT_DIR_REPLY); + if (!ctnetlink_filter_match_tuple(&filter->reply, tuple, + filter->reply_flags, + filter->family)) + goto ignore_entry; + } + #ifdef CONFIG_NF_CONNTRACK_MARK - if ((ct->mark & filter->mark.mask) != filter->mark.val) + if ((filter->cta_flags & CTA_FILTER_FLAG(CTA_MARK_MASK)) && + (ct->mark & filter->mark.mask) != filter->mark.val) + goto ignore_entry; + else if ((filter->cta_flags & CTA_FILTER_FLAG(CTA_MARK)) && + ct->mark != filter->mark.val) goto ignore_entry; #endif @@ -925,6 +1123,7 @@ ignore_entry: static int ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { + unsigned int flags = cb->data ? NLM_F_DUMP_FILTERED : 0; struct net *net = sock_net(skb->sk); struct nf_conn *ct, *last; struct nf_conntrack_tuple_hash *h; @@ -979,7 +1178,7 @@ restart: ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), - ct, true); + ct, true, flags); if (res < 0) { nf_conntrack_get(&ct->ct_general); cb->args[1] = (unsigned long)ct; @@ -1014,31 +1213,50 @@ out: } static int ipv4_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *t) + struct nf_conntrack_tuple *t, + u_int32_t flags) { - if (!tb[CTA_IP_V4_SRC] || !tb[CTA_IP_V4_DST]) - return -EINVAL; + if (flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { + if (!tb[CTA_IP_V4_SRC]) + return -EINVAL; + + t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]); + } + + if (flags & CTA_FILTER_FLAG(CTA_IP_DST)) { + if (!tb[CTA_IP_V4_DST]) + return -EINVAL; - t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]); - t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]); + t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]); + } return 0; } static int ipv6_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *t) + struct nf_conntrack_tuple *t, + u_int32_t flags) { - if (!tb[CTA_IP_V6_SRC] || !tb[CTA_IP_V6_DST]) - return -EINVAL; + if (flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { + if (!tb[CTA_IP_V6_SRC]) + return -EINVAL; - t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]); - t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]); + t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]); + } + + if (flags & CTA_FILTER_FLAG(CTA_IP_DST)) { + if (!tb[CTA_IP_V6_DST]) + return -EINVAL; + + t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]); + } return 0; } static int ctnetlink_parse_tuple_ip(struct nlattr *attr, - struct nf_conntrack_tuple *tuple) + struct nf_conntrack_tuple *tuple, + u_int32_t flags) { struct nlattr *tb[CTA_IP_MAX+1]; int ret = 0; @@ -1054,10 +1272,10 @@ static int ctnetlink_parse_tuple_ip(struct nlattr *attr, switch (tuple->src.l3num) { case NFPROTO_IPV4: - ret = ipv4_nlattr_to_tuple(tb, tuple); + ret = ipv4_nlattr_to_tuple(tb, tuple, flags); break; case NFPROTO_IPV6: - ret = ipv6_nlattr_to_tuple(tb, tuple); + ret = ipv6_nlattr_to_tuple(tb, tuple, flags); break; } @@ -1069,7 +1287,8 @@ static const struct nla_policy proto_nla_policy[CTA_PROTO_MAX+1] = { }; static int ctnetlink_parse_tuple_proto(struct nlattr *attr, - struct nf_conntrack_tuple *tuple) + struct nf_conntrack_tuple *tuple, + u_int32_t flags) { const struct nf_conntrack_l4proto *l4proto; struct nlattr *tb[CTA_PROTO_MAX+1]; @@ -1080,8 +1299,12 @@ static int ctnetlink_parse_tuple_proto(struct nlattr *attr, if (ret < 0) return ret; + if (!(flags & CTA_FILTER_FLAG(CTA_PROTO_NUM))) + return 0; + if (!tb[CTA_PROTO_NUM]) return -EINVAL; + tuple->dst.protonum = nla_get_u8(tb[CTA_PROTO_NUM]); rcu_read_lock(); @@ -1092,7 +1315,7 @@ static int ctnetlink_parse_tuple_proto(struct nlattr *attr, l4proto->nla_policy, NULL); if (ret == 0) - ret = l4proto->nlattr_to_tuple(tb, tuple); + ret = l4proto->nlattr_to_tuple(tb, tuple, flags); } rcu_read_unlock(); @@ -1143,10 +1366,21 @@ static const struct nla_policy tuple_nla_policy[CTA_TUPLE_MAX+1] = { [CTA_TUPLE_ZONE] = { .type = NLA_U16 }, }; +#define CTA_FILTER_F_ALL_CTA_PROTO \ + (CTA_FILTER_F_CTA_PROTO_SRC_PORT | \ + CTA_FILTER_F_CTA_PROTO_DST_PORT | \ + CTA_FILTER_F_CTA_PROTO_ICMP_TYPE | \ + CTA_FILTER_F_CTA_PROTO_ICMP_CODE | \ + CTA_FILTER_F_CTA_PROTO_ICMP_ID | \ + CTA_FILTER_F_CTA_PROTO_ICMPV6_TYPE | \ + CTA_FILTER_F_CTA_PROTO_ICMPV6_CODE | \ + CTA_FILTER_F_CTA_PROTO_ICMPV6_ID) + static int -ctnetlink_parse_tuple(const struct nlattr * const cda[], - struct nf_conntrack_tuple *tuple, u32 type, - u_int8_t l3num, struct nf_conntrack_zone *zone) +ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], + struct nf_conntrack_tuple *tuple, u32 type, + u_int8_t l3num, struct nf_conntrack_zone *zone, + u_int32_t flags) { struct nlattr *tb[CTA_TUPLE_MAX+1]; int err; @@ -1158,23 +1392,32 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[], if (err < 0) return err; - if (!tb[CTA_TUPLE_IP]) - return -EINVAL; tuple->src.l3num = l3num; - err = ctnetlink_parse_tuple_ip(tb[CTA_TUPLE_IP], tuple); - if (err < 0) - return err; + if (flags & CTA_FILTER_FLAG(CTA_IP_DST) || + flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { + if (!tb[CTA_TUPLE_IP]) + return -EINVAL; - if (!tb[CTA_TUPLE_PROTO]) - return -EINVAL; + err = ctnetlink_parse_tuple_ip(tb[CTA_TUPLE_IP], tuple, flags); + if (err < 0) + return err; + } - err = ctnetlink_parse_tuple_proto(tb[CTA_TUPLE_PROTO], tuple); - if (err < 0) - return err; + if (flags & CTA_FILTER_FLAG(CTA_PROTO_NUM)) { + if (!tb[CTA_TUPLE_PROTO]) + return -EINVAL; - if (tb[CTA_TUPLE_ZONE]) { + err = ctnetlink_parse_tuple_proto(tb[CTA_TUPLE_PROTO], tuple, flags); + if (err < 0) + return err; + } else if (flags & CTA_FILTER_FLAG(ALL_CTA_PROTO)) { + /* Can't manage proto flags without a protonum */ + return -EINVAL; + } + + if ((flags & CTA_FILTER_FLAG(CTA_TUPLE_ZONE)) && tb[CTA_TUPLE_ZONE]) { if (!zone) return -EINVAL; @@ -1193,6 +1436,15 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[], return 0; } +static int +ctnetlink_parse_tuple(const struct nlattr * const cda[], + struct nf_conntrack_tuple *tuple, u32 type, + u_int8_t l3num, struct nf_conntrack_zone *zone) +{ + return ctnetlink_parse_tuple_filter(cda, tuple, type, l3num, zone, + CTA_FILTER_FLAG(ALL)); +} + static const struct nla_policy help_nla_policy[CTA_HELP_MAX+1] = { [CTA_HELP_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN - 1 }, @@ -1240,6 +1492,7 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { .len = NF_CT_LABELS_MAX_SIZE }, [CTA_LABELS_MASK] = { .type = NLA_BINARY, .len = NF_CT_LABELS_MAX_SIZE }, + [CTA_FILTER] = { .type = NLA_NESTED }, }; static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data) @@ -1256,7 +1509,10 @@ static int ctnetlink_flush_conntrack(struct net *net, { struct ctnetlink_filter *filter = NULL; - if (family || (cda[CTA_MARK] && cda[CTA_MARK_MASK])) { + if (ctnetlink_needs_filter(family, cda)) { + if (cda[CTA_FILTER]) + return -EOPNOTSUPP; + filter = ctnetlink_alloc_filter(cda, family); if (IS_ERR(filter)) return PTR_ERR(filter); @@ -1385,7 +1641,7 @@ static int ctnetlink_get_conntrack(struct net *net, struct sock *ctnl, } err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, - NFNL_MSG_TYPE(nlh->nlmsg_type), ct, true); + NFNL_MSG_TYPE(nlh->nlmsg_type), ct, true, 0); nf_ct_put(ct); if (err <= 0) goto free; @@ -1458,7 +1714,7 @@ restart: res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), - ct, dying ? true : false); + ct, dying ? true : false, 0); if (res < 0) { if (!atomic_inc_not_zero(&ct->ct_general.use)) continue; diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index c2e3dff773bc..4efd8741c105 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -20,6 +20,8 @@ #include #include +#include "nf_internals.h" + static const unsigned int nf_ct_icmp_timeout = 30*HZ; bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, @@ -271,20 +273,32 @@ static const struct nla_policy icmp_nla_policy[CTA_PROTO_MAX+1] = { }; static int icmp_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *tuple) + struct nf_conntrack_tuple *tuple, + u_int32_t flags) { - if (!tb[CTA_PROTO_ICMP_TYPE] || - !tb[CTA_PROTO_ICMP_CODE] || - !tb[CTA_PROTO_ICMP_ID]) - return -EINVAL; - - tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]); - tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]); - tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]); - - if (tuple->dst.u.icmp.type >= sizeof(invmap) || - !invmap[tuple->dst.u.icmp.type]) - return -EINVAL; + if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_TYPE)) { + if (!tb[CTA_PROTO_ICMP_TYPE]) + return -EINVAL; + + tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]); + if (tuple->dst.u.icmp.type >= sizeof(invmap) || + !invmap[tuple->dst.u.icmp.type]) + return -EINVAL; + } + + if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_CODE)) { + if (!tb[CTA_PROTO_ICMP_CODE]) + return -EINVAL; + + tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]); + } + + if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_ID)) { + if (!tb[CTA_PROTO_ICMP_ID]) + return -EINVAL; + + tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]); + } return 0; } diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index 6f9144e1f1c1..facd8c64ec4e 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -24,6 +24,8 @@ #include #include +#include "nf_internals.h" + static const unsigned int nf_ct_icmpv6_timeout = 30*HZ; bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, @@ -193,21 +195,33 @@ static const struct nla_policy icmpv6_nla_policy[CTA_PROTO_MAX+1] = { }; static int icmpv6_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *tuple) + struct nf_conntrack_tuple *tuple, + u_int32_t flags) { - if (!tb[CTA_PROTO_ICMPV6_TYPE] || - !tb[CTA_PROTO_ICMPV6_CODE] || - !tb[CTA_PROTO_ICMPV6_ID]) - return -EINVAL; - - tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]); - tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]); - tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]); - - if (tuple->dst.u.icmp.type < 128 || - tuple->dst.u.icmp.type - 128 >= sizeof(invmap) || - !invmap[tuple->dst.u.icmp.type - 128]) - return -EINVAL; + if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_TYPE)) { + if (!tb[CTA_PROTO_ICMPV6_TYPE]) + return -EINVAL; + + tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]); + if (tuple->dst.u.icmp.type < 128 || + tuple->dst.u.icmp.type - 128 >= sizeof(invmap) || + !invmap[tuple->dst.u.icmp.type - 128]) + return -EINVAL; + } + + if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_CODE)) { + if (!tb[CTA_PROTO_ICMPV6_CODE]) + return -EINVAL; + + tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]); + } + + if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_ID)) { + if (!tb[CTA_PROTO_ICMPV6_ID]) + return -EINVAL; + + tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]); + } return 0; } diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index d6c43902ebd7..832ae64179f0 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -6,6 +6,23 @@ #include #include +/* nf_conntrack_netlink.c: applied on tuple filters */ +#define CTA_FILTER_F_CTA_IP_SRC (1 << 0) +#define CTA_FILTER_F_CTA_IP_DST (1 << 1) +#define CTA_FILTER_F_CTA_TUPLE_ZONE (1 << 2) +#define CTA_FILTER_F_CTA_PROTO_NUM (1 << 3) +#define CTA_FILTER_F_CTA_PROTO_SRC_PORT (1 << 4) +#define CTA_FILTER_F_CTA_PROTO_DST_PORT (1 << 5) +#define CTA_FILTER_F_CTA_PROTO_ICMP_TYPE (1 << 6) +#define CTA_FILTER_F_CTA_PROTO_ICMP_CODE (1 << 7) +#define CTA_FILTER_F_CTA_PROTO_ICMP_ID (1 << 8) +#define CTA_FILTER_F_CTA_PROTO_ICMPV6_TYPE (1 << 9) +#define CTA_FILTER_F_CTA_PROTO_ICMPV6_CODE (1 << 10) +#define CTA_FILTER_F_CTA_PROTO_ICMPV6_ID (1 << 11) +#define CTA_FILTER_F_MAX (1 << 12) +#define CTA_FILTER_F_ALL (CTA_FILTER_F_MAX-1) +#define CTA_FILTER_FLAG(ctattr) CTA_FILTER_F_ ## ctattr + /* nf_queue.c */ void nf_queue_nf_hook_drop(struct net *net); -- cgit v1.2.3 From 83fc5dd57f86c3ec7d6d22565a6ff6c948853b64 Mon Sep 17 00:00:00 2001 From: Jérôme Pouiller Date: Mon, 11 May 2020 18:19:02 +0200 Subject: mmc: fix compilation of user API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The definitions of MMC_IOC_CMD and of MMC_IOC_MULTI_CMD rely on MMC_BLOCK_MAJOR: #define MMC_IOC_CMD _IOWR(MMC_BLOCK_MAJOR, 0, struct mmc_ioc_cmd) #define MMC_IOC_MULTI_CMD _IOWR(MMC_BLOCK_MAJOR, 1, struct mmc_ioc_multi_cmd) However, MMC_BLOCK_MAJOR is defined in linux/major.h and linux/mmc/ioctl.h did not include it. Signed-off-by: Jérôme Pouiller Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200511161902.191405-1-Jerome.Pouiller@silabs.com Signed-off-by: Ulf Hansson --- include/uapi/linux/mmc/ioctl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mmc/ioctl.h b/include/uapi/linux/mmc/ioctl.h index 00c08120f3ba..27a39847d55c 100644 --- a/include/uapi/linux/mmc/ioctl.h +++ b/include/uapi/linux/mmc/ioctl.h @@ -3,6 +3,7 @@ #define LINUX_MMC_IOCTL_H #include +#include struct mmc_ioc_cmd { /* -- cgit v1.2.3 From a8a24f3f6e38103b77cf399c38eb54e1219d00d6 Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Fri, 29 May 2020 02:00:47 +0530 Subject: vfio: UAPI for migration interface for device state - Defined MIGRATION region type and sub-type. - Defined vfio_device_migration_info structure which will be placed at the 0th offset of migration region to get/set VFIO device related information. Defined members of structure and usage on read/write access. - Defined device states and state transition details. - Defined sequence to be followed while saving and resuming VFIO device. Signed-off-by: Kirti Wankhede Reviewed-by: Neo Jia Reviewed-by: Cornelia Huck Reviewed-by: Yan Zhao Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 228 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 228 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 015516bcfaa3..ad9bb5af3463 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -305,6 +305,7 @@ struct vfio_region_info_cap_type { #define VFIO_REGION_TYPE_PCI_VENDOR_MASK (0xffff) #define VFIO_REGION_TYPE_GFX (1) #define VFIO_REGION_TYPE_CCW (2) +#define VFIO_REGION_TYPE_MIGRATION (3) /* sub-types for VFIO_REGION_TYPE_PCI_* */ @@ -379,6 +380,233 @@ struct vfio_region_gfx_edid { /* sub-types for VFIO_REGION_TYPE_CCW */ #define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD (1) +/* sub-types for VFIO_REGION_TYPE_MIGRATION */ +#define VFIO_REGION_SUBTYPE_MIGRATION (1) + +/* + * The structure vfio_device_migration_info is placed at the 0th offset of + * the VFIO_REGION_SUBTYPE_MIGRATION region to get and set VFIO device related + * migration information. Field accesses from this structure are only supported + * at their native width and alignment. Otherwise, the result is undefined and + * vendor drivers should return an error. + * + * device_state: (read/write) + * - The user application writes to this field to inform the vendor driver + * about the device state to be transitioned to. + * - The vendor driver should take the necessary actions to change the + * device state. After successful transition to a given state, the + * vendor driver should return success on write(device_state, state) + * system call. If the device state transition fails, the vendor driver + * should return an appropriate -errno for the fault condition. + * - On the user application side, if the device state transition fails, + * that is, if write(device_state, state) returns an error, read + * device_state again to determine the current state of the device from + * the vendor driver. + * - The vendor driver should return previous state of the device unless + * the vendor driver has encountered an internal error, in which case + * the vendor driver may report the device_state VFIO_DEVICE_STATE_ERROR. + * - The user application must use the device reset ioctl to recover the + * device from VFIO_DEVICE_STATE_ERROR state. If the device is + * indicated to be in a valid device state by reading device_state, the + * user application may attempt to transition the device to any valid + * state reachable from the current state or terminate itself. + * + * device_state consists of 3 bits: + * - If bit 0 is set, it indicates the _RUNNING state. If bit 0 is clear, + * it indicates the _STOP state. When the device state is changed to + * _STOP, driver should stop the device before write() returns. + * - If bit 1 is set, it indicates the _SAVING state, which means that the + * driver should start gathering device state information that will be + * provided to the VFIO user application to save the device's state. + * - If bit 2 is set, it indicates the _RESUMING state, which means that + * the driver should prepare to resume the device. Data provided through + * the migration region should be used to resume the device. + * Bits 3 - 31 are reserved for future use. To preserve them, the user + * application should perform a read-modify-write operation on this + * field when modifying the specified bits. + * + * +------- _RESUMING + * |+------ _SAVING + * ||+----- _RUNNING + * ||| + * 000b => Device Stopped, not saving or resuming + * 001b => Device running, which is the default state + * 010b => Stop the device & save the device state, stop-and-copy state + * 011b => Device running and save the device state, pre-copy state + * 100b => Device stopped and the device state is resuming + * 101b => Invalid state + * 110b => Error state + * 111b => Invalid state + * + * State transitions: + * + * _RESUMING _RUNNING Pre-copy Stop-and-copy _STOP + * (100b) (001b) (011b) (010b) (000b) + * 0. Running or default state + * | + * + * 1. Normal Shutdown (optional) + * |------------------------------------->| + * + * 2. Save the state or suspend + * |------------------------->|---------->| + * + * 3. Save the state during live migration + * |----------->|------------>|---------->| + * + * 4. Resuming + * |<---------| + * + * 5. Resumed + * |--------->| + * + * 0. Default state of VFIO device is _RUNNNG when the user application starts. + * 1. During normal shutdown of the user application, the user application may + * optionally change the VFIO device state from _RUNNING to _STOP. This + * transition is optional. The vendor driver must support this transition but + * must not require it. + * 2. When the user application saves state or suspends the application, the + * device state transitions from _RUNNING to stop-and-copy and then to _STOP. + * On state transition from _RUNNING to stop-and-copy, driver must stop the + * device, save the device state and send it to the application through the + * migration region. The sequence to be followed for such transition is given + * below. + * 3. In live migration of user application, the state transitions from _RUNNING + * to pre-copy, to stop-and-copy, and to _STOP. + * On state transition from _RUNNING to pre-copy, the driver should start + * gathering the device state while the application is still running and send + * the device state data to application through the migration region. + * On state transition from pre-copy to stop-and-copy, the driver must stop + * the device, save the device state and send it to the user application + * through the migration region. + * Vendor drivers must support the pre-copy state even for implementations + * where no data is provided to the user before the stop-and-copy state. The + * user must not be required to consume all migration data before the device + * transitions to a new state, including the stop-and-copy state. + * The sequence to be followed for above two transitions is given below. + * 4. To start the resuming phase, the device state should be transitioned from + * the _RUNNING to the _RESUMING state. + * In the _RESUMING state, the driver should use the device state data + * received through the migration region to resume the device. + * 5. After providing saved device data to the driver, the application should + * change the state from _RESUMING to _RUNNING. + * + * reserved: + * Reads on this field return zero and writes are ignored. + * + * pending_bytes: (read only) + * The number of pending bytes still to be migrated from the vendor driver. + * + * data_offset: (read only) + * The user application should read data_offset field from the migration + * region. The user application should read the device data from this + * offset within the migration region during the _SAVING state or write + * the device data during the _RESUMING state. See below for details of + * sequence to be followed. + * + * data_size: (read/write) + * The user application should read data_size to get the size in bytes of + * the data copied in the migration region during the _SAVING state and + * write the size in bytes of the data copied in the migration region + * during the _RESUMING state. + * + * The format of the migration region is as follows: + * ------------------------------------------------------------------ + * |vfio_device_migration_info| data section | + * | | /////////////////////////////// | + * ------------------------------------------------------------------ + * ^ ^ + * offset 0-trapped part data_offset + * + * The structure vfio_device_migration_info is always followed by the data + * section in the region, so data_offset will always be nonzero. The offset + * from where the data is copied is decided by the kernel driver. The data + * section can be trapped, mmapped, or partitioned, depending on how the kernel + * driver defines the data section. The data section partition can be defined + * as mapped by the sparse mmap capability. If mmapped, data_offset must be + * page aligned, whereas initial section which contains the + * vfio_device_migration_info structure, might not end at the offset, which is + * page aligned. The user is not required to access through mmap regardless + * of the capabilities of the region mmap. + * The vendor driver should determine whether and how to partition the data + * section. The vendor driver should return data_offset accordingly. + * + * The sequence to be followed while in pre-copy state and stop-and-copy state + * is as follows: + * a. Read pending_bytes, indicating the start of a new iteration to get device + * data. Repeated read on pending_bytes at this stage should have no side + * effects. + * If pending_bytes == 0, the user application should not iterate to get data + * for that device. + * If pending_bytes > 0, perform the following steps. + * b. Read data_offset, indicating that the vendor driver should make data + * available through the data section. The vendor driver should return this + * read operation only after data is available from (region + data_offset) + * to (region + data_offset + data_size). + * c. Read data_size, which is the amount of data in bytes available through + * the migration region. + * Read on data_offset and data_size should return the offset and size of + * the current buffer if the user application reads data_offset and + * data_size more than once here. + * d. Read data_size bytes of data from (region + data_offset) from the + * migration region. + * e. Process the data. + * f. Read pending_bytes, which indicates that the data from the previous + * iteration has been read. If pending_bytes > 0, go to step b. + * + * The user application can transition from the _SAVING|_RUNNING + * (pre-copy state) to the _SAVING (stop-and-copy) state regardless of the + * number of pending bytes. The user application should iterate in _SAVING + * (stop-and-copy) until pending_bytes is 0. + * + * The sequence to be followed while _RESUMING device state is as follows: + * While data for this device is available, repeat the following steps: + * a. Read data_offset from where the user application should write data. + * b. Write migration data starting at the migration region + data_offset for + * the length determined by data_size from the migration source. + * c. Write data_size, which indicates to the vendor driver that data is + * written in the migration region. Vendor driver must return this write + * operations on consuming data. Vendor driver should apply the + * user-provided migration region data to the device resume state. + * + * If an error occurs during the above sequences, the vendor driver can return + * an error code for next read() or write() operation, which will terminate the + * loop. The user application should then take the next necessary action, for + * example, failing migration or terminating the user application. + * + * For the user application, data is opaque. The user application should write + * data in the same order as the data is received and the data should be of + * same transaction size at the source. + */ + +struct vfio_device_migration_info { + __u32 device_state; /* VFIO device state */ +#define VFIO_DEVICE_STATE_STOP (0) +#define VFIO_DEVICE_STATE_RUNNING (1 << 0) +#define VFIO_DEVICE_STATE_SAVING (1 << 1) +#define VFIO_DEVICE_STATE_RESUMING (1 << 2) +#define VFIO_DEVICE_STATE_MASK (VFIO_DEVICE_STATE_RUNNING | \ + VFIO_DEVICE_STATE_SAVING | \ + VFIO_DEVICE_STATE_RESUMING) + +#define VFIO_DEVICE_STATE_VALID(state) \ + (state & VFIO_DEVICE_STATE_RESUMING ? \ + (state & VFIO_DEVICE_STATE_MASK) == VFIO_DEVICE_STATE_RESUMING : 1) + +#define VFIO_DEVICE_STATE_IS_ERROR(state) \ + ((state & VFIO_DEVICE_STATE_MASK) == (VFIO_DEVICE_STATE_SAVING | \ + VFIO_DEVICE_STATE_RESUMING)) + +#define VFIO_DEVICE_STATE_SET_ERROR(state) \ + ((state & ~VFIO_DEVICE_STATE_MASK) | VFIO_DEVICE_SATE_SAVING | \ + VFIO_DEVICE_STATE_RESUMING) + + __u32 reserved; + __u64 pending_bytes; + __u64 data_offset; + __u64 data_size; +}; + /* * The MSIX mappable capability informs that MSIX data of a BAR can be mmapped * which allows direct access to non-MSIX registers which happened to be within -- cgit v1.2.3 From b704fd14a06f678f080e44db28061f1bcb1f595c Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Fri, 29 May 2020 02:00:50 +0530 Subject: vfio iommu: Add ioctl definition for dirty pages tracking IOMMU container maintains a list of all pages pinned by vfio_pin_pages API. All pages pinned by vendor driver through this API should be considered as dirty during migration. When container consists of IOMMU capable device and all pages are pinned and mapped, then all pages are marked dirty. Added support to start/stop dirtied pages tracking and to get bitmap of all dirtied pages for requested IO virtual address range. Signed-off-by: Kirti Wankhede Reviewed-by: Neo Jia Reviewed-by: Cornelia Huck Reviewed-by: Yan Zhao Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 57 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index ad9bb5af3463..009a8c80079d 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1033,6 +1033,12 @@ struct vfio_iommu_type1_dma_map { #define VFIO_IOMMU_MAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 13) +struct vfio_bitmap { + __u64 pgsize; /* page size for bitmap in bytes */ + __u64 size; /* in bytes */ + __u64 __user *data; /* one bit per page */ +}; + /** * VFIO_IOMMU_UNMAP_DMA - _IOWR(VFIO_TYPE, VFIO_BASE + 14, * struct vfio_dma_unmap) @@ -1059,6 +1065,57 @@ struct vfio_iommu_type1_dma_unmap { #define VFIO_IOMMU_ENABLE _IO(VFIO_TYPE, VFIO_BASE + 15) #define VFIO_IOMMU_DISABLE _IO(VFIO_TYPE, VFIO_BASE + 16) +/** + * VFIO_IOMMU_DIRTY_PAGES - _IOWR(VFIO_TYPE, VFIO_BASE + 17, + * struct vfio_iommu_type1_dirty_bitmap) + * IOCTL is used for dirty pages logging. + * Caller should set flag depending on which operation to perform, details as + * below: + * + * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_START flag set, instructs + * the IOMMU driver to log pages that are dirtied or potentially dirtied by + * the device; designed to be used when a migration is in progress. Dirty pages + * are logged until logging is disabled by user application by calling the IOCTL + * with VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP flag. + * + * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP flag set, instructs + * the IOMMU driver to stop logging dirtied pages. + * + * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP flag set + * returns the dirty pages bitmap for IOMMU container for a given IOVA range. + * The user must specify the IOVA range and the pgsize through the structure + * vfio_iommu_type1_dirty_bitmap_get in the data[] portion. This interface + * supports getting a bitmap of the smallest supported pgsize only and can be + * modified in future to get a bitmap of any specified supported pgsize. The + * user must provide a zeroed memory area for the bitmap memory and specify its + * size in bitmap.size. One bit is used to represent one page consecutively + * starting from iova offset. The user should provide page size in bitmap.pgsize + * field. A bit set in the bitmap indicates that the page at that offset from + * iova is dirty. The caller must set argsz to a value including the size of + * structure vfio_iommu_type1_dirty_bitmap_get, but excluding the size of the + * actual bitmap. If dirty pages logging is not enabled, an error will be + * returned. + * + * Only one of the flags _START, _STOP and _GET may be specified at a time. + * + */ +struct vfio_iommu_type1_dirty_bitmap { + __u32 argsz; + __u32 flags; +#define VFIO_IOMMU_DIRTY_PAGES_FLAG_START (1 << 0) +#define VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP (1 << 1) +#define VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP (1 << 2) + __u8 data[]; +}; + +struct vfio_iommu_type1_dirty_bitmap_get { + __u64 iova; /* IO virtual address */ + __u64 size; /* Size of iova range */ + struct vfio_bitmap bitmap; +}; + +#define VFIO_IOMMU_DIRTY_PAGES _IO(VFIO_TYPE, VFIO_BASE + 17) + /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */ /* -- cgit v1.2.3 From 331e33d2960c8292bad8b02578fcfac18f721517 Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Fri, 29 May 2020 02:00:52 +0530 Subject: vfio iommu: Update UNMAP_DMA ioctl to get dirty bitmap before unmap DMA mapped pages, including those pinned by mdev vendor drivers, might get unpinned and unmapped while migration is active and device is still running. For example, in pre-copy phase while guest driver could access those pages, host device or vendor driver can dirty these mapped pages. Such pages should be marked dirty so as to maintain memory consistency for a user making use of dirty page tracking. To get bitmap during unmap, user should allocate memory for bitmap, set it all zeros, set size of allocated memory, set page size to be considered for bitmap and set flag VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP. Signed-off-by: Kirti Wankhede Reviewed-by: Neo Jia Reviewed-by: Cornelia Huck Reviewed-by: Yan Zhao Signed-off-by: Alex Williamson --- drivers/vfio/vfio_iommu_type1.c | 61 +++++++++++++++++++++++++++++++++-------- include/uapi/linux/vfio.h | 11 ++++++++ 2 files changed, 61 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index be6fc0d88633..e31fcc23e81a 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1049,23 +1049,25 @@ static int verify_bitmap_size(uint64_t npages, uint64_t bitmap_size) } static int vfio_dma_do_unmap(struct vfio_iommu *iommu, - struct vfio_iommu_type1_dma_unmap *unmap) + struct vfio_iommu_type1_dma_unmap *unmap, + struct vfio_bitmap *bitmap) { - uint64_t mask; struct vfio_dma *dma, *dma_last = NULL; - size_t unmapped = 0; + size_t unmapped = 0, pgsize; int ret = 0, retries = 0; + unsigned long pgshift; mutex_lock(&iommu->lock); - mask = ((uint64_t)1 << __ffs(iommu->pgsize_bitmap)) - 1; + pgshift = __ffs(iommu->pgsize_bitmap); + pgsize = (size_t)1 << pgshift; - if (unmap->iova & mask) { + if (unmap->iova & (pgsize - 1)) { ret = -EINVAL; goto unlock; } - if (!unmap->size || unmap->size & mask) { + if (!unmap->size || unmap->size & (pgsize - 1)) { ret = -EINVAL; goto unlock; } @@ -1076,9 +1078,15 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu, goto unlock; } - WARN_ON(mask & PAGE_MASK); -again: + /* When dirty tracking is enabled, allow only min supported pgsize */ + if ((unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) && + (!iommu->dirty_page_tracking || (bitmap->pgsize != pgsize))) { + ret = -EINVAL; + goto unlock; + } + WARN_ON((pgsize - 1) & PAGE_MASK); +again: /* * vfio-iommu-type1 (v1) - User mappings were coalesced together to * avoid tracking individual mappings. This means that the granularity @@ -1159,6 +1167,14 @@ again: mutex_lock(&iommu->lock); goto again; } + + if (unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) { + ret = update_user_bitmap(bitmap->data, dma, + unmap->iova, pgsize); + if (ret) + break; + } + unmapped += dma->size; vfio_remove_dma(iommu, dma); } @@ -2497,17 +2513,40 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, } else if (cmd == VFIO_IOMMU_UNMAP_DMA) { struct vfio_iommu_type1_dma_unmap unmap; - long ret; + struct vfio_bitmap bitmap = { 0 }; + int ret; minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size); if (copy_from_user(&unmap, (void __user *)arg, minsz)) return -EFAULT; - if (unmap.argsz < minsz || unmap.flags) + if (unmap.argsz < minsz || + unmap.flags & ~VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) return -EINVAL; - ret = vfio_dma_do_unmap(iommu, &unmap); + if (unmap.flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) { + unsigned long pgshift; + + if (unmap.argsz < (minsz + sizeof(bitmap))) + return -EINVAL; + + if (copy_from_user(&bitmap, + (void __user *)(arg + minsz), + sizeof(bitmap))) + return -EFAULT; + + if (!access_ok((void __user *)bitmap.data, bitmap.size)) + return -EINVAL; + + pgshift = __ffs(bitmap.pgsize); + ret = verify_bitmap_size(unmap.size >> pgshift, + bitmap.size); + if (ret) + return ret; + } + + ret = vfio_dma_do_unmap(iommu, &unmap, &bitmap); if (ret) return ret; diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 009a8c80079d..ff4b6706f7df 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1048,12 +1048,23 @@ struct vfio_bitmap { * field. No guarantee is made to the user that arbitrary unmaps of iova * or size different from those used in the original mapping call will * succeed. + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get the dirty bitmap + * before unmapping IO virtual addresses. When this flag is set, the user must + * provide a struct vfio_bitmap in data[]. User must provide zero-allocated + * memory via vfio_bitmap.data and its size in the vfio_bitmap.size field. + * A bit in the bitmap represents one page, of user provided page size in + * vfio_bitmap.pgsize field, consecutively starting from iova offset. Bit set + * indicates that the page at that offset from iova is dirty. A Bitmap of the + * pages in the range of unmapped size is returned in the user-provided + * vfio_bitmap.data. */ struct vfio_iommu_type1_dma_unmap { __u32 argsz; __u32 flags; +#define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0) __u64 iova; /* IO virtual address */ __u64 size; /* Size of mapping (bytes) */ + __u8 data[]; }; #define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14) -- cgit v1.2.3 From ad721705d09c62f0d108a6b4f59867ebfd592c90 Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Fri, 29 May 2020 02:00:53 +0530 Subject: vfio iommu: Add migration capability to report supported features Added migration capability in IOMMU info chain. User application should check IOMMU info chain for migration capability to use dirty page tracking feature provided by kernel module. User application must check page sizes supported and maximum dirty bitmap size returned by this capability structure for ioctls used to get dirty bitmap. Signed-off-by: Kirti Wankhede Reviewed-by: Cornelia Huck Reviewed-by: Yan Zhao Signed-off-by: Alex Williamson --- drivers/vfio/vfio_iommu_type1.c | 23 ++++++++++++++++++++++- include/uapi/linux/vfio.h | 23 +++++++++++++++++++++++ 2 files changed, 45 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index e31fcc23e81a..f5c6ca46f165 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -2423,6 +2423,22 @@ static int vfio_iommu_iova_build_caps(struct vfio_iommu *iommu, return ret; } +static int vfio_iommu_migration_build_caps(struct vfio_iommu *iommu, + struct vfio_info_cap *caps) +{ + struct vfio_iommu_type1_info_cap_migration cap_mig; + + cap_mig.header.id = VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION; + cap_mig.header.version = 1; + + cap_mig.flags = 0; + /* support minimum pgsize */ + cap_mig.pgsize_bitmap = (size_t)1 << __ffs(iommu->pgsize_bitmap); + cap_mig.max_dirty_bitmap_size = DIRTY_BITMAP_SIZE_MAX; + + return vfio_info_add_capability(caps, &cap_mig.header, sizeof(cap_mig)); +} + static long vfio_iommu_type1_ioctl(void *iommu_data, unsigned int cmd, unsigned long arg) { @@ -2469,8 +2485,13 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, info.iova_pgsizes = iommu->pgsize_bitmap; - ret = vfio_iommu_iova_build_caps(iommu, &caps); + ret = vfio_iommu_migration_build_caps(iommu, &caps); + + if (!ret) + ret = vfio_iommu_iova_build_caps(iommu, &caps); + mutex_unlock(&iommu->lock); + if (ret) return ret; diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index ff4b6706f7df..fde4692a6989 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1013,6 +1013,29 @@ struct vfio_iommu_type1_info_cap_iova_range { struct vfio_iova_range iova_ranges[]; }; +/* + * The migration capability allows to report supported features for migration. + * + * The structures below define version 1 of this capability. + * + * The existence of this capability indicates that IOMMU kernel driver supports + * dirty page logging. + * + * pgsize_bitmap: Kernel driver returns bitmap of supported page sizes for dirty + * page logging. + * max_dirty_bitmap_size: Kernel driver returns maximum supported dirty bitmap + * size in bytes that can be used by user applications when getting the dirty + * bitmap. + */ +#define VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION 1 + +struct vfio_iommu_type1_info_cap_migration { + struct vfio_info_cap_header header; + __u32 flags; + __u64 pgsize_bitmap; + __u64 max_dirty_bitmap_size; /* in bytes */ +}; + #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12) /** -- cgit v1.2.3 From 43e64bf301fd8c54f0082d91c6ffd4de861baf96 Mon Sep 17 00:00:00 2001 From: Rajkumar Manoharan Date: Thu, 28 May 2020 21:34:29 +0200 Subject: cfg80211: handle 6 GHz capability of new station Handle 6 GHz HE capability while adding new station. It will be used later in mac80211 station processing. Signed-off-by: Rajkumar Manoharan Link: https://lore.kernel.org/r/1589399105-25472-2-git-send-email-rmanohar@codeaurora.org [handle nl80211_set_station, require WME, remove NL80211_HE_6GHZ_CAPABILITY_LEN] Link: https://lore.kernel.org/r/20200528213443.b6b711fd4312.Ic9b97d57b6c4f2b28d4b2d23d2849d8bc20bd8cc@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ include/uapi/linux/nl80211.h | 5 +++++ net/wireless/nl80211.c | 18 +++++++++++++++++- 3 files changed, 24 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index a38653358885..da734ea71b5a 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1238,6 +1238,7 @@ struct sta_txpwr { * @he_capa_len: the length of the HE capabilities * @airtime_weight: airtime scheduler weight for this station * @txpwr: transmit power for an associated station + * @he_6ghz_capa: HE 6 GHz Band capabilities of station */ struct station_parameters { const u8 *supported_rates; @@ -1270,6 +1271,7 @@ struct station_parameters { u8 he_capa_len; u16 airtime_weight; struct sta_txpwr txpwr; + const struct ieee80211_he_6ghz_capa *he_6ghz_capa; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c14666b75e57..e42ae429383e 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2502,6 +2502,9 @@ enum nl80211_commands { * first channel segment specified in %NL80211_ATTR_CENTER_FREQ1. * @NL80211_ATTR_SCAN_FREQ_KHZ: nested attribute with KHz frequencies * + * @NL80211_ATTR_HE_6GHZ_CAPABILITY: HE 6 GHz Band Capability element (from + * association request when used with NL80211_CMD_NEW_STATION). + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2982,6 +2985,8 @@ enum nl80211_attrs { NL80211_ATTR_CENTER_FREQ1_OFFSET, NL80211_ATTR_SCAN_FREQ_KHZ, + NL80211_ATTR_HE_6GHZ_CAPABILITY, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 22c4d13e28cb..bf8bd8268cb7 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -654,6 +654,10 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_RECEIVE_MULTICAST] = { .type = NLA_FLAG }, [NL80211_ATTR_WIPHY_FREQ_OFFSET] = NLA_POLICY_RANGE(NLA_U32, 0, 999), [NL80211_ATTR_SCAN_FREQ_KHZ] = { .type = NLA_NESTED }, + [NL80211_ATTR_HE_6GHZ_CAPABILITY] = { + .type = NLA_EXACT_LEN, + .len = sizeof(struct ieee80211_he_6ghz_capa), + }, }; /* policy for the key attributes */ @@ -5989,6 +5993,10 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) nla_get_u8(info->attrs[NL80211_ATTR_OPMODE_NOTIF]); } + if (info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]) + params.he_6ghz_capa = + nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + if (info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]) params.airtime_weight = nla_get_u16(info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]); @@ -6123,6 +6131,10 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } + if (info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]) + params.he_6ghz_capa = + nla_data(info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]); + if (info->attrs[NL80211_ATTR_OPMODE_NOTIF]) { params.opmode_notif_used = true; params.opmode_notif = @@ -6167,10 +6179,14 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) params.vht_capa = NULL; /* HE requires WME */ - if (params.he_capa_len) + if (params.he_capa_len || params.he_6ghz_capa) return -EINVAL; } + /* Ensure that HT/VHT capabilities are not set for 6 GHz HE STA */ + if (params.he_6ghz_capa && (params.ht_capa || params.vht_capa)) + return -EINVAL; + /* When you run into this, adjust the code below for the new flag */ BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 7); -- cgit v1.2.3 From 223952177296c34d9c8de9cde33204caffe55725 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 28 May 2020 21:34:31 +0200 Subject: cfg80211: add and expose HE 6 GHz band capabilities These capabilities cover what would otherwise be transported in HT/VHT capabilities, but only a subset thereof that is actually needed on 6 GHz with HE already present. Expose the capabilities to userspace, drivers are expected to set them as using the 6 GHz band (currently) requires HE capability. Link: https://lore.kernel.org/r/20200528213443.244cd5cb9db8.Icd8c773277a88c837e7e3af1d4d1013cc3b66543@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 3 +++ include/uapi/linux/nl80211.h | 3 +++ net/wireless/nl80211.c | 9 ++++++++- 3 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index da734ea71b5a..9b76be3d561a 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -354,10 +354,13 @@ struct ieee80211_sta_he_cap { * * @types_mask: interface types mask * @he_cap: holds the HE capabilities + * @he_6ghz_capa: HE 6 GHz capabilities, must be filled in for a + * 6 GHz band channel (and 0 may be valid value). */ struct ieee80211_sband_iftype_data { u16 types_mask; struct ieee80211_sta_he_cap he_cap; + struct ieee80211_he_6ghz_capa he_6ghz_capa; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index e42ae429383e..5b350d032fa3 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3565,6 +3565,8 @@ enum nl80211_mpath_info { * defined in HE capabilities IE * @NL80211_BAND_IFTYPE_ATTR_MAX: highest band HE capability attribute currently * defined + * @NL80211_BAND_IFTYPE_ATTR_HE_6GHZ_CAPA: HE 6GHz band capabilities (__le16), + * given for all 6 GHz band channels * @__NL80211_BAND_IFTYPE_ATTR_AFTER_LAST: internal use */ enum nl80211_band_iftype_attr { @@ -3575,6 +3577,7 @@ enum nl80211_band_iftype_attr { NL80211_BAND_IFTYPE_ATTR_HE_CAP_PHY, NL80211_BAND_IFTYPE_ATTR_HE_CAP_MCS_SET, NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE, + NL80211_BAND_IFTYPE_ATTR_HE_6GHZ_CAPA, /* keep last */ __NL80211_BAND_IFTYPE_ATTR_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index bf8bd8268cb7..3a24e6add13e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1562,6 +1562,7 @@ static int nl80211_send_coalesce(struct sk_buff *msg, static int nl80211_send_iftype_data(struct sk_buff *msg, + const struct ieee80211_supported_band *sband, const struct ieee80211_sband_iftype_data *iftdata) { const struct ieee80211_sta_he_cap *he_cap = &iftdata->he_cap; @@ -1585,6 +1586,12 @@ nl80211_send_iftype_data(struct sk_buff *msg, return -ENOBUFS; } + if (sband->band == NL80211_BAND_6GHZ && + nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_6GHZ_CAPA, + sizeof(iftdata->he_6ghz_capa), + &iftdata->he_6ghz_capa)) + return -ENOBUFS; + return 0; } @@ -1633,7 +1640,7 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg, if (!iftdata) return -ENOBUFS; - err = nl80211_send_iftype_data(msg, + err = nl80211_send_iftype_data(msg, sband, &sband->iftype_data[i]); if (err) return err; -- cgit v1.2.3 From 093a48d2aa4b74db3134b61d7b7a061dbe79177b Mon Sep 17 00:00:00 2001 From: Nathan Errera Date: Thu, 28 May 2020 21:22:38 +0200 Subject: cfg80211: support bigger kek/kck key length With some newer AKMs, the KCK and KEK are bigger, so allow that if the driver advertises support for it. In addition, add a new attribute for the AKM so we can use it for offloaded rekeying. Signed-off-by: Nathan Errera [reword commit message] Link: https://lore.kernel.org/r/20200528212237.5eb58b00a5d1.I61b09d77c4f382e8d58a05dcca78096e99a6bc15@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 12 +++++++++--- include/uapi/linux/nl80211.h | 4 ++++ net/wireless/nl80211.c | 23 +++++++++++++++++++---- 3 files changed, 32 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 95b55eea2afb..b58ad1a3f695 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2936,12 +2936,17 @@ struct cfg80211_wowlan_wakeup { /** * struct cfg80211_gtk_rekey_data - rekey data - * @kek: key encryption key (NL80211_KEK_LEN bytes) - * @kck: key confirmation key (NL80211_KCK_LEN bytes) + * @kek: key encryption key (@kek_len bytes) + * @kck: key confirmation key (@kck_len bytes) * @replay_ctr: replay counter (NL80211_REPLAY_CTR_LEN bytes) + * @kek_len: length of kek + * @kck_len length of kck + * @akm: akm (oui, id) */ struct cfg80211_gtk_rekey_data { const u8 *kek, *kck, *replay_ctr; + u32 akm; + u8 kek_len, kck_len; }; /** @@ -4166,9 +4171,10 @@ struct cfg80211_ops { * beaconing mode (AP, IBSS, Mesh, ...). * @WIPHY_FLAG_HAS_STATIC_WEP: The device supports static WEP key installation * before connection. + * @WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK: The device supports bigger kek and kck keys */ enum wiphy_flags { - /* use hole at 0 */ + WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK = BIT(0), /* use hole at 1 */ /* use hole at 2 */ WIPHY_FLAG_NETNS_OK = BIT(3), diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 5b350d032fa3..dad8c8f8581f 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5396,6 +5396,8 @@ enum plink_actions { #define NL80211_KCK_LEN 16 #define NL80211_KEK_LEN 16 +#define NL80211_KCK_EXT_LEN 24 +#define NL80211_KEK_EXT_LEN 32 #define NL80211_REPLAY_CTR_LEN 8 /** @@ -5404,6 +5406,7 @@ enum plink_actions { * @NL80211_REKEY_DATA_KEK: key encryption key (binary) * @NL80211_REKEY_DATA_KCK: key confirmation key (binary) * @NL80211_REKEY_DATA_REPLAY_CTR: replay counter (binary) + * @NL80211_REKEY_DATA_AKM: AKM data (OUI, suite type) * @NUM_NL80211_REKEY_DATA: number of rekey attributes (internal) * @MAX_NL80211_REKEY_DATA: highest rekey attribute (internal) */ @@ -5412,6 +5415,7 @@ enum nl80211_rekey_data { NL80211_REKEY_DATA_KEK, NL80211_REKEY_DATA_KCK, NL80211_REKEY_DATA_REPLAY_CTR, + NL80211_REKEY_DATA_AKM, /* keep last */ NUM_NL80211_REKEY_DATA, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 3a24e6add13e..263ae395ad44 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -730,9 +730,16 @@ nl80211_coalesce_policy[NUM_NL80211_ATTR_COALESCE_RULE] = { /* policy for GTK rekey offload attributes */ static const struct nla_policy nl80211_rekey_policy[NUM_NL80211_REKEY_DATA] = { - [NL80211_REKEY_DATA_KEK] = NLA_POLICY_EXACT_LEN_WARN(NL80211_KEK_LEN), - [NL80211_REKEY_DATA_KCK] = NLA_POLICY_EXACT_LEN_WARN(NL80211_KCK_LEN), + [NL80211_REKEY_DATA_KEK] = { + .type = NLA_BINARY, + .len = NL80211_KEK_EXT_LEN + }, + [NL80211_REKEY_DATA_KCK] = { + .type = NLA_BINARY, + .len = NL80211_KCK_EXT_LEN + }, [NL80211_REKEY_DATA_REPLAY_CTR] = NLA_POLICY_EXACT_LEN_WARN(NL80211_REPLAY_CTR_LEN), + [NL80211_REKEY_DATA_AKM] = { .type = NLA_U32 }, }; static const struct nla_policy @@ -12347,14 +12354,22 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info) return -EINVAL; if (nla_len(tb[NL80211_REKEY_DATA_REPLAY_CTR]) != NL80211_REPLAY_CTR_LEN) return -ERANGE; - if (nla_len(tb[NL80211_REKEY_DATA_KEK]) != NL80211_KEK_LEN) + if (nla_len(tb[NL80211_REKEY_DATA_KEK]) != NL80211_KEK_LEN && + !(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK && + nla_len(tb[NL80211_REKEY_DATA_KEK]) == NL80211_KEK_EXT_LEN)) return -ERANGE; - if (nla_len(tb[NL80211_REKEY_DATA_KCK]) != NL80211_KCK_LEN) + if (nla_len(tb[NL80211_REKEY_DATA_KCK]) != NL80211_KCK_LEN && + !(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK && + nla_len(tb[NL80211_REKEY_DATA_KEK]) == NL80211_KCK_EXT_LEN)) return -ERANGE; rekey_data.kek = nla_data(tb[NL80211_REKEY_DATA_KEK]); rekey_data.kck = nla_data(tb[NL80211_REKEY_DATA_KCK]); rekey_data.replay_ctr = nla_data(tb[NL80211_REKEY_DATA_REPLAY_CTR]); + rekey_data.kek_len = nla_len(tb[NL80211_REKEY_DATA_KEK]); + rekey_data.kck_len = nla_len(tb[NL80211_REKEY_DATA_KCK]); + if (tb[NL80211_REKEY_DATA_AKM]) + rekey_data.akm = nla_get_u32(tb[NL80211_REKEY_DATA_AKM]); wdev_lock(wdev); if (!wdev->current_bss) { -- cgit v1.2.3 From 72de5fa4c16195827252b961ba44028a39dfeaff Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 25 May 2020 16:41:22 +0200 Subject: KVM: x86: announce KVM_FEATURE_ASYNC_PF_INT Introduce new capability to indicate that KVM supports interrupt based delivery of 'page ready' APF events. This includes support for both MSR_KVM_ASYNC_PF_INT and MSR_KVM_ASYNC_PF_ACK. Signed-off-by: Vitaly Kuznetsov Message-Id: <20200525144125.143875-8-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/cpuid.rst | 6 ++++++ Documentation/virt/kvm/msr.rst | 12 ++++++++---- arch/x86/include/uapi/asm/kvm_para.h | 1 + arch/x86/kvm/cpuid.c | 3 ++- arch/x86/kvm/x86.c | 1 + include/uapi/linux/kvm.h | 1 + 6 files changed, 19 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/cpuid.rst b/Documentation/virt/kvm/cpuid.rst index f721c89327ec..a7dff9186bed 100644 --- a/Documentation/virt/kvm/cpuid.rst +++ b/Documentation/virt/kvm/cpuid.rst @@ -86,6 +86,12 @@ KVM_FEATURE_PV_SCHED_YIELD 13 guest checks this feature bit before using paravirtualized sched yield. +KVM_FEATURE_ASYNC_PF_INT 14 guest checks this feature bit + before using the second async + pf control msr 0x4b564d06 and + async pf acknowledgment msr + 0x4b564d07. + KVM_FEATURE_CLOCSOURCE_STABLE_BIT 24 host will warn if no guest-side per-cpu warps are expeced in kvmclock diff --git a/Documentation/virt/kvm/msr.rst b/Documentation/virt/kvm/msr.rst index 9b107889b033..e37a14c323d2 100644 --- a/Documentation/virt/kvm/msr.rst +++ b/Documentation/virt/kvm/msr.rst @@ -213,7 +213,8 @@ data: cpl == 0. Bit 2 is 1 if asynchronous page faults are delivered to L1 as #PF vmexits. Bit 2 can be set only if KVM_FEATURE_ASYNC_PF_VMEXIT is present in CPUID. Bit 3 enables interrupt based delivery of 'page ready' - events. + events. Bit 3 can only be set if KVM_FEATURE_ASYNC_PF_INT is present in + CPUID. 'Page not present' events are currently always delivered as synthetic #PF exception. During delivery of these events APF CR2 register contains @@ -242,7 +243,8 @@ data: Note, MSR_KVM_ASYNC_PF_INT MSR specifying the interrupt vector for 'page ready' APF delivery needs to be written to before enabling APF mechanism - in MSR_KVM_ASYNC_PF_EN or interrupt #0 can get injected. + in MSR_KVM_ASYNC_PF_EN or interrupt #0 can get injected. The MSR is + available if KVM_FEATURE_ASYNC_PF_INT is present in CPUID. Note, previously, 'page ready' events were delivered via the same #PF exception as 'page not present' events but this is now deprecated. If @@ -360,7 +362,8 @@ data: Interrupt vector for asynchnonous 'page ready' notifications delivery. The vector has to be set up before asynchronous page fault mechanism - is enabled in MSR_KVM_ASYNC_PF_EN. + is enabled in MSR_KVM_ASYNC_PF_EN. The MSR is only available if + KVM_FEATURE_ASYNC_PF_INT is present in CPUID. MSR_KVM_ASYNC_PF_ACK: 0x4b564d07 @@ -371,4 +374,5 @@ data: When the guest is done processing 'page ready' APF event and 'token' field in 'struct kvm_vcpu_pv_apf_data' is cleared it is supposed to write '1' to bit 0 of the MSR, this causes the host to re-scan its queue - and check if there are more notifications pending. + and check if there are more notifications pending. The MSR is available + if KVM_FEATURE_ASYNC_PF_INT is present in CPUID. diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 7ac20df80ba8..812e9b4c1114 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -31,6 +31,7 @@ #define KVM_FEATURE_PV_SEND_IPI 11 #define KVM_FEATURE_POLL_CONTROL 12 #define KVM_FEATURE_PV_SCHED_YIELD 13 +#define KVM_FEATURE_ASYNC_PF_INT 14 #define KVM_HINTS_REALTIME 0 diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index cd708b0b460a..a9f1905896fb 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -711,7 +711,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) (1 << KVM_FEATURE_ASYNC_PF_VMEXIT) | (1 << KVM_FEATURE_PV_SEND_IPI) | (1 << KVM_FEATURE_POLL_CONTROL) | - (1 << KVM_FEATURE_PV_SCHED_YIELD); + (1 << KVM_FEATURE_PV_SCHED_YIELD) | + (1 << KVM_FEATURE_ASYNC_PF_INT); if (sched_info_on()) entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c9d709a672f3..ae3a7f2fbda2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3446,6 +3446,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_X86_ROBUST_SINGLESTEP: case KVM_CAP_XSAVE: case KVM_CAP_ASYNC_PF: + case KVM_CAP_ASYNC_PF_INT: case KVM_CAP_GET_TSC_KHZ: case KVM_CAP_KVMCLOCK_CTRL: case KVM_CAP_READONLY_MEM: diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ac9eba0289d1..fc0075988b80 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1018,6 +1018,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_PROTECTED 180 #define KVM_CAP_PPC_SECURE_GUEST 181 #define KVM_CAP_HALT_POLL 182 +#define KVM_CAP_ASYNC_PF_INT 183 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From f7d31e65368aeef973fab788aa22c4f1d5a6af66 Mon Sep 17 00:00:00 2001 From: Jon Doron Date: Fri, 24 Apr 2020 14:37:40 +0300 Subject: x86/kvm/hyper-v: Explicitly align hcall param for kvm_hyperv_exit The problem the patch is trying to address is the fact that 'struct kvm_hyperv_exit' has different layout on when compiling in 32 and 64 bit modes. In 64-bit mode the default alignment boundary is 64 bits thus forcing extra gaps after 'type' and 'msr' but in 32-bit mode the boundary is at 32 bits thus no extra gaps. This is an issue as even when the kernel is 64 bit, the userspace using the interface can be both 32 and 64 bit but the same 32 bit userspace has to work with 32 bit kernel. The issue is fixed by forcing the 64 bit layout, this leads to ABI change for 32 bit builds and while we are obviously breaking '32 bit userspace with 32 bit kernel' case, we're fixing the '32 bit userspace with 64 bit kernel' one. As the interface has no (known) users and 32 bit KVM is rather baroque nowadays, this seems like a reasonable decision. Reviewed-by: Vitaly Kuznetsov Signed-off-by: Jon Doron Message-Id: <20200424113746.3473563-2-arilou@gmail.com> Reviewed-by: Roman Kagan Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 2 ++ include/uapi/linux/kvm.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index d871dacb984e..d0569db2b1e2 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5067,9 +5067,11 @@ EOI was received. #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 __u32 type; + __u32 pad1; union { struct { __u32 msr; + __u32 pad2; __u64 control; __u64 evt_page; __u64 msg_page; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index fc0075988b80..cc04aceb8793 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -189,9 +189,11 @@ struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 __u32 type; + __u32 pad1; union { struct { __u32 msr; + __u32 pad2; __u64 control; __u64 evt_page; __u64 msg_page; -- cgit v1.2.3 From f97f5a56f5977311f3833056a73cdbb0ee56cb1e Mon Sep 17 00:00:00 2001 From: Jon Doron Date: Fri, 29 May 2020 16:45:40 +0300 Subject: x86/kvm/hyper-v: Add support for synthetic debugger interface Add support for Hyper-V synthetic debugger (syndbg) interface. The syndbg interface is using MSRs to emulate a way to send/recv packets data. The debug transport dll (kdvm/kdnet) will identify if Hyper-V is enabled and if it supports the synthetic debugger interface it will attempt to use it, instead of trying to initialize a network adapter. Reviewed-by: Vitaly Kuznetsov Signed-off-by: Jon Doron Message-Id: <20200529134543.1127440-4-arilou@gmail.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 16 ++++ arch/x86/include/asm/kvm_host.h | 13 ++++ arch/x86/kvm/hyperv.c | 158 +++++++++++++++++++++++++++++++++++++++- arch/x86/kvm/hyperv.h | 5 ++ arch/x86/kvm/trace.h | 51 +++++++++++++ arch/x86/kvm/x86.c | 8 ++ include/uapi/linux/kvm.h | 10 +++ 7 files changed, 258 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index db22e834ce2a..aad60be4884e 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5070,6 +5070,7 @@ EOI was received. struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 + #define KVM_EXIT_HYPERV_SYNDBG 3 __u32 type; __u32 pad1; union { @@ -5085,6 +5086,15 @@ EOI was received. __u64 result; __u64 params[2]; } hcall; + struct { + __u32 msr; + __u32 pad2; + __u64 control; + __u64 status; + __u64 send_page; + __u64 recv_page; + __u64 pending_page; + } syndbg; } u; }; /* KVM_EXIT_HYPERV */ @@ -5101,6 +5111,12 @@ Hyper-V SynIC state change. Notification is used to remap SynIC event/message pages and to enable/disable SynIC messages/events processing in userspace. + - KVM_EXIT_HYPERV_SYNDBG -- synchronously notify user-space about + +Hyper-V Synthetic debugger state change. Notification is used to either update +the pending_page location or to send a control command (send the buffer located +in send_page or recv a buffer to recv_page). + :: /* KVM_EXIT_ARM_NISV */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b878fcd164ce..58337a25396a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -863,6 +863,18 @@ struct kvm_apic_map { struct kvm_lapic *phys_map[]; }; +/* Hyper-V synthetic debugger (SynDbg)*/ +struct kvm_hv_syndbg { + struct { + u64 control; + u64 status; + u64 send_page; + u64 recv_page; + u64 pending_page; + } control; + u64 options; +}; + /* Hyper-V emulation context */ struct kvm_hv { struct mutex hv_lock; @@ -886,6 +898,7 @@ struct kvm_hv { atomic_t num_mismatched_vp_indexes; struct hv_partition_assist_pg *hv_pa_pg; + struct kvm_hv_syndbg hv_syndbg; }; enum kvm_irqchip_mode { diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index f9d3b919823c..c21f99357ad5 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -21,6 +21,7 @@ #include "x86.h" #include "lapic.h" #include "ioapic.h" +#include "cpuid.h" #include "hyperv.h" #include @@ -266,6 +267,123 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, return ret; } +static bool kvm_hv_is_syndbg_enabled(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *entry; + + entry = kvm_find_cpuid_entry(vcpu, + HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES, + 0); + if (!entry) + return false; + + return entry->eax & HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; +} + +static int kvm_hv_syndbg_complete_userspace(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_hv *hv = &kvm->arch.hyperv; + + if (vcpu->run->hyperv.u.syndbg.msr == HV_X64_MSR_SYNDBG_CONTROL) + hv->hv_syndbg.control.status = + vcpu->run->hyperv.u.syndbg.status; + return 1; +} + +static void syndbg_exit(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu); + struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv; + + hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNDBG; + hv_vcpu->exit.u.syndbg.msr = msr; + hv_vcpu->exit.u.syndbg.control = syndbg->control.control; + hv_vcpu->exit.u.syndbg.send_page = syndbg->control.send_page; + hv_vcpu->exit.u.syndbg.recv_page = syndbg->control.recv_page; + hv_vcpu->exit.u.syndbg.pending_page = syndbg->control.pending_page; + vcpu->arch.complete_userspace_io = + kvm_hv_syndbg_complete_userspace; + + kvm_make_request(KVM_REQ_HV_EXIT, vcpu); +} + +static int syndbg_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) +{ + struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu); + + if (!kvm_hv_is_syndbg_enabled(vcpu) && !host) + return 1; + + trace_kvm_hv_syndbg_set_msr(vcpu->vcpu_id, + vcpu_to_hv_vcpu(vcpu)->vp_index, msr, data); + switch (msr) { + case HV_X64_MSR_SYNDBG_CONTROL: + syndbg->control.control = data; + if (!host) + syndbg_exit(vcpu, msr); + break; + case HV_X64_MSR_SYNDBG_STATUS: + syndbg->control.status = data; + break; + case HV_X64_MSR_SYNDBG_SEND_BUFFER: + syndbg->control.send_page = data; + break; + case HV_X64_MSR_SYNDBG_RECV_BUFFER: + syndbg->control.recv_page = data; + break; + case HV_X64_MSR_SYNDBG_PENDING_BUFFER: + syndbg->control.pending_page = data; + if (!host) + syndbg_exit(vcpu, msr); + break; + case HV_X64_MSR_SYNDBG_OPTIONS: + syndbg->options = data; + break; + default: + break; + } + + return 0; +} + +static int syndbg_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) +{ + struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu); + + if (!kvm_hv_is_syndbg_enabled(vcpu) && !host) + return 1; + + switch (msr) { + case HV_X64_MSR_SYNDBG_CONTROL: + *pdata = syndbg->control.control; + break; + case HV_X64_MSR_SYNDBG_STATUS: + *pdata = syndbg->control.status; + break; + case HV_X64_MSR_SYNDBG_SEND_BUFFER: + *pdata = syndbg->control.send_page; + break; + case HV_X64_MSR_SYNDBG_RECV_BUFFER: + *pdata = syndbg->control.recv_page; + break; + case HV_X64_MSR_SYNDBG_PENDING_BUFFER: + *pdata = syndbg->control.pending_page; + break; + case HV_X64_MSR_SYNDBG_OPTIONS: + *pdata = syndbg->options; + break; + default: + break; + } + + trace_kvm_hv_syndbg_get_msr(vcpu->vcpu_id, + vcpu_to_hv_vcpu(vcpu)->vp_index, msr, + *pdata); + + return 0; +} + static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata, bool host) { @@ -800,6 +918,8 @@ static bool kvm_hv_msr_partition_wide(u32 msr) case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: + case HV_X64_MSR_SYNDBG_OPTIONS: + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: r = true; break; } @@ -1061,6 +1181,9 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, if (!host) return 1; break; + case HV_X64_MSR_SYNDBG_OPTIONS: + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: + return syndbg_set_msr(vcpu, msr, data, host); default: vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", msr, data); @@ -1190,7 +1313,8 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 0; } -static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, + bool host) { u64 data = 0; struct kvm *kvm = vcpu->kvm; @@ -1227,6 +1351,9 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case HV_X64_MSR_TSC_EMULATION_STATUS: data = hv->hv_tsc_emulation_status; break; + case HV_X64_MSR_SYNDBG_OPTIONS: + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: + return syndbg_get_msr(vcpu, msr, pdata, host); default: vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); return 1; @@ -1316,7 +1443,7 @@ int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) int r; mutex_lock(&vcpu->kvm->arch.hyperv.hv_lock); - r = kvm_hv_get_msr_pw(vcpu, msr, pdata); + r = kvm_hv_get_msr_pw(vcpu, msr, pdata, host); mutex_unlock(&vcpu->kvm->arch.hyperv.hv_lock); return r; } else @@ -1795,6 +1922,9 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, { .function = HYPERV_CPUID_FEATURES }, { .function = HYPERV_CPUID_ENLIGHTMENT_INFO }, { .function = HYPERV_CPUID_IMPLEMENT_LIMITS }, + { .function = HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS }, + { .function = HYPERV_CPUID_SYNDBG_INTERFACE }, + { .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES }, { .function = HYPERV_CPUID_NESTED_FEATURES }, }; int i, nent = ARRAY_SIZE(cpuid_entries); @@ -1820,7 +1950,7 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, case HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS: memcpy(signature, "Linux KVM Hv", 12); - ent->eax = HYPERV_CPUID_NESTED_FEATURES; + ent->eax = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES; ent->ebx = signature[0]; ent->ecx = signature[1]; ent->edx = signature[2]; @@ -1859,6 +1989,10 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE; ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; + ent->ebx |= HV_X64_DEBUGGING; + ent->edx |= HV_X64_GUEST_DEBUGGING_AVAILABLE; + ent->edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE; + /* * Direct Synthetic timers only make sense with in-kernel * LAPIC @@ -1902,6 +2036,24 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, break; + case HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS: + memcpy(signature, "Linux KVM Hv", 12); + + ent->eax = 0; + ent->ebx = signature[0]; + ent->ecx = signature[1]; + ent->edx = signature[2]; + break; + + case HYPERV_CPUID_SYNDBG_INTERFACE: + memcpy(signature, "VS#1\0\0\0\0\0\0\0\0", 12); + ent->eax = signature[0]; + break; + + case HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES: + ent->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + break; + default: break; } diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 7f50ff0bad07..e68c6c2e9649 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -73,6 +73,11 @@ static inline struct kvm_vcpu *synic_to_vcpu(struct kvm_vcpu_hv_synic *synic) return hv_vcpu_to_vcpu(container_of(synic, struct kvm_vcpu_hv, synic)); } +static inline struct kvm_hv_syndbg *vcpu_to_hv_syndbg(struct kvm_vcpu *vcpu) +{ + return &vcpu->kvm->arch.hyperv.hv_syndbg; +} + int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host); int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host); diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 54a10c98d746..b66432b015d2 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1541,6 +1541,57 @@ TRACE_EVENT(kvm_nested_vmenter_failed, __print_symbolic(__entry->err, VMX_VMENTER_INSTRUCTION_ERRORS)) ); +/* + * Tracepoint for syndbg_set_msr. + */ +TRACE_EVENT(kvm_hv_syndbg_set_msr, + TP_PROTO(int vcpu_id, u32 vp_index, u32 msr, u64 data), + TP_ARGS(vcpu_id, vp_index, msr, data), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, vp_index) + __field(u32, msr) + __field(u64, data) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->vp_index = vp_index; + __entry->msr = msr; + __entry->data = data; + ), + + TP_printk("vcpu_id %d vp_index %u msr 0x%x data 0x%llx", + __entry->vcpu_id, __entry->vp_index, __entry->msr, + __entry->data) +); + +/* + * Tracepoint for syndbg_get_msr. + */ +TRACE_EVENT(kvm_hv_syndbg_get_msr, + TP_PROTO(int vcpu_id, u32 vp_index, u32 msr, u64 data), + TP_ARGS(vcpu_id, vp_index, msr, data), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, vp_index) + __field(u32, msr) + __field(u64, data) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->vp_index = vp_index; + __entry->msr = msr; + __entry->data = data; + ), + + TP_printk("vcpu_id %d vp_index %u msr 0x%x data 0x%llx", + __entry->vcpu_id, __entry->vp_index, __entry->msr, + __entry->data) +); #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ca8a57312291..9e41b5135340 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1246,6 +1246,10 @@ static const u32 emulated_msrs_all[] = { HV_X64_MSR_VP_ASSIST_PAGE, HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL, HV_X64_MSR_TSC_EMULATION_STATUS, + HV_X64_MSR_SYNDBG_OPTIONS, + HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, + HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, + HV_X64_MSR_SYNDBG_PENDING_BUFFER, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, @@ -3011,6 +3015,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ break; case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: + case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: @@ -3272,6 +3278,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0x20000000; break; case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: + case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index cc04aceb8793..6721eb563eda 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -188,6 +188,7 @@ struct kvm_s390_cmma_log { struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 +#define KVM_EXIT_HYPERV_SYNDBG 3 __u32 type; __u32 pad1; union { @@ -203,6 +204,15 @@ struct kvm_hyperv_exit { __u64 result; __u64 params[2]; } hcall; + struct { + __u32 msr; + __u32 pad2; + __u64 control; + __u64 status; + __u64 send_page; + __u64 recv_page; + __u64 pending_page; + } syndbg; } u; }; -- cgit v1.2.3 From 9eefeabed6f831018c15bd7e17d34967ee34d9dd Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 29 May 2020 21:36:39 +0300 Subject: devlink: Add 'mirror' trap action The action is used by control traps such as IGMP query. The packet is flooded by the device, but also trapped to the CPU in order for the software bridge to mark the receiving port as a multicast router port. Such packets are marked with 'skb->offload_fwd_mark = 1' in order to prevent the software bridge from flooding them again. Signed-off-by: Ido Schimmel Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- Documentation/networking/devlink/devlink-trap.rst | 2 ++ include/uapi/linux/devlink.h | 3 +++ net/core/devlink.c | 3 ++- 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst index 4ca241e70064..5b97327caefc 100644 --- a/Documentation/networking/devlink/devlink-trap.rst +++ b/Documentation/networking/devlink/devlink-trap.rst @@ -108,6 +108,8 @@ The ``devlink-trap`` mechanism supports the following packet trap actions: * ``trap``: The sole copy of the packet is sent to the CPU. * ``drop``: The packet is dropped by the underlying device and a copy is not sent to the CPU. + * ``mirror``: The packet is forwarded by the underlying device and a copy is + sent to the CPU. Generic Packet Traps ==================== diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 1ae90e06c06d..16305932a950 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -233,10 +233,13 @@ enum { * @DEVLINK_TRAP_ACTION_DROP: Packet is dropped by the device and a copy is not * sent to the CPU. * @DEVLINK_TRAP_ACTION_TRAP: The sole copy of the packet is sent to the CPU. + * @DEVLINK_TRAP_ACTION_MIRROR: Packet is forwarded by the device and a copy is + * sent to the CPU. */ enum devlink_trap_action { DEVLINK_TRAP_ACTION_DROP, DEVLINK_TRAP_ACTION_TRAP, + DEVLINK_TRAP_ACTION_MIRROR, }; /** diff --git a/net/core/devlink.c b/net/core/devlink.c index d9fff7083f02..d6298917b077 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -5869,7 +5869,8 @@ devlink_trap_action_get_from_info(struct genl_info *info, val = nla_get_u8(info->attrs[DEVLINK_ATTR_TRAP_ACTION]); switch (val) { case DEVLINK_TRAP_ACTION_DROP: /* fall-through */ - case DEVLINK_TRAP_ACTION_TRAP: + case DEVLINK_TRAP_ACTION_TRAP: /* fall-through */ + case DEVLINK_TRAP_ACTION_MIRROR: *p_trap_action = val; break; default: -- cgit v1.2.3 From 30a4e9a29ab9aadfe6c5386ae4aa396b1d2556c2 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 29 May 2020 21:36:40 +0300 Subject: devlink: Add 'control' trap type This type is used for traps that trap control packets such as ARP request and IGMP query to the CPU. Do not report such packets to the kernel's drop monitor as they were not dropped by the device no encountered an exception during forwarding. Signed-off-by: Ido Schimmel Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- Documentation/networking/devlink/devlink-trap.rst | 8 +++++++- include/uapi/linux/devlink.h | 6 ++++++ net/core/devlink.c | 7 +++++++ 3 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst index 5b97327caefc..6c293cfa23ee 100644 --- a/Documentation/networking/devlink/devlink-trap.rst +++ b/Documentation/networking/devlink/devlink-trap.rst @@ -55,7 +55,7 @@ The following diagram provides a general overview of ``devlink-trap``:: | | +-------^--------+ | - | + | Non-control traps | +----+----+ | | Kernel's Rx path @@ -97,6 +97,12 @@ The ``devlink-trap`` mechanism supports the following packet trap types: processed by ``devlink`` and injected to the kernel's Rx path. Changing the action of such traps is not allowed, as it can easily break the control plane. + * ``control``: Trapped packets were trapped by the device because these are + control packets required for the correct functioning of the control plane. + For example, ARP request and IGMP query packets. Packets are injected to + the kernel's Rx path, but not reported to the kernel's drop monitor. + Changing the action of such traps is not allowed, as it can easily break + the control plane. .. _Trap-Actions: diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 16305932a950..08563e6a424d 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -253,10 +253,16 @@ enum devlink_trap_action { * control plane for resolution. Trapped packets * are processed by devlink and injected to * the kernel's Rx path. + * @DEVLINK_TRAP_TYPE_CONTROL: Packet was trapped because it is required for + * the correct functioning of the control plane. + * For example, an ARP request packet. Trapped + * packets are injected to the kernel's Rx path, + * but not reported to drop monitor. */ enum devlink_trap_type { DEVLINK_TRAP_TYPE_DROP, DEVLINK_TRAP_TYPE_EXCEPTION, + DEVLINK_TRAP_TYPE_CONTROL, }; enum { diff --git a/net/core/devlink.c b/net/core/devlink.c index d6298917b077..47c28e0f848f 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -8847,6 +8847,13 @@ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, devlink_trap_stats_update(trap_item->stats, skb->len); devlink_trap_stats_update(trap_item->group_item->stats, skb->len); + /* Control packets were not dropped by the device or encountered an + * exception during forwarding and therefore should not be reported to + * the kernel's drop monitor. + */ + if (trap_item->trap->type == DEVLINK_TRAP_TYPE_CONTROL) + return; + devlink_trap_report_metadata_fill(&hw_metadata, trap_item, in_devlink_port, fa_cookie); net_dm_hw_report(skb, &hw_metadata); -- cgit v1.2.3 From 7e89ed8ab3f74e0746d3ea80537d7a06b0e27732 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Sat, 30 May 2020 18:09:46 +0000 Subject: bridge: mrp: Update MRP frame type Replace u16/u32 with be16/be32 in the MRP frame types. This fixes sparse warnings like: warning: cast to restricted __be16 Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- include/uapi/linux/mrp_bridge.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mrp_bridge.h b/include/uapi/linux/mrp_bridge.h index 2600cdf5a284..bcad42128d62 100644 --- a/include/uapi/linux/mrp_bridge.h +++ b/include/uapi/linux/mrp_bridge.h @@ -55,30 +55,30 @@ struct br_mrp_end_hdr { }; struct br_mrp_common_hdr { - __u16 seq_id; + __be16 seq_id; __u8 domain[MRP_DOMAIN_UUID_LENGTH]; }; struct br_mrp_ring_test_hdr { - __u16 prio; + __be16 prio; __u8 sa[ETH_ALEN]; - __u16 port_role; - __u16 state; - __u16 transitions; - __u32 timestamp; + __be16 port_role; + __be16 state; + __be16 transitions; + __be32 timestamp; }; struct br_mrp_ring_topo_hdr { - __u16 prio; + __be16 prio; __u8 sa[ETH_ALEN]; - __u16 interval; + __be16 interval; }; struct br_mrp_ring_link_hdr { __u8 sa[ETH_ALEN]; - __u16 port_role; - __u16 interval; - __u16 blocked; + __be16 port_role; + __be16 interval; + __be16 blocked; }; #endif -- cgit v1.2.3 From 4b3a61b030d1131dcf3633a276158a3d0a435a47 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Sat, 30 May 2020 18:09:47 +0000 Subject: bridge: mrp: Set the priority of MRP instance Each MRP instance has a priority, a lower value means a higher priority. The priority of MRP instance is stored in MRP_Test frame in this way all the MRP nodes in the ring can see other nodes priority. Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- include/net/switchdev.h | 1 + include/uapi/linux/if_bridge.h | 2 ++ net/bridge/br_mrp.c | 3 ++- net/bridge/br_mrp_netlink.c | 5 +++++ net/bridge/br_mrp_switchdev.c | 1 + net/bridge/br_private_mrp.h | 1 + 6 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index db519957e134..f82ef4c45f5e 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -116,6 +116,7 @@ struct switchdev_obj_mrp { struct net_device *p_port; struct net_device *s_port; u32 ring_id; + u16 prio; }; #define SWITCHDEV_OBJ_MRP(OBJ) \ diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 5a43eb86c93b..0162c1370ecb 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -176,6 +176,7 @@ enum { IFLA_BRIDGE_MRP_INSTANCE_RING_ID, IFLA_BRIDGE_MRP_INSTANCE_P_IFINDEX, IFLA_BRIDGE_MRP_INSTANCE_S_IFINDEX, + IFLA_BRIDGE_MRP_INSTANCE_PRIO, __IFLA_BRIDGE_MRP_INSTANCE_MAX, }; @@ -230,6 +231,7 @@ struct br_mrp_instance { __u32 ring_id; __u32 p_ifindex; __u32 s_ifindex; + __u16 prio; }; struct br_mrp_ring_state { diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index 8ea59504ef47..f8fd037219fe 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -147,7 +147,7 @@ static struct sk_buff *br_mrp_alloc_test_skb(struct br_mrp *mrp, br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_RING_TEST, sizeof(*hdr)); hdr = skb_put(skb, sizeof(*hdr)); - hdr->prio = cpu_to_be16(MRP_DEFAULT_PRIO); + hdr->prio = cpu_to_be16(mrp->prio); ether_addr_copy(hdr->sa, p->br->dev->dev_addr); hdr->port_role = cpu_to_be16(port_role); hdr->state = cpu_to_be16(mrp->ring_state); @@ -290,6 +290,7 @@ int br_mrp_add(struct net_bridge *br, struct br_mrp_instance *instance) return -ENOMEM; mrp->ring_id = instance->ring_id; + mrp->prio = instance->prio; p = br_mrp_get_port(br, instance->p_ifindex); spin_lock_bh(&br->lock); diff --git a/net/bridge/br_mrp_netlink.c b/net/bridge/br_mrp_netlink.c index d9de780d2ce0..8cb67d9ca44e 100644 --- a/net/bridge/br_mrp_netlink.c +++ b/net/bridge/br_mrp_netlink.c @@ -22,6 +22,7 @@ br_mrp_instance_policy[IFLA_BRIDGE_MRP_INSTANCE_MAX + 1] = { [IFLA_BRIDGE_MRP_INSTANCE_RING_ID] = { .type = NLA_U32 }, [IFLA_BRIDGE_MRP_INSTANCE_P_IFINDEX] = { .type = NLA_U32 }, [IFLA_BRIDGE_MRP_INSTANCE_S_IFINDEX] = { .type = NLA_U32 }, + [IFLA_BRIDGE_MRP_INSTANCE_PRIO] = { .type = NLA_U16 }, }; static int br_mrp_instance_parse(struct net_bridge *br, struct nlattr *attr, @@ -49,6 +50,10 @@ static int br_mrp_instance_parse(struct net_bridge *br, struct nlattr *attr, inst.ring_id = nla_get_u32(tb[IFLA_BRIDGE_MRP_INSTANCE_RING_ID]); inst.p_ifindex = nla_get_u32(tb[IFLA_BRIDGE_MRP_INSTANCE_P_IFINDEX]); inst.s_ifindex = nla_get_u32(tb[IFLA_BRIDGE_MRP_INSTANCE_S_IFINDEX]); + inst.prio = MRP_DEFAULT_PRIO; + + if (tb[IFLA_BRIDGE_MRP_INSTANCE_PRIO]) + inst.prio = nla_get_u16(tb[IFLA_BRIDGE_MRP_INSTANCE_PRIO]); if (cmd == RTM_SETLINK) return br_mrp_add(br, &inst); diff --git a/net/bridge/br_mrp_switchdev.c b/net/bridge/br_mrp_switchdev.c index 51cb1d5a24b4..3a776043bf80 100644 --- a/net/bridge/br_mrp_switchdev.c +++ b/net/bridge/br_mrp_switchdev.c @@ -12,6 +12,7 @@ int br_mrp_switchdev_add(struct net_bridge *br, struct br_mrp *mrp) .p_port = rtnl_dereference(mrp->p_port)->dev, .s_port = rtnl_dereference(mrp->s_port)->dev, .ring_id = mrp->ring_id, + .prio = mrp->prio, }; int err; diff --git a/net/bridge/br_private_mrp.h b/net/bridge/br_private_mrp.h index a0f53cc3ab85..558941ce2366 100644 --- a/net/bridge/br_private_mrp.h +++ b/net/bridge/br_private_mrp.h @@ -14,6 +14,7 @@ struct br_mrp { struct net_bridge_port __rcu *s_port; u32 ring_id; + u16 prio; enum br_mrp_ring_role_type ring_role; u8 ring_role_offloaded; -- cgit v1.2.3 From c6676e7d62cfb5cb7c1c5320a26f3634a11afdb0 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Sat, 30 May 2020 18:09:48 +0000 Subject: bridge: mrp: Add support for role MRA A node that has the MRA role, it can behave as MRM or MRC. Initially it starts as MRM and sends MRP_Test frames on both ring ports. If it detects that there are MRP_Test send by another MRM, then it checks if these frames have a lower priority than itself. In this case it would send MRP_Nack frames to notify the other node that it needs to stop sending MRP_Test frames. If it receives a MRP_Nack frame then it stops sending MRP_Test frames and starts to behave as a MRC but it would continue to monitor the MRP_Test frames send by MRM. If at a point the MRM stops to send MRP_Test frames it would get the MRM role and start to send MRP_Test frames. Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- include/net/switchdev.h | 1 + include/uapi/linux/if_bridge.h | 2 + include/uapi/linux/mrp_bridge.h | 38 ++++++++++++ net/bridge/br_mrp.c | 125 ++++++++++++++++++++++++++++++++++------ net/bridge/br_mrp_netlink.c | 6 ++ net/bridge/br_mrp_switchdev.c | 4 +- net/bridge/br_private_mrp.h | 4 +- 7 files changed, 159 insertions(+), 21 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index f82ef4c45f5e..b8c059b4e06d 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -130,6 +130,7 @@ struct switchdev_obj_ring_test_mrp { u8 max_miss; u32 ring_id; u32 period; + bool monitor; }; #define SWITCHDEV_OBJ_RING_TEST_MRP(OBJ) \ diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 0162c1370ecb..caa6914a3e53 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -222,6 +222,7 @@ enum { IFLA_BRIDGE_MRP_START_TEST_INTERVAL, IFLA_BRIDGE_MRP_START_TEST_MAX_MISS, IFLA_BRIDGE_MRP_START_TEST_PERIOD, + IFLA_BRIDGE_MRP_START_TEST_MONITOR, __IFLA_BRIDGE_MRP_START_TEST_MAX, }; @@ -249,6 +250,7 @@ struct br_mrp_start_test { __u32 interval; __u32 max_miss; __u32 period; + __u32 monitor; }; struct bridge_stp_xstats { diff --git a/include/uapi/linux/mrp_bridge.h b/include/uapi/linux/mrp_bridge.h index bcad42128d62..84f15f48a7cb 100644 --- a/include/uapi/linux/mrp_bridge.h +++ b/include/uapi/linux/mrp_bridge.h @@ -11,11 +11,14 @@ #define MRP_DOMAIN_UUID_LENGTH 16 #define MRP_VERSION 1 #define MRP_FRAME_PRIO 7 +#define MRP_OUI_LENGTH 3 +#define MRP_MANUFACTURE_DATA_LENGTH 2 enum br_mrp_ring_role_type { BR_MRP_RING_ROLE_DISABLED, BR_MRP_RING_ROLE_MRC, BR_MRP_RING_ROLE_MRM, + BR_MRP_RING_ROLE_MRA, }; enum br_mrp_ring_state_type { @@ -43,6 +46,13 @@ enum br_mrp_tlv_header_type { BR_MRP_TLV_HEADER_RING_TOPO = 0x3, BR_MRP_TLV_HEADER_RING_LINK_DOWN = 0x4, BR_MRP_TLV_HEADER_RING_LINK_UP = 0x5, + BR_MRP_TLV_HEADER_OPTION = 0x7f, +}; + +enum br_mrp_sub_tlv_header_type { + BR_MRP_SUB_TLV_HEADER_TEST_MGR_NACK = 0x1, + BR_MRP_SUB_TLV_HEADER_TEST_PROPAGATE = 0x2, + BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR = 0x3, }; struct br_mrp_tlv_hdr { @@ -50,6 +60,11 @@ struct br_mrp_tlv_hdr { __u8 length; }; +struct br_mrp_sub_tlv_hdr { + __u8 type; + __u8 length; +}; + struct br_mrp_end_hdr { struct br_mrp_tlv_hdr hdr; }; @@ -81,4 +96,27 @@ struct br_mrp_ring_link_hdr { __be16 blocked; }; +struct br_mrp_sub_opt_hdr { + __u8 type; + __u8 manufacture_data[MRP_MANUFACTURE_DATA_LENGTH]; +}; + +struct br_mrp_test_mgr_nack_hdr { + __be16 prio; + __u8 sa[ETH_ALEN]; + __be16 other_prio; + __u8 other_sa[ETH_ALEN]; +}; + +struct br_mrp_test_prop_hdr { + __be16 prio; + __u8 sa[ETH_ALEN]; + __be16 other_prio; + __u8 other_sa[ETH_ALEN]; +}; + +struct br_mrp_oui_hdr { + __u8 oui[MRP_OUI_LENGTH]; +}; + #endif diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index f8fd037219fe..24986ec7d38c 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -160,6 +160,16 @@ static struct sk_buff *br_mrp_alloc_test_skb(struct br_mrp *mrp, return skb; } +/* This function is continuously called in the following cases: + * - when node role is MRM, in this case test_monitor is always set to false + * because it needs to notify the userspace that the ring is open and needs to + * send MRP_Test frames + * - when node role is MRA, there are 2 subcases: + * - when MRA behaves as MRM, in this case is similar with MRM role + * - when MRA behaves as MRC, in this case test_monitor is set to true, + * because it needs to detect when it stops seeing MRP_Test frames + * from MRM node but it doesn't need to send MRP_Test frames. + */ static void br_mrp_test_work_expired(struct work_struct *work) { struct delayed_work *del_work = to_delayed_work(work); @@ -177,8 +187,14 @@ static void br_mrp_test_work_expired(struct work_struct *work) /* Notify that the ring is open only if the ring state is * closed, otherwise it would continue to notify at every * interval. + * Also notify that the ring is open when the node has the + * role MRA and behaves as MRC. The reason is that the + * userspace needs to know when the MRM stopped sending + * MRP_Test frames so that the current node to try to take + * the role of a MRM. */ - if (mrp->ring_state == BR_MRP_RING_STATE_CLOSED) + if (mrp->ring_state == BR_MRP_RING_STATE_CLOSED || + mrp->test_monitor) notify_open = true; } @@ -186,12 +202,15 @@ static void br_mrp_test_work_expired(struct work_struct *work) p = rcu_dereference(mrp->p_port); if (p) { - skb = br_mrp_alloc_test_skb(mrp, p, BR_MRP_PORT_ROLE_PRIMARY); - if (!skb) - goto out; - - skb_reset_network_header(skb); - dev_queue_xmit(skb); + if (!mrp->test_monitor) { + skb = br_mrp_alloc_test_skb(mrp, p, + BR_MRP_PORT_ROLE_PRIMARY); + if (!skb) + goto out; + + skb_reset_network_header(skb); + dev_queue_xmit(skb); + } if (notify_open && !mrp->ring_role_offloaded) br_mrp_port_open(p->dev, true); @@ -199,12 +218,15 @@ static void br_mrp_test_work_expired(struct work_struct *work) p = rcu_dereference(mrp->s_port); if (p) { - skb = br_mrp_alloc_test_skb(mrp, p, BR_MRP_PORT_ROLE_SECONDARY); - if (!skb) - goto out; - - skb_reset_network_header(skb); - dev_queue_xmit(skb); + if (!mrp->test_monitor) { + skb = br_mrp_alloc_test_skb(mrp, p, + BR_MRP_PORT_ROLE_SECONDARY); + if (!skb) + goto out; + + skb_reset_network_header(skb); + dev_queue_xmit(skb); + } if (notify_open && !mrp->ring_role_offloaded) br_mrp_port_open(p->dev, true); @@ -227,7 +249,7 @@ static void br_mrp_del_impl(struct net_bridge *br, struct br_mrp *mrp) /* Stop sending MRP_Test frames */ cancel_delayed_work_sync(&mrp->test_work); - br_mrp_switchdev_send_ring_test(br, mrp, 0, 0, 0); + br_mrp_switchdev_send_ring_test(br, mrp, 0, 0, 0, 0); br_mrp_switchdev_del(br, mrp); @@ -452,8 +474,8 @@ int br_mrp_set_ring_role(struct net_bridge *br, return 0; } -/* Start to generate MRP test frames, the frames are generated by HW and if it - * fails, they are generated by the SW. +/* Start to generate or monitor MRP test frames, the frames are generated by + * HW and if it fails, they are generated by the SW. * note: already called with rtnl_lock */ int br_mrp_start_test(struct net_bridge *br, @@ -464,16 +486,18 @@ int br_mrp_start_test(struct net_bridge *br, if (!mrp) return -EINVAL; - /* Try to push it to the HW and if it fails then continue to generate in - * SW and if that also fails then return error + /* Try to push it to the HW and if it fails then continue with SW + * implementation and if that also fails then return error. */ if (!br_mrp_switchdev_send_ring_test(br, mrp, test->interval, - test->max_miss, test->period)) + test->max_miss, test->period, + test->monitor)) return 0; mrp->test_interval = test->interval; mrp->test_end = jiffies + usecs_to_jiffies(test->period); mrp->test_max_miss = test->max_miss; + mrp->test_monitor = test->monitor; mrp->test_count_miss = 0; queue_delayed_work(system_wq, &mrp->test_work, usecs_to_jiffies(test->interval)); @@ -510,6 +534,57 @@ static void br_mrp_mrm_process(struct br_mrp *mrp, struct net_bridge_port *port, br_mrp_port_open(port->dev, false); } +/* Determin if the test hdr has a better priority than the node */ +static bool br_mrp_test_better_than_own(struct br_mrp *mrp, + struct net_bridge *br, + const struct br_mrp_ring_test_hdr *hdr) +{ + u16 prio = be16_to_cpu(hdr->prio); + + if (prio < mrp->prio || + (prio == mrp->prio && + ether_addr_to_u64(hdr->sa) < ether_addr_to_u64(br->dev->dev_addr))) + return true; + + return false; +} + +/* Process only MRP Test frame. All the other MRP frames are processed by + * userspace application + * note: already called with rcu_read_lock + */ +static void br_mrp_mra_process(struct br_mrp *mrp, struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb) +{ + const struct br_mrp_ring_test_hdr *test_hdr; + struct br_mrp_ring_test_hdr _test_hdr; + const struct br_mrp_tlv_hdr *hdr; + struct br_mrp_tlv_hdr _hdr; + + /* Each MRP header starts with a version field which is 16 bits. + * Therefore skip the version and get directly the TLV header. + */ + hdr = skb_header_pointer(skb, sizeof(uint16_t), sizeof(_hdr), &_hdr); + if (!hdr) + return; + + if (hdr->type != BR_MRP_TLV_HEADER_RING_TEST) + return; + + test_hdr = skb_header_pointer(skb, sizeof(uint16_t) + sizeof(_hdr), + sizeof(_test_hdr), &_test_hdr); + if (!test_hdr) + return; + + /* Only frames that have a better priority than the node will + * clear the miss counter because otherwise the node will need to behave + * as MRM. + */ + if (br_mrp_test_better_than_own(mrp, br, test_hdr)) + mrp->test_count_miss = 0; +} + /* This will just forward the frame to the other mrp ring port(MRC role) or will * not do anything. * note: already called with rcu_read_lock @@ -546,6 +621,18 @@ static int br_mrp_rcv(struct net_bridge_port *p, return 1; } + /* If the role is MRA then don't forward the frames if it behaves as + * MRM node + */ + if (mrp->ring_role == BR_MRP_RING_ROLE_MRA) { + if (!mrp->test_monitor) { + br_mrp_mrm_process(mrp, p, skb); + return 1; + } + + br_mrp_mra_process(mrp, br, p, skb); + } + /* Clone the frame and forward it on the other MRP port */ nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) diff --git a/net/bridge/br_mrp_netlink.c b/net/bridge/br_mrp_netlink.c index 8cb67d9ca44e..34b3a8776991 100644 --- a/net/bridge/br_mrp_netlink.c +++ b/net/bridge/br_mrp_netlink.c @@ -196,6 +196,7 @@ br_mrp_start_test_policy[IFLA_BRIDGE_MRP_START_TEST_MAX + 1] = { [IFLA_BRIDGE_MRP_START_TEST_INTERVAL] = { .type = NLA_U32 }, [IFLA_BRIDGE_MRP_START_TEST_MAX_MISS] = { .type = NLA_U32 }, [IFLA_BRIDGE_MRP_START_TEST_PERIOD] = { .type = NLA_U32 }, + [IFLA_BRIDGE_MRP_START_TEST_MONITOR] = { .type = NLA_U32 }, }; static int br_mrp_start_test_parse(struct net_bridge *br, struct nlattr *attr, @@ -225,6 +226,11 @@ static int br_mrp_start_test_parse(struct net_bridge *br, struct nlattr *attr, test.interval = nla_get_u32(tb[IFLA_BRIDGE_MRP_START_TEST_INTERVAL]); test.max_miss = nla_get_u32(tb[IFLA_BRIDGE_MRP_START_TEST_MAX_MISS]); test.period = nla_get_u32(tb[IFLA_BRIDGE_MRP_START_TEST_PERIOD]); + test.monitor = false; + + if (tb[IFLA_BRIDGE_MRP_START_TEST_MONITOR]) + test.monitor = + nla_get_u32(tb[IFLA_BRIDGE_MRP_START_TEST_MONITOR]); return br_mrp_start_test(br, &test); } diff --git a/net/bridge/br_mrp_switchdev.c b/net/bridge/br_mrp_switchdev.c index 3a776043bf80..0da68a0da4b5 100644 --- a/net/bridge/br_mrp_switchdev.c +++ b/net/bridge/br_mrp_switchdev.c @@ -65,7 +65,8 @@ int br_mrp_switchdev_set_ring_role(struct net_bridge *br, int br_mrp_switchdev_send_ring_test(struct net_bridge *br, struct br_mrp *mrp, u32 interval, - u8 max_miss, u32 period) + u8 max_miss, u32 period, + bool monitor) { struct switchdev_obj_ring_test_mrp test = { .obj.orig_dev = br->dev, @@ -74,6 +75,7 @@ int br_mrp_switchdev_send_ring_test(struct net_bridge *br, .max_miss = max_miss, .ring_id = mrp->ring_id, .period = period, + .monitor = monitor, }; int err; diff --git a/net/bridge/br_private_mrp.h b/net/bridge/br_private_mrp.h index 558941ce2366..33b255e38ffe 100644 --- a/net/bridge/br_private_mrp.h +++ b/net/bridge/br_private_mrp.h @@ -26,6 +26,7 @@ struct br_mrp { unsigned long test_end; u32 test_count_miss; u32 test_max_miss; + bool test_monitor; u32 seq_id; @@ -52,7 +53,8 @@ int br_mrp_switchdev_set_ring_role(struct net_bridge *br, struct br_mrp *mrp, int br_mrp_switchdev_set_ring_state(struct net_bridge *br, struct br_mrp *mrp, enum br_mrp_ring_state_type state); int br_mrp_switchdev_send_ring_test(struct net_bridge *br, struct br_mrp *mrp, - u32 interval, u8 max_miss, u32 period); + u32 interval, u8 max_miss, u32 period, + bool monitor); int br_mrp_port_switchdev_set_state(struct net_bridge_port *p, enum br_mrp_port_state_type state); int br_mrp_port_switchdev_set_role(struct net_bridge_port *p, -- cgit v1.2.3 From 13d70f5a5ecff367db2fb18ed4ebe433eab8a74c Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Sun, 24 May 2020 09:51:15 -0700 Subject: bpf, sk_msg: Add get socket storage helpers Add helpers to use local socket storage. Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/159033907577.12355.14740125020572756560.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 2 ++ net/core/filter.c | 15 +++++++++++++++ tools/include/uapi/linux/bpf.h | 2 ++ 3 files changed, 19 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 97e1fd19ff58..54b93f8b49b8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3645,6 +3645,8 @@ struct sk_msg_md { __u32 remote_port; /* Stored in network byte order */ __u32 local_port; /* stored in host byte order */ __u32 size; /* Total size of sk_msg */ + + __bpf_md_ptr(struct bpf_sock *, sk); /* current socket */ }; struct sk_reuseport_md { diff --git a/net/core/filter.c b/net/core/filter.c index c3b496a19748..a6fc23447f12 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6449,6 +6449,10 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_current_pid_tgid: return &bpf_get_current_pid_tgid_proto; + case BPF_FUNC_sk_storage_get: + return &bpf_sk_storage_get_proto; + case BPF_FUNC_sk_storage_delete: + return &bpf_sk_storage_delete_proto; #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; @@ -7273,6 +7277,11 @@ static bool sk_msg_is_valid_access(int off, int size, if (size != sizeof(__u64)) return false; break; + case offsetof(struct sk_msg_md, sk): + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_SOCKET; + break; case bpf_ctx_range(struct sk_msg_md, family): case bpf_ctx_range(struct sk_msg_md, remote_ip4): case bpf_ctx_range(struct sk_msg_md, local_ip4): @@ -8609,6 +8618,12 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, si->dst_reg, si->src_reg, offsetof(struct sk_msg_sg, size)); break; + + case offsetof(struct sk_msg_md, sk): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_msg, sk)); + break; } return insn - insn_buf; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 97e1fd19ff58..54b93f8b49b8 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3645,6 +3645,8 @@ struct sk_msg_md { __u32 remote_port; /* Stored in network byte order */ __u32 local_port; /* stored in host byte order */ __u32 size; /* Total size of sk_msg */ + + __bpf_md_ptr(struct bpf_sock *, sk); /* current socket */ }; struct sk_reuseport_md { -- cgit v1.2.3 From 457f44363a8894135c85b7a9afd2bd8196db24ab Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 29 May 2020 00:54:20 -0700 Subject: bpf: Implement BPF ring buffer and verifier support for it This commit adds a new MPSC ring buffer implementation into BPF ecosystem, which allows multiple CPUs to submit data to a single shared ring buffer. On the consumption side, only single consumer is assumed. Motivation ---------- There are two distinctive motivators for this work, which are not satisfied by existing perf buffer, which prompted creation of a new ring buffer implementation. - more efficient memory utilization by sharing ring buffer across CPUs; - preserving ordering of events that happen sequentially in time, even across multiple CPUs (e.g., fork/exec/exit events for a task). These two problems are independent, but perf buffer fails to satisfy both. Both are a result of a choice to have per-CPU perf ring buffer. Both can be also solved by having an MPSC implementation of ring buffer. The ordering problem could technically be solved for perf buffer with some in-kernel counting, but given the first one requires an MPSC buffer, the same solution would solve the second problem automatically. Semantics and APIs ------------------ Single ring buffer is presented to BPF programs as an instance of BPF map of type BPF_MAP_TYPE_RINGBUF. Two other alternatives considered, but ultimately rejected. One way would be to, similar to BPF_MAP_TYPE_PERF_EVENT_ARRAY, make BPF_MAP_TYPE_RINGBUF could represent an array of ring buffers, but not enforce "same CPU only" rule. This would be more familiar interface compatible with existing perf buffer use in BPF, but would fail if application needed more advanced logic to lookup ring buffer by arbitrary key. HASH_OF_MAPS addresses this with current approach. Additionally, given the performance of BPF ringbuf, many use cases would just opt into a simple single ring buffer shared among all CPUs, for which current approach would be an overkill. Another approach could introduce a new concept, alongside BPF map, to represent generic "container" object, which doesn't necessarily have key/value interface with lookup/update/delete operations. This approach would add a lot of extra infrastructure that has to be built for observability and verifier support. It would also add another concept that BPF developers would have to familiarize themselves with, new syntax in libbpf, etc. But then would really provide no additional benefits over the approach of using a map. BPF_MAP_TYPE_RINGBUF doesn't support lookup/update/delete operations, but so doesn't few other map types (e.g., queue and stack; array doesn't support delete, etc). The approach chosen has an advantage of re-using existing BPF map infrastructure (introspection APIs in kernel, libbpf support, etc), being familiar concept (no need to teach users a new type of object in BPF program), and utilizing existing tooling (bpftool). For common scenario of using a single ring buffer for all CPUs, it's as simple and straightforward, as would be with a dedicated "container" object. On the other hand, by being a map, it can be combined with ARRAY_OF_MAPS and HASH_OF_MAPS map-in-maps to implement a wide variety of topologies, from one ring buffer for each CPU (e.g., as a replacement for perf buffer use cases), to a complicated application hashing/sharding of ring buffers (e.g., having a small pool of ring buffers with hashed task's tgid being a look up key to preserve order, but reduce contention). Key and value sizes are enforced to be zero. max_entries is used to specify the size of ring buffer and has to be a power of 2 value. There are a bunch of similarities between perf buffer (BPF_MAP_TYPE_PERF_EVENT_ARRAY) and new BPF ring buffer semantics: - variable-length records; - if there is no more space left in ring buffer, reservation fails, no blocking; - memory-mappable data area for user-space applications for ease of consumption and high performance; - epoll notifications for new incoming data; - but still the ability to do busy polling for new data to achieve the lowest latency, if necessary. BPF ringbuf provides two sets of APIs to BPF programs: - bpf_ringbuf_output() allows to *copy* data from one place to a ring buffer, similarly to bpf_perf_event_output(); - bpf_ringbuf_reserve()/bpf_ringbuf_commit()/bpf_ringbuf_discard() APIs split the whole process into two steps. First, a fixed amount of space is reserved. If successful, a pointer to a data inside ring buffer data area is returned, which BPF programs can use similarly to a data inside array/hash maps. Once ready, this piece of memory is either committed or discarded. Discard is similar to commit, but makes consumer ignore the record. bpf_ringbuf_output() has disadvantage of incurring extra memory copy, because record has to be prepared in some other place first. But it allows to submit records of the length that's not known to verifier beforehand. It also closely matches bpf_perf_event_output(), so will simplify migration significantly. bpf_ringbuf_reserve() avoids the extra copy of memory by providing a memory pointer directly to ring buffer memory. In a lot of cases records are larger than BPF stack space allows, so many programs have use extra per-CPU array as a temporary heap for preparing sample. bpf_ringbuf_reserve() avoid this needs completely. But in exchange, it only allows a known constant size of memory to be reserved, such that verifier can verify that BPF program can't access memory outside its reserved record space. bpf_ringbuf_output(), while slightly slower due to extra memory copy, covers some use cases that are not suitable for bpf_ringbuf_reserve(). The difference between commit and discard is very small. Discard just marks a record as discarded, and such records are supposed to be ignored by consumer code. Discard is useful for some advanced use-cases, such as ensuring all-or-nothing multi-record submission, or emulating temporary malloc()/free() within single BPF program invocation. Each reserved record is tracked by verifier through existing reference-tracking logic, similar to socket ref-tracking. It is thus impossible to reserve a record, but forget to submit (or discard) it. bpf_ringbuf_query() helper allows to query various properties of ring buffer. Currently 4 are supported: - BPF_RB_AVAIL_DATA returns amount of unconsumed data in ring buffer; - BPF_RB_RING_SIZE returns the size of ring buffer; - BPF_RB_CONS_POS/BPF_RB_PROD_POS returns current logical possition of consumer/producer, respectively. Returned values are momentarily snapshots of ring buffer state and could be off by the time helper returns, so this should be used only for debugging/reporting reasons or for implementing various heuristics, that take into account highly-changeable nature of some of those characteristics. One such heuristic might involve more fine-grained control over poll/epoll notifications about new data availability in ring buffer. Together with BPF_RB_NO_WAKEUP/BPF_RB_FORCE_WAKEUP flags for output/commit/discard helpers, it allows BPF program a high degree of control and, e.g., more efficient batched notifications. Default self-balancing strategy, though, should be adequate for most applications and will work reliable and efficiently already. Design and implementation ------------------------- This reserve/commit schema allows a natural way for multiple producers, either on different CPUs or even on the same CPU/in the same BPF program, to reserve independent records and work with them without blocking other producers. This means that if BPF program was interruped by another BPF program sharing the same ring buffer, they will both get a record reserved (provided there is enough space left) and can work with it and submit it independently. This applies to NMI context as well, except that due to using a spinlock during reservation, in NMI context, bpf_ringbuf_reserve() might fail to get a lock, in which case reservation will fail even if ring buffer is not full. The ring buffer itself internally is implemented as a power-of-2 sized circular buffer, with two logical and ever-increasing counters (which might wrap around on 32-bit architectures, that's not a problem): - consumer counter shows up to which logical position consumer consumed the data; - producer counter denotes amount of data reserved by all producers. Each time a record is reserved, producer that "owns" the record will successfully advance producer counter. At that point, data is still not yet ready to be consumed, though. Each record has 8 byte header, which contains the length of reserved record, as well as two extra bits: busy bit to denote that record is still being worked on, and discard bit, which might be set at commit time if record is discarded. In the latter case, consumer is supposed to skip the record and move on to the next one. Record header also encodes record's relative offset from the beginning of ring buffer data area (in pages). This allows bpf_ringbuf_commit()/bpf_ringbuf_discard() to accept only the pointer to the record itself, without requiring also the pointer to ring buffer itself. Ring buffer memory location will be restored from record metadata header. This significantly simplifies verifier, as well as improving API usability. Producer counter increments are serialized under spinlock, so there is a strict ordering between reservations. Commits, on the other hand, are completely lockless and independent. All records become available to consumer in the order of reservations, but only after all previous records where already committed. It is thus possible for slow producers to temporarily hold off submitted records, that were reserved later. Reservation/commit/consumer protocol is verified by litmus tests in Documentation/litmus-test/bpf-rb. One interesting implementation bit, that significantly simplifies (and thus speeds up as well) implementation of both producers and consumers is how data area is mapped twice contiguously back-to-back in the virtual memory. This allows to not take any special measures for samples that have to wrap around at the end of the circular buffer data area, because the next page after the last data page would be first data page again, and thus the sample will still appear completely contiguous in virtual memory. See comment and a simple ASCII diagram showing this visually in bpf_ringbuf_area_alloc(). Another feature that distinguishes BPF ringbuf from perf ring buffer is a self-pacing notifications of new data being availability. bpf_ringbuf_commit() implementation will send a notification of new record being available after commit only if consumer has already caught up right up to the record being committed. If not, consumer still has to catch up and thus will see new data anyways without needing an extra poll notification. Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c) show that this allows to achieve a very high throughput without having to resort to tricks like "notify only every Nth sample", which are necessary with perf buffer. For extreme cases, when BPF program wants more manual control of notifications, commit/discard/output helpers accept BPF_RB_NO_WAKEUP and BPF_RB_FORCE_WAKEUP flags, which give full control over notifications of data availability, but require extra caution and diligence in using this API. Comparison to alternatives -------------------------- Before considering implementing BPF ring buffer from scratch existing alternatives in kernel were evaluated, but didn't seem to meet the needs. They largely fell into few categores: - per-CPU buffers (perf, ftrace, etc), which don't satisfy two motivations outlined above (ordering and memory consumption); - linked list-based implementations; while some were multi-producer designs, consuming these from user-space would be very complicated and most probably not performant; memory-mapping contiguous piece of memory is simpler and more performant for user-space consumers; - io_uring is SPSC, but also requires fixed-sized elements. Naively turning SPSC queue into MPSC w/ lock would have subpar performance compared to locked reserve + lockless commit, as with BPF ring buffer. Fixed sized elements would be too limiting for BPF programs, given existing BPF programs heavily rely on variable-sized perf buffer already; - specialized implementations (like a new printk ring buffer, [0]) with lots of printk-specific limitations and implications, that didn't seem to fit well for intended use with BPF programs. [0] https://lwn.net/Articles/779550/ Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200529075424.3139988-2-andriin@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 13 + include/linux/bpf_types.h | 1 + include/linux/bpf_verifier.h | 4 + include/uapi/linux/bpf.h | 84 +++- kernel/bpf/Makefile | 2 +- kernel/bpf/helpers.c | 10 + kernel/bpf/ringbuf.c | 501 +++++++++++++++++++++ kernel/bpf/syscall.c | 12 + kernel/bpf/verifier.c | 195 ++++++-- kernel/trace/bpf_trace.c | 10 + tools/include/uapi/linux/bpf.h | 84 +++- tools/testing/selftests/bpf/verifier/and.c | 4 +- .../testing/selftests/bpf/verifier/array_access.c | 4 +- tools/testing/selftests/bpf/verifier/bounds.c | 6 +- tools/testing/selftests/bpf/verifier/calls.c | 2 +- .../selftests/bpf/verifier/direct_value_access.c | 4 +- .../selftests/bpf/verifier/helper_access_var_len.c | 2 +- .../selftests/bpf/verifier/helper_value_access.c | 6 +- .../selftests/bpf/verifier/value_ptr_arith.c | 8 +- 19 files changed, 882 insertions(+), 70 deletions(-) create mode 100644 kernel/bpf/ringbuf.c (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index efe8836b5c48..e5884f7f801c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -90,6 +90,8 @@ struct bpf_map_ops { int (*map_direct_value_meta)(const struct bpf_map *map, u64 imm, u32 *off); int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); + __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, + struct poll_table_struct *pts); }; struct bpf_map_memory { @@ -244,6 +246,9 @@ enum bpf_arg_type { ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ + ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */ + ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */ + ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ }; /* type of values returned from helper functions */ @@ -255,6 +260,7 @@ enum bpf_return_type { RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */ RET_PTR_TO_TCP_SOCK_OR_NULL, /* returns a pointer to a tcp_sock or NULL */ RET_PTR_TO_SOCK_COMMON_OR_NULL, /* returns a pointer to a sock_common or NULL */ + RET_PTR_TO_ALLOC_MEM_OR_NULL, /* returns a pointer to dynamically allocated memory or NULL */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs @@ -322,6 +328,8 @@ enum bpf_reg_type { PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ PTR_TO_BTF_ID, /* reg points to kernel struct */ PTR_TO_BTF_ID_OR_NULL, /* reg points to kernel struct or NULL */ + PTR_TO_MEM, /* reg points to valid memory region */ + PTR_TO_MEM_OR_NULL, /* reg points to valid memory region or NULL */ }; /* The information passed from prog-specific *_is_valid_access @@ -1611,6 +1619,11 @@ extern const struct bpf_func_proto bpf_tcp_sock_proto; extern const struct bpf_func_proto bpf_jiffies64_proto; extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_event_output_data_proto; +extern const struct bpf_func_proto bpf_ringbuf_output_proto; +extern const struct bpf_func_proto bpf_ringbuf_reserve_proto; +extern const struct bpf_func_proto bpf_ringbuf_submit_proto; +extern const struct bpf_func_proto bpf_ringbuf_discard_proto; +extern const struct bpf_func_proto bpf_ringbuf_query_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 29d22752fc87..fa8e1b552acd 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -118,6 +118,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) #if defined(CONFIG_BPF_JIT) BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops) #endif +BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops) BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index ea833087e853..ca08db4ffb5f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -54,6 +54,8 @@ struct bpf_reg_state { u32 btf_id; /* for PTR_TO_BTF_ID */ + u32 mem_size; /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */ + /* Max size from any of the above. */ unsigned long raw; }; @@ -63,6 +65,8 @@ struct bpf_reg_state { * offset, so they can share range knowledge. * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we * came from, when one is tested for != NULL. + * For PTR_TO_MEM_OR_NULL this is used to identify memory allocation + * for the purpose of tracking that it's freed. * For PTR_TO_SOCKET this is used to share which pointers retain the * same reference to the socket, to determine proper reference freeing. */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 54b93f8b49b8..974ca6e948e3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -147,6 +147,7 @@ enum bpf_map_type { BPF_MAP_TYPE_SK_STORAGE, BPF_MAP_TYPE_DEVMAP_HASH, BPF_MAP_TYPE_STRUCT_OPS, + BPF_MAP_TYPE_RINGBUF, }; /* Note that tracing related programs such as @@ -3157,6 +3158,59 @@ union bpf_attr { * **bpf_sk_cgroup_id**\ (). * Return * The id is returned or 0 in case the id could not be retrieved. + * + * void *bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) + * Description + * Copy *size* bytes from *data* into a ring buffer *ringbuf*. + * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of + * new data availability is sent. + * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of + * new data availability is sent unconditionally. + * Return + * 0, on success; + * < 0, on error. + * + * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags) + * Description + * Reserve *size* bytes of payload in a ring buffer *ringbuf*. + * Return + * Valid pointer with *size* bytes of memory available; NULL, + * otherwise. + * + * void bpf_ringbuf_submit(void *data, u64 flags) + * Description + * Submit reserved ring buffer sample, pointed to by *data*. + * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of + * new data availability is sent. + * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of + * new data availability is sent unconditionally. + * Return + * Nothing. Always succeeds. + * + * void bpf_ringbuf_discard(void *data, u64 flags) + * Description + * Discard reserved ring buffer sample, pointed to by *data*. + * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of + * new data availability is sent. + * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of + * new data availability is sent unconditionally. + * Return + * Nothing. Always succeeds. + * + * u64 bpf_ringbuf_query(void *ringbuf, u64 flags) + * Description + * Query various characteristics of provided ring buffer. What + * exactly is queries is determined by *flags*: + * - BPF_RB_AVAIL_DATA - amount of data not yet consumed; + * - BPF_RB_RING_SIZE - the size of ring buffer; + * - BPF_RB_CONS_POS - consumer position (can wrap around); + * - BPF_RB_PROD_POS - producer(s) position (can wrap around); + * Data returned is just a momentary snapshots of actual values + * and could be inaccurate, so this facility should be used to + * power heuristics and for reporting, not to make 100% correct + * calculation. + * Return + * Requested value, or 0, if flags are not recognized. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3288,7 +3342,12 @@ union bpf_attr { FN(seq_printf), \ FN(seq_write), \ FN(sk_cgroup_id), \ - FN(sk_ancestor_cgroup_id), + FN(sk_ancestor_cgroup_id), \ + FN(ringbuf_output), \ + FN(ringbuf_reserve), \ + FN(ringbuf_submit), \ + FN(ringbuf_discard), \ + FN(ringbuf_query), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3398,6 +3457,29 @@ enum { BPF_F_GET_BRANCH_RECORDS_SIZE = (1ULL << 0), }; +/* BPF_FUNC_bpf_ringbuf_commit, BPF_FUNC_bpf_ringbuf_discard, and + * BPF_FUNC_bpf_ringbuf_output flags. + */ +enum { + BPF_RB_NO_WAKEUP = (1ULL << 0), + BPF_RB_FORCE_WAKEUP = (1ULL << 1), +}; + +/* BPF_FUNC_bpf_ringbuf_query flags */ +enum { + BPF_RB_AVAIL_DATA = 0, + BPF_RB_RING_SIZE = 1, + BPF_RB_CONS_POS = 2, + BPF_RB_PROD_POS = 3, +}; + +/* BPF ring buffer constants */ +enum { + BPF_RINGBUF_BUSY_BIT = (1U << 31), + BPF_RINGBUF_DISCARD_BIT = (1U << 30), + BPF_RINGBUF_HDR_SZ = 8, +}; + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 375b933010dd..8fca02f64811 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -4,7 +4,7 @@ CFLAGS_core.o += $(call cc-disable-warning, override-init) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o -obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o +obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o obj-$(CONFIG_BPF_JIT) += trampoline.o obj-$(CONFIG_BPF_SYSCALL) += btf.o diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index bb4fb634275e..be43ab3e619f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -635,6 +635,16 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; + case BPF_FUNC_ringbuf_output: + return &bpf_ringbuf_output_proto; + case BPF_FUNC_ringbuf_reserve: + return &bpf_ringbuf_reserve_proto; + case BPF_FUNC_ringbuf_submit: + return &bpf_ringbuf_submit_proto; + case BPF_FUNC_ringbuf_discard: + return &bpf_ringbuf_discard_proto; + case BPF_FUNC_ringbuf_query: + return &bpf_ringbuf_query_proto; default: break; } diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c new file mode 100644 index 000000000000..180414bb0d3e --- /dev/null +++ b/kernel/bpf/ringbuf.c @@ -0,0 +1,501 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE) + +/* non-mmap()'able part of bpf_ringbuf (everything up to consumer page) */ +#define RINGBUF_PGOFF \ + (offsetof(struct bpf_ringbuf, consumer_pos) >> PAGE_SHIFT) +/* consumer page and producer page */ +#define RINGBUF_POS_PAGES 2 + +#define RINGBUF_MAX_RECORD_SZ (UINT_MAX/4) + +/* Maximum size of ring buffer area is limited by 32-bit page offset within + * record header, counted in pages. Reserve 8 bits for extensibility, and take + * into account few extra pages for consumer/producer pages and + * non-mmap()'able parts. This gives 64GB limit, which seems plenty for single + * ring buffer. + */ +#define RINGBUF_MAX_DATA_SZ \ + (((1ULL << 24) - RINGBUF_POS_PAGES - RINGBUF_PGOFF) * PAGE_SIZE) + +struct bpf_ringbuf { + wait_queue_head_t waitq; + struct irq_work work; + u64 mask; + struct page **pages; + int nr_pages; + spinlock_t spinlock ____cacheline_aligned_in_smp; + /* Consumer and producer counters are put into separate pages to allow + * mapping consumer page as r/w, but restrict producer page to r/o. + * This protects producer position from being modified by user-space + * application and ruining in-kernel position tracking. + */ + unsigned long consumer_pos __aligned(PAGE_SIZE); + unsigned long producer_pos __aligned(PAGE_SIZE); + char data[] __aligned(PAGE_SIZE); +}; + +struct bpf_ringbuf_map { + struct bpf_map map; + struct bpf_map_memory memory; + struct bpf_ringbuf *rb; +}; + +/* 8-byte ring buffer record header structure */ +struct bpf_ringbuf_hdr { + u32 len; + u32 pg_off; +}; + +static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) +{ + const gfp_t flags = GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN | + __GFP_ZERO; + int nr_meta_pages = RINGBUF_PGOFF + RINGBUF_POS_PAGES; + int nr_data_pages = data_sz >> PAGE_SHIFT; + int nr_pages = nr_meta_pages + nr_data_pages; + struct page **pages, *page; + struct bpf_ringbuf *rb; + size_t array_size; + int i; + + /* Each data page is mapped twice to allow "virtual" + * continuous read of samples wrapping around the end of ring + * buffer area: + * ------------------------------------------------------ + * | meta pages | real data pages | same data pages | + * ------------------------------------------------------ + * | | 1 2 3 4 5 6 7 8 9 | 1 2 3 4 5 6 7 8 9 | + * ------------------------------------------------------ + * | | TA DA | TA DA | + * ------------------------------------------------------ + * ^^^^^^^ + * | + * Here, no need to worry about special handling of wrapped-around + * data due to double-mapped data pages. This works both in kernel and + * when mmap()'ed in user-space, simplifying both kernel and + * user-space implementations significantly. + */ + array_size = (nr_meta_pages + 2 * nr_data_pages) * sizeof(*pages); + if (array_size > PAGE_SIZE) + pages = vmalloc_node(array_size, numa_node); + else + pages = kmalloc_node(array_size, flags, numa_node); + if (!pages) + return NULL; + + for (i = 0; i < nr_pages; i++) { + page = alloc_pages_node(numa_node, flags, 0); + if (!page) { + nr_pages = i; + goto err_free_pages; + } + pages[i] = page; + if (i >= nr_meta_pages) + pages[nr_data_pages + i] = page; + } + + rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages, + VM_ALLOC | VM_USERMAP, PAGE_KERNEL); + if (rb) { + rb->pages = pages; + rb->nr_pages = nr_pages; + return rb; + } + +err_free_pages: + for (i = 0; i < nr_pages; i++) + __free_page(pages[i]); + kvfree(pages); + return NULL; +} + +static void bpf_ringbuf_notify(struct irq_work *work) +{ + struct bpf_ringbuf *rb = container_of(work, struct bpf_ringbuf, work); + + wake_up_all(&rb->waitq); +} + +static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) +{ + struct bpf_ringbuf *rb; + + if (!data_sz || !PAGE_ALIGNED(data_sz)) + return ERR_PTR(-EINVAL); + +#ifdef CONFIG_64BIT + /* on 32-bit arch, it's impossible to overflow record's hdr->pgoff */ + if (data_sz > RINGBUF_MAX_DATA_SZ) + return ERR_PTR(-E2BIG); +#endif + + rb = bpf_ringbuf_area_alloc(data_sz, numa_node); + if (!rb) + return ERR_PTR(-ENOMEM); + + spin_lock_init(&rb->spinlock); + init_waitqueue_head(&rb->waitq); + init_irq_work(&rb->work, bpf_ringbuf_notify); + + rb->mask = data_sz - 1; + rb->consumer_pos = 0; + rb->producer_pos = 0; + + return rb; +} + +static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) +{ + struct bpf_ringbuf_map *rb_map; + u64 cost; + int err; + + if (attr->map_flags & ~RINGBUF_CREATE_FLAG_MASK) + return ERR_PTR(-EINVAL); + + if (attr->key_size || attr->value_size || + attr->max_entries == 0 || !PAGE_ALIGNED(attr->max_entries)) + return ERR_PTR(-EINVAL); + + rb_map = kzalloc(sizeof(*rb_map), GFP_USER); + if (!rb_map) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&rb_map->map, attr); + + cost = sizeof(struct bpf_ringbuf_map) + + sizeof(struct bpf_ringbuf) + + attr->max_entries; + err = bpf_map_charge_init(&rb_map->map.memory, cost); + if (err) + goto err_free_map; + + rb_map->rb = bpf_ringbuf_alloc(attr->max_entries, rb_map->map.numa_node); + if (IS_ERR(rb_map->rb)) { + err = PTR_ERR(rb_map->rb); + goto err_uncharge; + } + + return &rb_map->map; + +err_uncharge: + bpf_map_charge_finish(&rb_map->map.memory); +err_free_map: + kfree(rb_map); + return ERR_PTR(err); +} + +static void bpf_ringbuf_free(struct bpf_ringbuf *rb) +{ + /* copy pages pointer and nr_pages to local variable, as we are going + * to unmap rb itself with vunmap() below + */ + struct page **pages = rb->pages; + int i, nr_pages = rb->nr_pages; + + vunmap(rb); + for (i = 0; i < nr_pages; i++) + __free_page(pages[i]); + kvfree(pages); +} + +static void ringbuf_map_free(struct bpf_map *map) +{ + struct bpf_ringbuf_map *rb_map; + + /* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, + * so the programs (can be more than one that used this map) were + * disconnected from events. Wait for outstanding critical sections in + * these programs to complete + */ + synchronize_rcu(); + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + bpf_ringbuf_free(rb_map->rb); + kfree(rb_map); +} + +static void *ringbuf_map_lookup_elem(struct bpf_map *map, void *key) +{ + return ERR_PTR(-ENOTSUPP); +} + +static int ringbuf_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 flags) +{ + return -ENOTSUPP; +} + +static int ringbuf_map_delete_elem(struct bpf_map *map, void *key) +{ + return -ENOTSUPP; +} + +static int ringbuf_map_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + return -ENOTSUPP; +} + +static size_t bpf_ringbuf_mmap_page_cnt(const struct bpf_ringbuf *rb) +{ + size_t data_pages = (rb->mask + 1) >> PAGE_SHIFT; + + /* consumer page + producer page + 2 x data pages */ + return RINGBUF_POS_PAGES + 2 * data_pages; +} + +static int ringbuf_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) +{ + struct bpf_ringbuf_map *rb_map; + size_t mmap_sz; + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + mmap_sz = bpf_ringbuf_mmap_page_cnt(rb_map->rb) << PAGE_SHIFT; + + if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) > mmap_sz) + return -EINVAL; + + return remap_vmalloc_range(vma, rb_map->rb, + vma->vm_pgoff + RINGBUF_PGOFF); +} + +static unsigned long ringbuf_avail_data_sz(struct bpf_ringbuf *rb) +{ + unsigned long cons_pos, prod_pos; + + cons_pos = smp_load_acquire(&rb->consumer_pos); + prod_pos = smp_load_acquire(&rb->producer_pos); + return prod_pos - cons_pos; +} + +static __poll_t ringbuf_map_poll(struct bpf_map *map, struct file *filp, + struct poll_table_struct *pts) +{ + struct bpf_ringbuf_map *rb_map; + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + poll_wait(filp, &rb_map->rb->waitq, pts); + + if (ringbuf_avail_data_sz(rb_map->rb)) + return EPOLLIN | EPOLLRDNORM; + return 0; +} + +const struct bpf_map_ops ringbuf_map_ops = { + .map_alloc = ringbuf_map_alloc, + .map_free = ringbuf_map_free, + .map_mmap = ringbuf_map_mmap, + .map_poll = ringbuf_map_poll, + .map_lookup_elem = ringbuf_map_lookup_elem, + .map_update_elem = ringbuf_map_update_elem, + .map_delete_elem = ringbuf_map_delete_elem, + .map_get_next_key = ringbuf_map_get_next_key, +}; + +/* Given pointer to ring buffer record metadata and struct bpf_ringbuf itself, + * calculate offset from record metadata to ring buffer in pages, rounded + * down. This page offset is stored as part of record metadata and allows to + * restore struct bpf_ringbuf * from record pointer. This page offset is + * stored at offset 4 of record metadata header. + */ +static size_t bpf_ringbuf_rec_pg_off(struct bpf_ringbuf *rb, + struct bpf_ringbuf_hdr *hdr) +{ + return ((void *)hdr - (void *)rb) >> PAGE_SHIFT; +} + +/* Given pointer to ring buffer record header, restore pointer to struct + * bpf_ringbuf itself by using page offset stored at offset 4 + */ +static struct bpf_ringbuf * +bpf_ringbuf_restore_from_rec(struct bpf_ringbuf_hdr *hdr) +{ + unsigned long addr = (unsigned long)(void *)hdr; + unsigned long off = (unsigned long)hdr->pg_off << PAGE_SHIFT; + + return (void*)((addr & PAGE_MASK) - off); +} + +static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) +{ + unsigned long cons_pos, prod_pos, new_prod_pos, flags; + u32 len, pg_off; + struct bpf_ringbuf_hdr *hdr; + + if (unlikely(size > RINGBUF_MAX_RECORD_SZ)) + return NULL; + + len = round_up(size + BPF_RINGBUF_HDR_SZ, 8); + cons_pos = smp_load_acquire(&rb->consumer_pos); + + if (in_nmi()) { + if (!spin_trylock_irqsave(&rb->spinlock, flags)) + return NULL; + } else { + spin_lock_irqsave(&rb->spinlock, flags); + } + + prod_pos = rb->producer_pos; + new_prod_pos = prod_pos + len; + + /* check for out of ringbuf space by ensuring producer position + * doesn't advance more than (ringbuf_size - 1) ahead + */ + if (new_prod_pos - cons_pos > rb->mask) { + spin_unlock_irqrestore(&rb->spinlock, flags); + return NULL; + } + + hdr = (void *)rb->data + (prod_pos & rb->mask); + pg_off = bpf_ringbuf_rec_pg_off(rb, hdr); + hdr->len = size | BPF_RINGBUF_BUSY_BIT; + hdr->pg_off = pg_off; + + /* pairs with consumer's smp_load_acquire() */ + smp_store_release(&rb->producer_pos, new_prod_pos); + + spin_unlock_irqrestore(&rb->spinlock, flags); + + return (void *)hdr + BPF_RINGBUF_HDR_SZ; +} + +BPF_CALL_3(bpf_ringbuf_reserve, struct bpf_map *, map, u64, size, u64, flags) +{ + struct bpf_ringbuf_map *rb_map; + + if (unlikely(flags)) + return 0; + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + return (unsigned long)__bpf_ringbuf_reserve(rb_map->rb, size); +} + +const struct bpf_func_proto bpf_ringbuf_reserve_proto = { + .func = bpf_ringbuf_reserve, + .ret_type = RET_PTR_TO_ALLOC_MEM_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_CONST_ALLOC_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, +}; + +static void bpf_ringbuf_commit(void *sample, u64 flags, bool discard) +{ + unsigned long rec_pos, cons_pos; + struct bpf_ringbuf_hdr *hdr; + struct bpf_ringbuf *rb; + u32 new_len; + + hdr = sample - BPF_RINGBUF_HDR_SZ; + rb = bpf_ringbuf_restore_from_rec(hdr); + new_len = hdr->len ^ BPF_RINGBUF_BUSY_BIT; + if (discard) + new_len |= BPF_RINGBUF_DISCARD_BIT; + + /* update record header with correct final size prefix */ + xchg(&hdr->len, new_len); + + /* if consumer caught up and is waiting for our record, notify about + * new data availability + */ + rec_pos = (void *)hdr - (void *)rb->data; + cons_pos = smp_load_acquire(&rb->consumer_pos) & rb->mask; + + if (flags & BPF_RB_FORCE_WAKEUP) + irq_work_queue(&rb->work); + else if (cons_pos == rec_pos && !(flags & BPF_RB_NO_WAKEUP)) + irq_work_queue(&rb->work); +} + +BPF_CALL_2(bpf_ringbuf_submit, void *, sample, u64, flags) +{ + bpf_ringbuf_commit(sample, flags, false /* discard */); + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_submit_proto = { + .func = bpf_ringbuf_submit, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_ALLOC_MEM, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_ringbuf_discard, void *, sample, u64, flags) +{ + bpf_ringbuf_commit(sample, flags, true /* discard */); + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_discard_proto = { + .func = bpf_ringbuf_discard, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_ALLOC_MEM, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_ringbuf_output, struct bpf_map *, map, void *, data, u64, size, + u64, flags) +{ + struct bpf_ringbuf_map *rb_map; + void *rec; + + if (unlikely(flags & ~(BPF_RB_NO_WAKEUP | BPF_RB_FORCE_WAKEUP))) + return -EINVAL; + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + rec = __bpf_ringbuf_reserve(rb_map->rb, size); + if (!rec) + return -EAGAIN; + + memcpy(rec, data, size); + bpf_ringbuf_commit(rec, flags, false /* discard */); + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_output_proto = { + .func = bpf_ringbuf_output, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_ringbuf_query, struct bpf_map *, map, u64, flags) +{ + struct bpf_ringbuf *rb; + + rb = container_of(map, struct bpf_ringbuf_map, map)->rb; + + switch (flags) { + case BPF_RB_AVAIL_DATA: + return ringbuf_avail_data_sz(rb); + case BPF_RB_RING_SIZE: + return rb->mask + 1; + case BPF_RB_CONS_POS: + return smp_load_acquire(&rb->consumer_pos); + case BPF_RB_PROD_POS: + return smp_load_acquire(&rb->producer_pos); + default: + return 0; + } +} + +const struct bpf_func_proto bpf_ringbuf_query_proto = { + .func = bpf_ringbuf_query, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 2c969a9b90d3..9de3540fa90c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -26,6 +26,7 @@ #include #include #include +#include #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ @@ -662,6 +663,16 @@ out: return err; } +static __poll_t bpf_map_poll(struct file *filp, struct poll_table_struct *pts) +{ + struct bpf_map *map = filp->private_data; + + if (map->ops->map_poll) + return map->ops->map_poll(map, filp, pts); + + return EPOLLERR; +} + const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, @@ -670,6 +681,7 @@ const struct file_operations bpf_map_fops = { .read = bpf_dummy_read, .write = bpf_dummy_write, .mmap = bpf_map_mmap, + .poll = bpf_map_poll, }; int bpf_map_new_fd(struct bpf_map *map, int flags) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6d725a26f66e..5c7bbaac81ef 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -233,6 +233,7 @@ struct bpf_call_arg_meta { bool pkt_access; int regno; int access_size; + int mem_size; u64 msize_max_value; int ref_obj_id; int func_id; @@ -408,7 +409,8 @@ static bool reg_type_may_be_null(enum bpf_reg_type type) type == PTR_TO_SOCKET_OR_NULL || type == PTR_TO_SOCK_COMMON_OR_NULL || type == PTR_TO_TCP_SOCK_OR_NULL || - type == PTR_TO_BTF_ID_OR_NULL; + type == PTR_TO_BTF_ID_OR_NULL || + type == PTR_TO_MEM_OR_NULL; } static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) @@ -422,7 +424,9 @@ static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type) return type == PTR_TO_SOCKET || type == PTR_TO_SOCKET_OR_NULL || type == PTR_TO_TCP_SOCK || - type == PTR_TO_TCP_SOCK_OR_NULL; + type == PTR_TO_TCP_SOCK_OR_NULL || + type == PTR_TO_MEM || + type == PTR_TO_MEM_OR_NULL; } static bool arg_type_may_be_refcounted(enum bpf_arg_type type) @@ -436,7 +440,9 @@ static bool arg_type_may_be_refcounted(enum bpf_arg_type type) */ static bool is_release_function(enum bpf_func_id func_id) { - return func_id == BPF_FUNC_sk_release; + return func_id == BPF_FUNC_sk_release || + func_id == BPF_FUNC_ringbuf_submit || + func_id == BPF_FUNC_ringbuf_discard; } static bool may_be_acquire_function(enum bpf_func_id func_id) @@ -444,7 +450,8 @@ static bool may_be_acquire_function(enum bpf_func_id func_id) return func_id == BPF_FUNC_sk_lookup_tcp || func_id == BPF_FUNC_sk_lookup_udp || func_id == BPF_FUNC_skc_lookup_tcp || - func_id == BPF_FUNC_map_lookup_elem; + func_id == BPF_FUNC_map_lookup_elem || + func_id == BPF_FUNC_ringbuf_reserve; } static bool is_acquire_function(enum bpf_func_id func_id, @@ -454,7 +461,8 @@ static bool is_acquire_function(enum bpf_func_id func_id, if (func_id == BPF_FUNC_sk_lookup_tcp || func_id == BPF_FUNC_sk_lookup_udp || - func_id == BPF_FUNC_skc_lookup_tcp) + func_id == BPF_FUNC_skc_lookup_tcp || + func_id == BPF_FUNC_ringbuf_reserve) return true; if (func_id == BPF_FUNC_map_lookup_elem && @@ -494,6 +502,8 @@ static const char * const reg_type_str[] = { [PTR_TO_XDP_SOCK] = "xdp_sock", [PTR_TO_BTF_ID] = "ptr_", [PTR_TO_BTF_ID_OR_NULL] = "ptr_or_null_", + [PTR_TO_MEM] = "mem", + [PTR_TO_MEM_OR_NULL] = "mem_or_null", }; static char slot_type_char[] = { @@ -2468,32 +2478,49 @@ static int check_map_access_type(struct bpf_verifier_env *env, u32 regno, return 0; } -/* check read/write into map element returned by bpf_map_lookup_elem() */ -static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off, - int size, bool zero_size_allowed) +/* check read/write into memory region (e.g., map value, ringbuf sample, etc) */ +static int __check_mem_access(struct bpf_verifier_env *env, int regno, + int off, int size, u32 mem_size, + bool zero_size_allowed) { - struct bpf_reg_state *regs = cur_regs(env); - struct bpf_map *map = regs[regno].map_ptr; + bool size_ok = size > 0 || (size == 0 && zero_size_allowed); + struct bpf_reg_state *reg; + + if (off >= 0 && size_ok && (u64)off + size <= mem_size) + return 0; - if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) || - off + size > map->value_size) { + reg = &cur_regs(env)[regno]; + switch (reg->type) { + case PTR_TO_MAP_VALUE: verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n", - map->value_size, off, size); - return -EACCES; + mem_size, off, size); + break; + case PTR_TO_PACKET: + case PTR_TO_PACKET_META: + case PTR_TO_PACKET_END: + verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n", + off, size, regno, reg->id, off, mem_size); + break; + case PTR_TO_MEM: + default: + verbose(env, "invalid access to memory, mem_size=%u off=%d size=%d\n", + mem_size, off, size); } - return 0; + + return -EACCES; } -/* check read/write into a map element with possible variable offset */ -static int check_map_access(struct bpf_verifier_env *env, u32 regno, - int off, int size, bool zero_size_allowed) +/* check read/write into a memory region with possible variable offset */ +static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno, + int off, int size, u32 mem_size, + bool zero_size_allowed) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regno]; int err; - /* We may have adjusted the register to this map value, so we + /* We may have adjusted the register pointing to memory region, so we * need to try adding each of min_value and max_value to off * to make sure our theoretical access will be safe. */ @@ -2514,10 +2541,10 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, regno); return -EACCES; } - err = __check_map_access(env, regno, reg->smin_value + off, size, - zero_size_allowed); + err = __check_mem_access(env, regno, reg->smin_value + off, size, + mem_size, zero_size_allowed); if (err) { - verbose(env, "R%d min value is outside of the array range\n", + verbose(env, "R%d min value is outside of the allowed memory range\n", regno); return err; } @@ -2527,18 +2554,38 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, * If reg->umax_value + off could overflow, treat that as unbounded too. */ if (reg->umax_value >= BPF_MAX_VAR_OFF) { - verbose(env, "R%d unbounded memory access, make sure to bounds check any array access into a map\n", + verbose(env, "R%d unbounded memory access, make sure to bounds check any such access\n", regno); return -EACCES; } - err = __check_map_access(env, regno, reg->umax_value + off, size, - zero_size_allowed); - if (err) - verbose(env, "R%d max value is outside of the array range\n", + err = __check_mem_access(env, regno, reg->umax_value + off, size, + mem_size, zero_size_allowed); + if (err) { + verbose(env, "R%d max value is outside of the allowed memory range\n", regno); + return err; + } + + return 0; +} - if (map_value_has_spin_lock(reg->map_ptr)) { - u32 lock = reg->map_ptr->spin_lock_off; +/* check read/write into a map element with possible variable offset */ +static int check_map_access(struct bpf_verifier_env *env, u32 regno, + int off, int size, bool zero_size_allowed) +{ + struct bpf_verifier_state *vstate = env->cur_state; + struct bpf_func_state *state = vstate->frame[vstate->curframe]; + struct bpf_reg_state *reg = &state->regs[regno]; + struct bpf_map *map = reg->map_ptr; + int err; + + err = check_mem_region_access(env, regno, off, size, map->value_size, + zero_size_allowed); + if (err) + return err; + + if (map_value_has_spin_lock(map)) { + u32 lock = map->spin_lock_off; /* if any part of struct bpf_spin_lock can be touched by * load/store reject this program. @@ -2596,21 +2643,6 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, } } -static int __check_packet_access(struct bpf_verifier_env *env, u32 regno, - int off, int size, bool zero_size_allowed) -{ - struct bpf_reg_state *regs = cur_regs(env); - struct bpf_reg_state *reg = ®s[regno]; - - if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) || - (u64)off + size > reg->range) { - verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n", - off, size, regno, reg->id, reg->off, reg->range); - return -EACCES; - } - return 0; -} - static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, int size, bool zero_size_allowed) { @@ -2631,16 +2663,17 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, regno); return -EACCES; } - err = __check_packet_access(env, regno, off, size, zero_size_allowed); + err = __check_mem_access(env, regno, off, size, reg->range, + zero_size_allowed); if (err) { verbose(env, "R%d offset is outside of the packet\n", regno); return err; } - /* __check_packet_access has made sure "off + size - 1" is within u16. + /* __check_mem_access has made sure "off + size - 1" is within u16. * reg->umax_value can't be bigger than MAX_PACKET_OFF which is 0xffff, * otherwise find_good_pkt_pointers would have refused to set range info - * that __check_packet_access would have rejected this pkt access. + * that __check_mem_access would have rejected this pkt access. * Therefore, "off + reg->umax_value + size - 1" won't overflow u32. */ env->prog->aux->max_pkt_offset = @@ -3220,6 +3253,16 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn mark_reg_unknown(env, regs, value_regno); } } + } else if (reg->type == PTR_TO_MEM) { + if (t == BPF_WRITE && value_regno >= 0 && + is_pointer_value(env, value_regno)) { + verbose(env, "R%d leaks addr into mem\n", value_regno); + return -EACCES; + } + err = check_mem_region_access(env, regno, off, size, + reg->mem_size, false); + if (!err && t == BPF_READ && value_regno >= 0) + mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_CTX) { enum bpf_reg_type reg_type = SCALAR_VALUE; u32 btf_id = 0; @@ -3557,6 +3600,10 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return -EACCES; return check_map_access(env, regno, reg->off, access_size, zero_size_allowed); + case PTR_TO_MEM: + return check_mem_region_access(env, regno, reg->off, + access_size, reg->mem_size, + zero_size_allowed); default: /* scalar_value|ptr_to_stack or invalid ptr */ return check_stack_boundary(env, regno, access_size, zero_size_allowed, meta); @@ -3661,6 +3708,17 @@ static bool arg_type_is_mem_size(enum bpf_arg_type type) type == ARG_CONST_SIZE_OR_ZERO; } +static bool arg_type_is_alloc_mem_ptr(enum bpf_arg_type type) +{ + return type == ARG_PTR_TO_ALLOC_MEM || + type == ARG_PTR_TO_ALLOC_MEM_OR_NULL; +} + +static bool arg_type_is_alloc_size(enum bpf_arg_type type) +{ + return type == ARG_CONST_ALLOC_SIZE_OR_ZERO; +} + static bool arg_type_is_int_ptr(enum bpf_arg_type type) { return type == ARG_PTR_TO_INT || @@ -3720,7 +3778,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_SIZE || - arg_type == ARG_CONST_SIZE_OR_ZERO) { + arg_type == ARG_CONST_SIZE_OR_ZERO || + arg_type == ARG_CONST_ALLOC_SIZE_OR_ZERO) { expected_type = SCALAR_VALUE; if (type != expected_type) goto err_type; @@ -3791,13 +3850,29 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, * happens during stack boundary checking. */ if (register_is_null(reg) && - arg_type == ARG_PTR_TO_MEM_OR_NULL) + (arg_type == ARG_PTR_TO_MEM_OR_NULL || + arg_type == ARG_PTR_TO_ALLOC_MEM_OR_NULL)) /* final test in check_stack_boundary() */; else if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE && + type != PTR_TO_MEM && type != expected_type) goto err_type; meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM; + } else if (arg_type_is_alloc_mem_ptr(arg_type)) { + expected_type = PTR_TO_MEM; + if (register_is_null(reg) && + arg_type == ARG_PTR_TO_ALLOC_MEM_OR_NULL) + /* final test in check_stack_boundary() */; + else if (type != expected_type) + goto err_type; + if (meta->ref_obj_id) { + verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", + regno, reg->ref_obj_id, + meta->ref_obj_id); + return -EFAULT; + } + meta->ref_obj_id = reg->ref_obj_id; } else if (arg_type_is_int_ptr(arg_type)) { expected_type = PTR_TO_STACK; if (!type_is_pkt_pointer(type) && @@ -3893,6 +3968,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, zero_size_allowed, meta); if (!err) err = mark_chain_precision(env, regno); + } else if (arg_type_is_alloc_size(arg_type)) { + if (!tnum_is_const(reg->var_off)) { + verbose(env, "R%d unbounded size, use 'var &= const' or 'if (var < const)'\n", + regno); + return -EACCES; + } + meta->mem_size = reg->var_off.value; } else if (arg_type_is_int_ptr(arg_type)) { int size = int_ptr_type_to_size(arg_type); @@ -3929,6 +4011,14 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_xdp_output) goto error; break; + case BPF_MAP_TYPE_RINGBUF: + if (func_id != BPF_FUNC_ringbuf_output && + func_id != BPF_FUNC_ringbuf_reserve && + func_id != BPF_FUNC_ringbuf_submit && + func_id != BPF_FUNC_ringbuf_discard && + func_id != BPF_FUNC_ringbuf_query) + goto error; + break; case BPF_MAP_TYPE_STACK_TRACE: if (func_id != BPF_FUNC_get_stackid) goto error; @@ -4655,6 +4745,11 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL; regs[BPF_REG_0].id = ++env->id_gen; + } else if (fn->ret_type == RET_PTR_TO_ALLOC_MEM_OR_NULL) { + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL; + regs[BPF_REG_0].id = ++env->id_gen; + regs[BPF_REG_0].mem_size = meta.mem_size; } else { verbose(env, "unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); @@ -6611,6 +6706,8 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, reg->type = PTR_TO_TCP_SOCK; } else if (reg->type == PTR_TO_BTF_ID_OR_NULL) { reg->type = PTR_TO_BTF_ID; + } else if (reg->type == PTR_TO_MEM_OR_NULL) { + reg->type = PTR_TO_MEM; } if (is_null) { /* We don't need id and ref_obj_id from this point diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 187cd6995bbb..3767d34114c0 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1088,6 +1088,16 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_read_value_proto; case BPF_FUNC_get_ns_current_pid_tgid: return &bpf_get_ns_current_pid_tgid_proto; + case BPF_FUNC_ringbuf_output: + return &bpf_ringbuf_output_proto; + case BPF_FUNC_ringbuf_reserve: + return &bpf_ringbuf_reserve_proto; + case BPF_FUNC_ringbuf_submit: + return &bpf_ringbuf_submit_proto; + case BPF_FUNC_ringbuf_discard: + return &bpf_ringbuf_discard_proto; + case BPF_FUNC_ringbuf_query: + return &bpf_ringbuf_query_proto; default: return NULL; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 54b93f8b49b8..974ca6e948e3 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -147,6 +147,7 @@ enum bpf_map_type { BPF_MAP_TYPE_SK_STORAGE, BPF_MAP_TYPE_DEVMAP_HASH, BPF_MAP_TYPE_STRUCT_OPS, + BPF_MAP_TYPE_RINGBUF, }; /* Note that tracing related programs such as @@ -3157,6 +3158,59 @@ union bpf_attr { * **bpf_sk_cgroup_id**\ (). * Return * The id is returned or 0 in case the id could not be retrieved. + * + * void *bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) + * Description + * Copy *size* bytes from *data* into a ring buffer *ringbuf*. + * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of + * new data availability is sent. + * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of + * new data availability is sent unconditionally. + * Return + * 0, on success; + * < 0, on error. + * + * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags) + * Description + * Reserve *size* bytes of payload in a ring buffer *ringbuf*. + * Return + * Valid pointer with *size* bytes of memory available; NULL, + * otherwise. + * + * void bpf_ringbuf_submit(void *data, u64 flags) + * Description + * Submit reserved ring buffer sample, pointed to by *data*. + * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of + * new data availability is sent. + * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of + * new data availability is sent unconditionally. + * Return + * Nothing. Always succeeds. + * + * void bpf_ringbuf_discard(void *data, u64 flags) + * Description + * Discard reserved ring buffer sample, pointed to by *data*. + * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of + * new data availability is sent. + * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of + * new data availability is sent unconditionally. + * Return + * Nothing. Always succeeds. + * + * u64 bpf_ringbuf_query(void *ringbuf, u64 flags) + * Description + * Query various characteristics of provided ring buffer. What + * exactly is queries is determined by *flags*: + * - BPF_RB_AVAIL_DATA - amount of data not yet consumed; + * - BPF_RB_RING_SIZE - the size of ring buffer; + * - BPF_RB_CONS_POS - consumer position (can wrap around); + * - BPF_RB_PROD_POS - producer(s) position (can wrap around); + * Data returned is just a momentary snapshots of actual values + * and could be inaccurate, so this facility should be used to + * power heuristics and for reporting, not to make 100% correct + * calculation. + * Return + * Requested value, or 0, if flags are not recognized. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3288,7 +3342,12 @@ union bpf_attr { FN(seq_printf), \ FN(seq_write), \ FN(sk_cgroup_id), \ - FN(sk_ancestor_cgroup_id), + FN(sk_ancestor_cgroup_id), \ + FN(ringbuf_output), \ + FN(ringbuf_reserve), \ + FN(ringbuf_submit), \ + FN(ringbuf_discard), \ + FN(ringbuf_query), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3398,6 +3457,29 @@ enum { BPF_F_GET_BRANCH_RECORDS_SIZE = (1ULL << 0), }; +/* BPF_FUNC_bpf_ringbuf_commit, BPF_FUNC_bpf_ringbuf_discard, and + * BPF_FUNC_bpf_ringbuf_output flags. + */ +enum { + BPF_RB_NO_WAKEUP = (1ULL << 0), + BPF_RB_FORCE_WAKEUP = (1ULL << 1), +}; + +/* BPF_FUNC_bpf_ringbuf_query flags */ +enum { + BPF_RB_AVAIL_DATA = 0, + BPF_RB_RING_SIZE = 1, + BPF_RB_CONS_POS = 2, + BPF_RB_PROD_POS = 3, +}; + +/* BPF ring buffer constants */ +enum { + BPF_RINGBUF_BUSY_BIT = (1U << 31), + BPF_RINGBUF_DISCARD_BIT = (1U << 30), + BPF_RINGBUF_HDR_SZ = 8, +}; + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, diff --git a/tools/testing/selftests/bpf/verifier/and.c b/tools/testing/selftests/bpf/verifier/and.c index e0fad1548737..d781bc86e100 100644 --- a/tools/testing/selftests/bpf/verifier/and.c +++ b/tools/testing/selftests/bpf/verifier/and.c @@ -15,7 +15,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 3 }, - .errstr = "R0 max value is outside of the array range", + .errstr = "R0 max value is outside of the allowed memory range", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -44,7 +44,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 3 }, - .errstr = "R0 max value is outside of the array range", + .errstr = "R0 max value is outside of the allowed memory range", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c index f3c33e128709..1c4b1939f5a8 100644 --- a/tools/testing/selftests/bpf/verifier/array_access.c +++ b/tools/testing/selftests/bpf/verifier/array_access.c @@ -117,7 +117,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 3 }, - .errstr = "R0 min value is outside of the array range", + .errstr = "R0 min value is outside of the allowed memory range", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -137,7 +137,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 3 }, - .errstr = "R0 unbounded memory access, make sure to bounds check any array access into a map", + .errstr = "R0 unbounded memory access, make sure to bounds check any such access", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index 58f4aa593b1b..4d6645f2874c 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -20,7 +20,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_8b = { 3 }, - .errstr = "R0 max value is outside of the array range", + .errstr = "R0 max value is outside of the allowed memory range", .result = REJECT, }, { @@ -146,7 +146,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_8b = { 3 }, - .errstr = "R0 min value is outside of the array range", + .errstr = "R0 min value is outside of the allowed memory range", .result = REJECT }, { @@ -354,7 +354,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_8b = { 3 }, - .errstr = "R0 max value is outside of the array range", + .errstr = "R0 max value is outside of the allowed memory range", .result = REJECT }, { diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 7629a0cebb9b..94258c6b5235 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -105,7 +105,7 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, .fixup_map_hash_8b = { 16 }, .result = REJECT, - .errstr = "R0 min value is outside of the array range", + .errstr = "R0 min value is outside of the allowed memory range", }, { "calls: overlapping caller/callee", diff --git a/tools/testing/selftests/bpf/verifier/direct_value_access.c b/tools/testing/selftests/bpf/verifier/direct_value_access.c index b9fb28e8e224..988f46a1a4c7 100644 --- a/tools/testing/selftests/bpf/verifier/direct_value_access.c +++ b/tools/testing/selftests/bpf/verifier/direct_value_access.c @@ -68,7 +68,7 @@ }, .fixup_map_array_48b = { 1 }, .result = REJECT, - .errstr = "R1 min value is outside of the array range", + .errstr = "R1 min value is outside of the allowed memory range", }, { "direct map access, write test 7", @@ -220,7 +220,7 @@ }, .fixup_map_array_small = { 1 }, .result = REJECT, - .errstr = "R1 min value is outside of the array range", + .errstr = "R1 min value is outside of the allowed memory range", }, { "direct map access, write test 19", diff --git a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c index 67ab12410050..5a605ae131a9 100644 --- a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c +++ b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c @@ -318,7 +318,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 4 }, - .errstr = "R1 min value is outside of the array range", + .errstr = "R1 min value is outside of the allowed memory range", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, diff --git a/tools/testing/selftests/bpf/verifier/helper_value_access.c b/tools/testing/selftests/bpf/verifier/helper_value_access.c index 7572e403ddb9..961f28139b96 100644 --- a/tools/testing/selftests/bpf/verifier/helper_value_access.c +++ b/tools/testing/selftests/bpf/verifier/helper_value_access.c @@ -280,7 +280,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 3 }, - .errstr = "R1 min value is outside of the array range", + .errstr = "R1 min value is outside of the allowed memory range", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -415,7 +415,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 3 }, - .errstr = "R1 min value is outside of the array range", + .errstr = "R1 min value is outside of the allowed memory range", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -926,7 +926,7 @@ }, .fixup_map_hash_16b = { 3, 10 }, .result = REJECT, - .errstr = "R2 unbounded memory access, make sure to bounds check any array access into a map", + .errstr = "R2 unbounded memory access, make sure to bounds check any such access", .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, { diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index a53d99cebd9f..97ee658e1242 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -50,7 +50,7 @@ .fixup_map_array_48b = { 8 }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "R0 min value is outside of the array range", + .errstr_unpriv = "R0 min value is outside of the allowed memory range", .retval = 1, }, { @@ -325,7 +325,7 @@ }, .fixup_map_array_48b = { 3 }, .result = REJECT, - .errstr = "R0 min value is outside of the array range", + .errstr = "R0 min value is outside of the allowed memory range", .result_unpriv = REJECT, .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", }, @@ -601,7 +601,7 @@ }, .fixup_map_array_48b = { 3 }, .result = REJECT, - .errstr = "R1 max value is outside of the array range", + .errstr = "R1 max value is outside of the allowed memory range", .errstr_unpriv = "R1 pointer arithmetic of map value goes out of range", .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -726,7 +726,7 @@ }, .fixup_map_array_48b = { 3 }, .result = REJECT, - .errstr = "R0 min value is outside of the array range", + .errstr = "R0 min value is outside of the allowed memory range", }, { "map access: value_ptr -= known scalar, 2", -- cgit v1.2.3 From c3c16f2ea6d20159903cf93afbb1155f3d8348d5 Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Tue, 26 May 2020 17:34:36 -0700 Subject: bpf: Add rx_queue_mapping to bpf_sock Add "rx_queue_mapping" to bpf_sock. This gives read access for the existing field (sk_rx_queue_mapping) of struct sock from bpf_sock. Semantics for the bpf_sock rx_queue_mapping access are similar to sk_rx_queue_get(), i.e the value NO_QUEUE_MAPPING is not allowed and -1 is returned in that case. This is useful for transmit queue selection based on the received queue index which is cached in the socket in the receive path. v3: Addressed review comments to add usecase in patch description, and fixed default value for rx_queue_mapping. v2: fixed build error for CONFIG_XPS wrapping, reported by kbuild test robot Signed-off-by: Amritha Nambiar Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 1 + net/core/filter.c | 18 ++++++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 974ca6e948e3..630432c5c292 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3612,6 +3612,7 @@ struct bpf_sock { __u32 dst_ip4; __u32 dst_ip6[4]; __u32 state; + __s32 rx_queue_mapping; }; struct bpf_tcp_sock { diff --git a/net/core/filter.c b/net/core/filter.c index a6fc23447f12..0008b029d644 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6849,6 +6849,7 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, case offsetof(struct bpf_sock, protocol): case offsetof(struct bpf_sock, dst_port): case offsetof(struct bpf_sock, src_port): + case offsetof(struct bpf_sock, rx_queue_mapping): case bpf_ctx_range(struct bpf_sock, src_ip4): case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): case bpf_ctx_range(struct bpf_sock, dst_ip4): @@ -7897,6 +7898,23 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, skc_state), target_size)); break; + case offsetof(struct bpf_sock, rx_queue_mapping): +#ifdef CONFIG_XPS + *insn++ = BPF_LDX_MEM( + BPF_FIELD_SIZEOF(struct sock, sk_rx_queue_mapping), + si->dst_reg, si->src_reg, + bpf_target_off(struct sock, sk_rx_queue_mapping, + sizeof_field(struct sock, + sk_rx_queue_mapping), + target_size)); + *insn++ = BPF_JMP_IMM(BPF_JNE, si->dst_reg, NO_QUEUE_MAPPING, + 1); + *insn++ = BPF_MOV64_IMM(si->dst_reg, -1); +#else + *insn++ = BPF_MOV64_IMM(si->dst_reg, -1); + *target_size = 2; +#endif + break; } return insn - insn_buf; -- cgit v1.2.3 From fbee97feed9b3e4acdf9590e1f6b4a2eefecfffe Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 29 May 2020 16:07:13 -0600 Subject: bpf: Add support to attach bpf program to a devmap entry MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern Signed-off-by: Alexei Starovoitov Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 5 +++ include/uapi/linux/bpf.h | 1 + kernel/bpf/devmap.c | 88 ++++++++++++++++++++++++++++++++++++++++-- net/core/dev.c | 18 +++++++++ tools/include/uapi/linux/bpf.h | 1 + 5 files changed, 109 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e5884f7f801c..e042311f991f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1250,6 +1250,7 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); +bool dev_map_can_have_prog(struct bpf_map *map); struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); void __cpu_map_flush(void); @@ -1363,6 +1364,10 @@ static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map { return NULL; } +static inline bool dev_map_can_have_prog(struct bpf_map *map) +{ + return false; +} static inline void __dev_flush(void) { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 630432c5c292..f1e364d69007 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -225,6 +225,7 @@ enum bpf_attach_type { BPF_CGROUP_INET6_GETPEERNAME, BPF_CGROUP_INET4_GETSOCKNAME, BPF_CGROUP_INET6_GETSOCKNAME, + BPF_XDP_DEVMAP, __MAX_BPF_ATTACH_TYPE }; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index a1459de0914e..0089d56617ec 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -63,12 +63,17 @@ struct xdp_dev_bulk_queue { /* DEVMAP values */ struct bpf_devmap_val { u32 ifindex; /* device index */ + union { + int fd; /* prog fd on map write */ + u32 id; /* prog id on map read */ + } bpf_prog; }; struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ struct hlist_node index_hlist; struct bpf_dtab *dtab; + struct bpf_prog *xdp_prog; struct rcu_head rcu; unsigned int idx; struct bpf_devmap_val val; @@ -111,12 +116,18 @@ static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { + u32 valsize = attr->value_size; u64 cost = 0; int err; - /* check sanity of attributes */ + /* check sanity of attributes. 2 value sizes supported: + * 4 bytes: ifindex + * 8 bytes: ifindex + prog fd + */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK) + (valsize != offsetofend(struct bpf_devmap_val, ifindex) && + valsize != offsetofend(struct bpf_devmap_val, bpf_prog.fd)) || + attr->map_flags & ~DEV_CREATE_FLAG_MASK) return -EINVAL; /* Lookup returns a pointer straight to dev->ifindex, so make sure the @@ -223,6 +234,8 @@ static void dev_map_free(struct bpf_map *map) hlist_for_each_entry_safe(dev, next, head, index_hlist) { hlist_del_rcu(&dev->index_hlist); + if (dev->xdp_prog) + bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } @@ -237,6 +250,8 @@ static void dev_map_free(struct bpf_map *map) if (!dev) continue; + if (dev->xdp_prog) + bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } @@ -323,6 +338,16 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, return -ENOENT; } +bool dev_map_can_have_prog(struct bpf_map *map) +{ + if ((map->map_type == BPF_MAP_TYPE_DEVMAP || + map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) && + map->value_size != offsetofend(struct bpf_devmap_val, ifindex)) + return true; + + return false; +} + static int bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) { struct net_device *dev = bq->dev; @@ -447,6 +472,30 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, return bq_enqueue(dev, xdpf, dev_rx); } +static struct xdp_buff *dev_map_run_prog(struct net_device *dev, + struct xdp_buff *xdp, + struct bpf_prog *xdp_prog) +{ + u32 act; + + act = bpf_prog_run_xdp(xdp_prog, xdp); + switch (act) { + case XDP_PASS: + return xdp; + case XDP_DROP: + break; + default: + bpf_warn_invalid_xdp_action(act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(dev, xdp_prog, act); + break; + } + + xdp_return_buff(xdp); + return NULL; +} + int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, struct net_device *dev_rx) { @@ -458,6 +507,11 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, { struct net_device *dev = dst->dev; + if (dst->xdp_prog) { + xdp = dev_map_run_prog(dev, xdp, dst->xdp_prog); + if (!xdp) + return 0; + } return __xdp_enqueue(dev, xdp, dev_rx); } @@ -494,6 +548,8 @@ static void __dev_map_entry_free(struct rcu_head *rcu) struct bpf_dtab_netdev *dev; dev = container_of(rcu, struct bpf_dtab_netdev, rcu); + if (dev->xdp_prog) + bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } @@ -547,6 +603,7 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, struct bpf_devmap_val *val, unsigned int idx) { + struct bpf_prog *prog = NULL; struct bpf_dtab_netdev *dev; dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, @@ -558,11 +615,31 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, if (!dev->dev) goto err_out; + if (val->bpf_prog.fd >= 0) { + prog = bpf_prog_get_type_dev(val->bpf_prog.fd, + BPF_PROG_TYPE_XDP, false); + if (IS_ERR(prog)) + goto err_put_dev; + if (prog->expected_attach_type != BPF_XDP_DEVMAP) + goto err_put_prog; + } + dev->idx = idx; dev->dtab = dtab; + if (prog) { + dev->xdp_prog = prog; + dev->val.bpf_prog.id = prog->aux->id; + } else { + dev->xdp_prog = NULL; + dev->val.bpf_prog.id = 0; + } dev->val.ifindex = val->ifindex; return dev; +err_put_prog: + bpf_prog_put(prog); +err_put_dev: + dev_put(dev->dev); err_out: kfree(dev); return ERR_PTR(-EINVAL); @@ -572,8 +649,8 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_devmap_val val = { .bpf_prog.fd = -1 }; struct bpf_dtab_netdev *dev, *old_dev; - struct bpf_devmap_val val = { }; u32 i = *(u32 *)key; if (unlikely(map_flags > BPF_EXIST)) @@ -588,6 +665,9 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map, if (!val.ifindex) { dev = NULL; + /* can not specify fd if ifindex is 0 */ + if (val.bpf_prog.fd != -1) + return -EINVAL; } else { dev = __dev_map_alloc_node(net, dtab, &val, i); if (IS_ERR(dev)) @@ -616,8 +696,8 @@ static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_devmap_val val = { .bpf_prog.fd = -1 }; struct bpf_dtab_netdev *dev, *old_dev; - struct bpf_devmap_val val = { }; u32 idx = *(u32 *)key; unsigned long flags; int err = -EEXIST; diff --git a/net/core/dev.c b/net/core/dev.c index ae37586f6ee8..10684833f864 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5420,6 +5420,18 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) struct bpf_prog *new = xdp->prog; int ret = 0; + if (new) { + u32 i; + + /* generic XDP does not work with DEVMAPs that can + * have a bpf_prog installed on an entry + */ + for (i = 0; i < new->aux->used_map_cnt; i++) { + if (dev_map_can_have_prog(new->aux->used_maps[i])) + return -EINVAL; + } + } + switch (xdp->command) { case XDP_SETUP_PROG: rcu_assign_pointer(dev->xdp_prog, new); @@ -8835,6 +8847,12 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, return -EINVAL; } + if (prog->expected_attach_type == BPF_XDP_DEVMAP) { + NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device"); + bpf_prog_put(prog); + return -EINVAL; + } + /* prog->aux->id may be 0 for orphaned device-bound progs */ if (prog->aux->id && prog->aux->id == prog_id) { bpf_prog_put(prog); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 974ca6e948e3..65d7717bce2f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -225,6 +225,7 @@ enum bpf_attach_type { BPF_CGROUP_INET6_GETPEERNAME, BPF_CGROUP_INET4_GETSOCKNAME, BPF_CGROUP_INET6_GETSOCKNAME, + BPF_XDP_DEVMAP, __MAX_BPF_ATTACH_TYPE }; -- cgit v1.2.3 From 64b59025c15b244c0954cf52b24fbabfcf5ed8f6 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 29 May 2020 16:07:14 -0600 Subject: xdp: Add xdp_txq_info to xdp_buff MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add xdp_txq_info as the Tx counterpart to xdp_rxq_info. At the moment only the device is added. Other fields (queue_index) can be added as use cases arise. >From a UAPI perspective, add egress_ifindex to xdp context for bpf programs to see the Tx device. Update the verifier to only allow accesses to egress_ifindex by XDP programs with BPF_XDP_DEVMAP expected attach type. Signed-off-by: David Ahern Signed-off-by: Alexei Starovoitov Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20200529220716.75383-4-dsahern@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 5 +++++ include/uapi/linux/bpf.h | 2 ++ kernel/bpf/devmap.c | 3 +++ net/core/filter.c | 17 +++++++++++++++++ tools/include/uapi/linux/bpf.h | 2 ++ 5 files changed, 29 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/xdp.h b/include/net/xdp.h index 90f11760bd12..d54022959491 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -61,12 +61,17 @@ struct xdp_rxq_info { struct xdp_mem_info mem; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ +struct xdp_txq_info { + struct net_device *dev; +}; + struct xdp_buff { void *data; void *data_end; void *data_meta; void *data_hard_start; struct xdp_rxq_info *rxq; + struct xdp_txq_info *txq; u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/ }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f1e364d69007..f862a58fb567 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3707,6 +3707,8 @@ struct xdp_md { /* Below access go through struct xdp_rxq_info */ __u32 ingress_ifindex; /* rxq->dev->ifindex */ __u32 rx_queue_index; /* rxq->queue_index */ + + __u32 egress_ifindex; /* txq->dev->ifindex */ }; enum sk_action { diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 0089d56617ec..c04fb1c72f5e 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -476,8 +476,11 @@ static struct xdp_buff *dev_map_run_prog(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { + struct xdp_txq_info txq = { .dev = dev }; u32 act; + xdp->txq = &txq; + act = bpf_prog_run_xdp(xdp_prog, xdp); switch (act) { case XDP_PASS: diff --git a/net/core/filter.c b/net/core/filter.c index 0008b029d644..85ff827aab73 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7015,6 +7015,13 @@ static bool xdp_is_valid_access(int off, int size, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { + if (prog->expected_attach_type != BPF_XDP_DEVMAP) { + switch (off) { + case offsetof(struct xdp_md, egress_ifindex): + return false; + } + } + if (type == BPF_WRITE) { if (bpf_prog_is_dev_bound(prog->aux)) { switch (off) { @@ -7985,6 +7992,16 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, offsetof(struct xdp_rxq_info, queue_index)); break; + case offsetof(struct xdp_md, egress_ifindex): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, txq), + si->dst_reg, si->src_reg, + offsetof(struct xdp_buff, txq)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_txq_info, dev), + si->dst_reg, si->dst_reg, + offsetof(struct xdp_txq_info, dev)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct net_device, ifindex)); + break; } return insn - insn_buf; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 65d7717bce2f..f74bc4a2385e 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3706,6 +3706,8 @@ struct xdp_md { /* Below access go through struct xdp_rxq_info */ __u32 ingress_ifindex; /* rxq->dev->ifindex */ __u32 rx_queue_index; /* rxq->queue_index */ + + __u32 egress_ifindex; /* txq->dev->ifindex */ }; enum sk_action { -- cgit v1.2.3 From 7f045a49fee04b5662cbdeaf0838f9322ae8c63a Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Sun, 31 May 2020 10:28:38 +0200 Subject: bpf: Add link-based BPF program attachment to network namespace Extend bpf() syscall subcommands that operate on bpf_link, that is LINK_CREATE, LINK_UPDATE, OBJ_GET_INFO, to accept attach types tied to network namespaces (only flow dissector at the moment). Link-based and prog-based attachment can be used interchangeably, but only one can exist at a time. Attempts to attach a link when a prog is already attached directly, and the other way around, will be met with -EEXIST. Attempts to detach a program when link exists result in -EINVAL. Attachment of multiple links of same attach type to one netns is not supported with the intention to lift the restriction when a use-case presents itself. Because of that link create returns -E2BIG when trying to create another netns link, when one already exists. Link-based attachments to netns don't keep a netns alive by holding a ref to it. Instead links get auto-detached from netns when the latter is being destroyed, using a pernet pre_exit callback. When auto-detached, link lives in defunct state as long there are open FDs for it. -ENOLINK is returned if a user tries to update a defunct link. Because bpf_link to netns doesn't hold a ref to struct net, special care is taken when releasing, updating, or filling link info. The netns might be getting torn down when any of these link operations are in progress. That is why auto-detach and update/release/fill_info are synchronized by the same mutex. Also, link ops have to always check if auto-detach has not happened yet and if netns is still alive (refcnt > 0). Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200531082846.2117903-5-jakub@cloudflare.com --- include/linux/bpf-netns.h | 8 ++ include/linux/bpf_types.h | 3 + include/net/netns/bpf.h | 1 + include/uapi/linux/bpf.h | 5 + kernel/bpf/net_namespace.c | 244 ++++++++++++++++++++++++++++++++++++++++- kernel/bpf/syscall.c | 3 + tools/include/uapi/linux/bpf.h | 5 + 7 files changed, 267 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h index f3aec3d79824..4052d649f36d 100644 --- a/include/linux/bpf-netns.h +++ b/include/linux/bpf-netns.h @@ -34,6 +34,8 @@ int netns_bpf_prog_query(const union bpf_attr *attr, int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int netns_bpf_prog_detach(const union bpf_attr *attr); +int netns_bpf_link_create(const union bpf_attr *attr, + struct bpf_prog *prog); #else static inline int netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -51,6 +53,12 @@ static inline int netns_bpf_prog_detach(const union bpf_attr *attr) { return -EOPNOTSUPP; } + +static inline int netns_bpf_link_create(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif #endif /* _BPF_NETNS_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index fa8e1b552acd..a18ae82a298a 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -126,3 +126,6 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup) #endif BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter) +#ifdef CONFIG_NET +BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns) +#endif diff --git a/include/net/netns/bpf.h b/include/net/netns/bpf.h index a858d1c5b166..a8dce2a380c8 100644 --- a/include/net/netns/bpf.h +++ b/include/net/netns/bpf.h @@ -12,6 +12,7 @@ struct bpf_prog; struct netns_bpf { struct bpf_prog __rcu *progs[MAX_NETNS_BPF_ATTACH_TYPE]; + struct bpf_link *links[MAX_NETNS_BPF_ATTACH_TYPE]; }; #endif /* __NETNS_BPF_H__ */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f862a58fb567..b9ed9f14f2a2 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -237,6 +237,7 @@ enum bpf_link_type { BPF_LINK_TYPE_TRACING = 2, BPF_LINK_TYPE_CGROUP = 3, BPF_LINK_TYPE_ITER = 4, + BPF_LINK_TYPE_NETNS = 5, MAX_BPF_LINK_TYPE, }; @@ -3839,6 +3840,10 @@ struct bpf_link_info { __u64 cgroup_id; __u32 attach_type; } cgroup; + struct { + __u32 netns_ino; + __u32 attach_type; + } netns; }; } __attribute__((aligned(8))); diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c index b37d81450c3a..78cf061f8179 100644 --- a/kernel/bpf/net_namespace.c +++ b/kernel/bpf/net_namespace.c @@ -8,9 +8,140 @@ * Functions to manage BPF programs attached to netns */ +struct bpf_netns_link { + struct bpf_link link; + enum bpf_attach_type type; + enum netns_bpf_attach_type netns_type; + + /* We don't hold a ref to net in order to auto-detach the link + * when netns is going away. Instead we rely on pernet + * pre_exit callback to clear this pointer. Must be accessed + * with netns_bpf_mutex held. + */ + struct net *net; +}; + /* Protects updates to netns_bpf */ DEFINE_MUTEX(netns_bpf_mutex); +/* Must be called with netns_bpf_mutex held. */ +static void __net_exit bpf_netns_link_auto_detach(struct bpf_link *link) +{ + struct bpf_netns_link *net_link = + container_of(link, struct bpf_netns_link, link); + + net_link->net = NULL; +} + +static void bpf_netns_link_release(struct bpf_link *link) +{ + struct bpf_netns_link *net_link = + container_of(link, struct bpf_netns_link, link); + enum netns_bpf_attach_type type = net_link->netns_type; + struct net *net; + + /* Link auto-detached by dying netns. */ + if (!net_link->net) + return; + + mutex_lock(&netns_bpf_mutex); + + /* Recheck after potential sleep. We can race with cleanup_net + * here, but if we see a non-NULL struct net pointer pre_exit + * has not happened yet and will block on netns_bpf_mutex. + */ + net = net_link->net; + if (!net) + goto out_unlock; + + net->bpf.links[type] = NULL; + RCU_INIT_POINTER(net->bpf.progs[type], NULL); + +out_unlock: + mutex_unlock(&netns_bpf_mutex); +} + +static void bpf_netns_link_dealloc(struct bpf_link *link) +{ + struct bpf_netns_link *net_link = + container_of(link, struct bpf_netns_link, link); + + kfree(net_link); +} + +static int bpf_netns_link_update_prog(struct bpf_link *link, + struct bpf_prog *new_prog, + struct bpf_prog *old_prog) +{ + struct bpf_netns_link *net_link = + container_of(link, struct bpf_netns_link, link); + enum netns_bpf_attach_type type = net_link->netns_type; + struct net *net; + int ret = 0; + + if (old_prog && old_prog != link->prog) + return -EPERM; + if (new_prog->type != link->prog->type) + return -EINVAL; + + mutex_lock(&netns_bpf_mutex); + + net = net_link->net; + if (!net || !check_net(net)) { + /* Link auto-detached or netns dying */ + ret = -ENOLINK; + goto out_unlock; + } + + old_prog = xchg(&link->prog, new_prog); + rcu_assign_pointer(net->bpf.progs[type], new_prog); + bpf_prog_put(old_prog); + +out_unlock: + mutex_unlock(&netns_bpf_mutex); + return ret; +} + +static int bpf_netns_link_fill_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + const struct bpf_netns_link *net_link = + container_of(link, struct bpf_netns_link, link); + unsigned int inum = 0; + struct net *net; + + mutex_lock(&netns_bpf_mutex); + net = net_link->net; + if (net && check_net(net)) + inum = net->ns.inum; + mutex_unlock(&netns_bpf_mutex); + + info->netns.netns_ino = inum; + info->netns.attach_type = net_link->type; + return 0; +} + +static void bpf_netns_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + struct bpf_link_info info = {}; + + bpf_netns_link_fill_info(link, &info); + seq_printf(seq, + "netns_ino:\t%u\n" + "attach_type:\t%u\n", + info.netns.netns_ino, + info.netns.attach_type); +} + +static const struct bpf_link_ops bpf_netns_link_ops = { + .release = bpf_netns_link_release, + .dealloc = bpf_netns_link_dealloc, + .update_prog = bpf_netns_link_update_prog, + .fill_link_info = bpf_netns_link_fill_info, + .show_fdinfo = bpf_netns_link_show_fdinfo, +}; + int netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { @@ -67,6 +198,13 @@ int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) net = current->nsproxy->net_ns; mutex_lock(&netns_bpf_mutex); + + /* Attaching prog directly is not compatible with links */ + if (net->bpf.links[type]) { + ret = -EEXIST; + goto out_unlock; + } + switch (type) { case NETNS_BPF_FLOW_DISSECTOR: ret = flow_dissector_bpf_prog_attach(net, prog); @@ -75,6 +213,7 @@ int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) ret = -EINVAL; break; } +out_unlock: mutex_unlock(&netns_bpf_mutex); return ret; @@ -86,6 +225,10 @@ static int __netns_bpf_prog_detach(struct net *net, { struct bpf_prog *attached; + /* Progs attached via links cannot be detached */ + if (net->bpf.links[type]) + return -EINVAL; + attached = rcu_dereference_protected(net->bpf.progs[type], lockdep_is_held(&netns_bpf_mutex)); if (!attached) @@ -111,13 +254,110 @@ int netns_bpf_prog_detach(const union bpf_attr *attr) return ret; } +static int netns_bpf_link_attach(struct net *net, struct bpf_link *link, + enum netns_bpf_attach_type type) +{ + struct bpf_prog *prog; + int err; + + mutex_lock(&netns_bpf_mutex); + + /* Allow attaching only one prog or link for now */ + if (net->bpf.links[type]) { + err = -E2BIG; + goto out_unlock; + } + /* Links are not compatible with attaching prog directly */ + prog = rcu_dereference_protected(net->bpf.progs[type], + lockdep_is_held(&netns_bpf_mutex)); + if (prog) { + err = -EEXIST; + goto out_unlock; + } + + switch (type) { + case NETNS_BPF_FLOW_DISSECTOR: + err = flow_dissector_bpf_prog_attach(net, link->prog); + break; + default: + err = -EINVAL; + break; + } + if (err) + goto out_unlock; + + net->bpf.links[type] = link; + +out_unlock: + mutex_unlock(&netns_bpf_mutex); + return err; +} + +int netns_bpf_link_create(const union bpf_attr *attr, struct bpf_prog *prog) +{ + enum netns_bpf_attach_type netns_type; + struct bpf_link_primer link_primer; + struct bpf_netns_link *net_link; + enum bpf_attach_type type; + struct net *net; + int err; + + if (attr->link_create.flags) + return -EINVAL; + + type = attr->link_create.attach_type; + netns_type = to_netns_bpf_attach_type(type); + if (netns_type < 0) + return -EINVAL; + + net = get_net_ns_by_fd(attr->link_create.target_fd); + if (IS_ERR(net)) + return PTR_ERR(net); + + net_link = kzalloc(sizeof(*net_link), GFP_USER); + if (!net_link) { + err = -ENOMEM; + goto out_put_net; + } + bpf_link_init(&net_link->link, BPF_LINK_TYPE_NETNS, + &bpf_netns_link_ops, prog); + net_link->net = net; + net_link->type = type; + net_link->netns_type = netns_type; + + err = bpf_link_prime(&net_link->link, &link_primer); + if (err) { + kfree(net_link); + goto out_put_net; + } + + err = netns_bpf_link_attach(net, &net_link->link, netns_type); + if (err) { + bpf_link_cleanup(&link_primer); + goto out_put_net; + } + + put_net(net); + return bpf_link_settle(&link_primer); + +out_put_net: + put_net(net); + return err; +} + static void __net_exit netns_bpf_pernet_pre_exit(struct net *net) { enum netns_bpf_attach_type type; + struct bpf_link *link; mutex_lock(&netns_bpf_mutex); - for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) - __netns_bpf_prog_detach(net, type); + for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) { + link = net->bpf.links[type]; + if (link) + bpf_netns_link_auto_detach(link); + else + __netns_bpf_prog_detach(net, type); + } mutex_unlock(&netns_bpf_mutex); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c77ab9c76f7b..e14a842d7e0d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3887,6 +3887,9 @@ static int link_create(union bpf_attr *attr) case BPF_PROG_TYPE_TRACING: ret = tracing_bpf_link_attach(attr, prog); break; + case BPF_PROG_TYPE_FLOW_DISSECTOR: + ret = netns_bpf_link_create(attr, prog); + break; default: ret = -EINVAL; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f862a58fb567..b9ed9f14f2a2 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -237,6 +237,7 @@ enum bpf_link_type { BPF_LINK_TYPE_TRACING = 2, BPF_LINK_TYPE_CGROUP = 3, BPF_LINK_TYPE_ITER = 4, + BPF_LINK_TYPE_NETNS = 5, MAX_BPF_LINK_TYPE, }; @@ -3839,6 +3840,10 @@ struct bpf_link_info { __u64 cgroup_id; __u32 attach_type; } cgroup; + struct { + __u32 netns_ino; + __u32 attach_type; + } netns; }; } __attribute__((aligned(8))); -- cgit v1.2.3 From e7c8cc35a64d1d21e6fb811c519eadbda30f4f77 Mon Sep 17 00:00:00 2001 From: Matej Genci Date: Wed, 11 Sep 2019 12:49:53 +0000 Subject: virtio: add VIRTIO_RING_NO_LEGACY Add macro to disable legacy vring functions. Signed-off-by: Matej Genci Link: https://lore.kernel.org/r/20190911124942.243713-1-matej.genci@nutanix.com Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_pci_modern.c | 1 + include/uapi/linux/virtio_ring.h | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 7abcc50838b8..db93cedd262f 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -16,6 +16,7 @@ #include #define VIRTIO_PCI_NO_LEGACY +#define VIRTIO_RING_NO_LEGACY #include "virtio_pci_common.h" /* diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h index 559f42e73315..9223c3a5c46a 100644 --- a/include/uapi/linux/virtio_ring.h +++ b/include/uapi/linux/virtio_ring.h @@ -135,6 +135,8 @@ struct vring { #define VRING_USED_ALIGN_SIZE 4 #define VRING_DESC_ALIGN_SIZE 16 +#ifndef VIRTIO_RING_NO_LEGACY + /* The standard layout for the ring is a continuous chunk of memory which looks * like this. We assume num is a power of 2. * @@ -181,6 +183,8 @@ static inline unsigned vring_size(unsigned int num, unsigned long align) + sizeof(__virtio16) * 3 + sizeof(struct vring_used_elem) * num; } +#endif /* VIRTIO_RING_NO_LEGACY */ + /* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */ /* Assuming a given event_idx value from the other side, if * we have just incremented index from old to new_idx, -- cgit v1.2.3 From a865e420b9561235851c3f5d483c82ef389d29bd Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 6 Apr 2020 08:42:55 -0400 Subject: virtio: force spec specified alignment on types The ring element addresses are passed between components with different alignments assumptions. Thus, if guest/userspace selects a pointer and host then gets and dereferences it, we might need to decrease the compiler-selected alignment to prevent compiler on the host from assuming pointer is aligned. This actually triggers on ARM with -mabi=apcs-gnu - which is a deprecated configuration, but it seems safer to handle this generally. Note that userspace that allocates the memory is actually OK and does not need to be fixed, but userspace that gets it from guest or another process does need to be fixed. The later doesn't generally talk to the kernel so while it might be buggy it's not talking to the kernel in the buggy way - it's just using the header in the buggy way - so fixing header and asking userspace to recompile is the best we can do. I verified that the produced kernel binary on x86 is exactly identical before and after the change. Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vhost/vhost.c | 8 +++---- drivers/vhost/vhost.h | 6 +++--- drivers/vhost/vringh.c | 6 +++--- include/linux/vringh.h | 6 +++--- include/uapi/linux/virtio_ring.h | 46 ++++++++++++++++++++++++++++++---------- 5 files changed, 48 insertions(+), 24 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 21a59b598ed8..96d9871fa0cb 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1244,9 +1244,9 @@ static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access) } static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, - struct vring_desc __user *desc, - struct vring_avail __user *avail, - struct vring_used __user *used) + vring_desc_t __user *desc, + vring_avail_t __user *avail, + vring_used_t __user *used) { return access_ok(desc, vhost_get_desc_size(vq, num)) && @@ -2301,7 +2301,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads, unsigned count) { - struct vring_used_elem __user *used; + vring_used_elem_t __user *used; u16 old, new; int start; diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index f8403bd46b85..60cab4c78229 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -67,9 +67,9 @@ struct vhost_virtqueue { /* The actual ring of buffers. */ struct mutex mutex; unsigned int num; - struct vring_desc __user *desc; - struct vring_avail __user *avail; - struct vring_used __user *used; + vring_desc_t __user *desc; + vring_avail_t __user *avail; + vring_used_t __user *used; const struct vhost_iotlb_map *meta_iotlb[VHOST_NUM_ADDRS]; struct file *kick; struct eventfd_ctx *call_ctx; diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index ba8e0d6cfd97..e059a9a47cdf 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -620,9 +620,9 @@ static inline int xfer_to_user(const struct vringh *vrh, */ int vringh_init_user(struct vringh *vrh, u64 features, unsigned int num, bool weak_barriers, - struct vring_desc __user *desc, - struct vring_avail __user *avail, - struct vring_used __user *used) + vring_desc_t __user *desc, + vring_avail_t __user *avail, + vring_used_t __user *used) { /* Sane power of 2 please! */ if (!num || num > 0xffff || (num & (num - 1))) { diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 9e2763d7c159..59bd50f99291 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -105,9 +105,9 @@ struct vringh_kiov { /* Helpers for userspace vrings. */ int vringh_init_user(struct vringh *vrh, u64 features, unsigned int num, bool weak_barriers, - struct vring_desc __user *desc, - struct vring_avail __user *avail, - struct vring_used __user *used); + vring_desc_t __user *desc, + vring_avail_t __user *avail, + vring_used_t __user *used); static inline void vringh_iov_init(struct vringh_iov *iov, struct iovec *iovec, unsigned num) diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h index 9223c3a5c46a..476d3e5c0fe7 100644 --- a/include/uapi/linux/virtio_ring.h +++ b/include/uapi/linux/virtio_ring.h @@ -86,6 +86,13 @@ * at the end of the used ring. Guest should ignore the used->flags field. */ #define VIRTIO_RING_F_EVENT_IDX 29 +/* Alignment requirements for vring elements. + * When using pre-virtio 1.0 layout, these fall out naturally. + */ +#define VRING_AVAIL_ALIGN_SIZE 2 +#define VRING_USED_ALIGN_SIZE 4 +#define VRING_DESC_ALIGN_SIZE 16 + /* Virtio ring descriptors: 16 bytes. These can chain together via "next". */ struct vring_desc { /* Address (guest-physical). */ @@ -112,29 +119,46 @@ struct vring_used_elem { __virtio32 len; }; +typedef struct vring_used_elem __attribute__((aligned(VRING_USED_ALIGN_SIZE))) + vring_used_elem_t; + struct vring_used { __virtio16 flags; __virtio16 idx; - struct vring_used_elem ring[]; + vring_used_elem_t ring[]; }; +/* + * The ring element addresses are passed between components with different + * alignments assumptions. Thus, we might need to decrease the compiler-selected + * alignment, and so must use a typedef to make sure the aligned attribute + * actually takes hold: + * + * https://gcc.gnu.org/onlinedocs//gcc/Common-Type-Attributes.html#Common-Type-Attributes + * + * When used on a struct, or struct member, the aligned attribute can only + * increase the alignment; in order to decrease it, the packed attribute must + * be specified as well. When used as part of a typedef, the aligned attribute + * can both increase and decrease alignment, and specifying the packed + * attribute generates a warning. + */ +typedef struct vring_desc __attribute__((aligned(VRING_DESC_ALIGN_SIZE))) + vring_desc_t; +typedef struct vring_avail __attribute__((aligned(VRING_AVAIL_ALIGN_SIZE))) + vring_avail_t; +typedef struct vring_used __attribute__((aligned(VRING_USED_ALIGN_SIZE))) + vring_used_t; + struct vring { unsigned int num; - struct vring_desc *desc; + vring_desc_t *desc; - struct vring_avail *avail; + vring_avail_t *avail; - struct vring_used *used; + vring_used_t *used; }; -/* Alignment requirements for vring elements. - * When using pre-virtio 1.0 layout, these fall out naturally. - */ -#define VRING_AVAIL_ALIGN_SIZE 2 -#define VRING_USED_ALIGN_SIZE 4 -#define VRING_DESC_ALIGN_SIZE 16 - #ifndef VIRTIO_RING_NO_LEGACY /* The standard layout for the ring is a continuous chunk of memory which looks -- cgit v1.2.3 From 24c986748ba670c903a9d6a11ee96de2b3f5f1b8 Mon Sep 17 00:00:00 2001 From: Farhan Ali Date: Tue, 5 May 2020 14:27:41 +0200 Subject: vfio-ccw: Introduce a new schib region The schib region can be used by userspace to get the subchannel- information block (SCHIB) for the passthrough subchannel. This can be useful to get information such as channel path information via the SCHIB.PMCW fields. Signed-off-by: Farhan Ali Signed-off-by: Eric Farman Reviewed-by: Cornelia Huck Message-Id: <20200505122745.53208-5-farman@linux.ibm.com> Signed-off-by: Cornelia Huck --- Documentation/s390/vfio-ccw.rst | 18 ++++++++- drivers/s390/cio/Makefile | 2 +- drivers/s390/cio/vfio_ccw_chp.c | 76 +++++++++++++++++++++++++++++++++++++ drivers/s390/cio/vfio_ccw_drv.c | 20 ++++++++++ drivers/s390/cio/vfio_ccw_ops.c | 14 ++++++- drivers/s390/cio/vfio_ccw_private.h | 3 ++ include/uapi/linux/vfio.h | 1 + include/uapi/linux/vfio_ccw.h | 10 +++++ 8 files changed, 140 insertions(+), 4 deletions(-) create mode 100644 drivers/s390/cio/vfio_ccw_chp.c (limited to 'include/uapi/linux') diff --git a/Documentation/s390/vfio-ccw.rst b/Documentation/s390/vfio-ccw.rst index 3a946fd45562..32310df525ba 100644 --- a/Documentation/s390/vfio-ccw.rst +++ b/Documentation/s390/vfio-ccw.rst @@ -282,6 +282,21 @@ for each access of the region. The following values may occur: ``-EBUSY`` The subchannel was status pending or busy while processing a halt request. +vfio-ccw schib region +--------------------- + +The vfio-ccw schib region is used to return Subchannel-Information +Block (SCHIB) data to userspace:: + + struct ccw_schib_region { + #define SCHIB_AREA_SIZE 52 + __u8 schib_area[SCHIB_AREA_SIZE]; + } __packed; + +This region is exposed via region type VFIO_REGION_SUBTYPE_CCW_SCHIB. + +Reading this region triggers a STORE SUBCHANNEL to be issued to the +associated hardware. vfio-ccw operation details -------------------------- @@ -385,7 +400,8 @@ through DASD/ECKD device online in a guest now and use it as a block device. The current code allows the guest to start channel programs via -START SUBCHANNEL, and to issue HALT SUBCHANNEL and CLEAR SUBCHANNEL. +START SUBCHANNEL, and to issue HALT SUBCHANNEL, CLEAR SUBCHANNEL, +and STORE SUBCHANNEL. Currently all channel programs are prefetched, regardless of the p-bit setting in the ORB. As a result, self modifying channel diff --git a/drivers/s390/cio/Makefile b/drivers/s390/cio/Makefile index 23eae4188876..a9235f111e79 100644 --- a/drivers/s390/cio/Makefile +++ b/drivers/s390/cio/Makefile @@ -21,5 +21,5 @@ qdio-objs := qdio_main.o qdio_thinint.o qdio_debug.o qdio_setup.o obj-$(CONFIG_QDIO) += qdio.o vfio_ccw-objs += vfio_ccw_drv.o vfio_ccw_cp.o vfio_ccw_ops.o vfio_ccw_fsm.o \ - vfio_ccw_async.o vfio_ccw_trace.o + vfio_ccw_async.o vfio_ccw_trace.o vfio_ccw_chp.o obj-$(CONFIG_VFIO_CCW) += vfio_ccw.o diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c new file mode 100644 index 000000000000..18f3b3e873a9 --- /dev/null +++ b/drivers/s390/cio/vfio_ccw_chp.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Channel path related status regions for vfio_ccw + * + * Copyright IBM Corp. 2020 + * + * Author(s): Farhan Ali + * Eric Farman + */ + +#include +#include "vfio_ccw_private.h" + +static ssize_t vfio_ccw_schib_region_read(struct vfio_ccw_private *private, + char __user *buf, size_t count, + loff_t *ppos) +{ + unsigned int i = VFIO_CCW_OFFSET_TO_INDEX(*ppos) - VFIO_CCW_NUM_REGIONS; + loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK; + struct ccw_schib_region *region; + int ret; + + if (pos + count > sizeof(*region)) + return -EINVAL; + + mutex_lock(&private->io_mutex); + region = private->region[i].data; + + if (cio_update_schib(private->sch)) { + ret = -ENODEV; + goto out; + } + + memcpy(region, &private->sch->schib, sizeof(*region)); + + if (copy_to_user(buf, (void *)region + pos, count)) { + ret = -EFAULT; + goto out; + } + + ret = count; + +out: + mutex_unlock(&private->io_mutex); + return ret; +} + +static ssize_t vfio_ccw_schib_region_write(struct vfio_ccw_private *private, + const char __user *buf, size_t count, + loff_t *ppos) +{ + return -EINVAL; +} + + +static void vfio_ccw_schib_region_release(struct vfio_ccw_private *private, + struct vfio_ccw_region *region) +{ + +} + +const struct vfio_ccw_regops vfio_ccw_schib_region_ops = { + .read = vfio_ccw_schib_region_read, + .write = vfio_ccw_schib_region_write, + .release = vfio_ccw_schib_region_release, +}; + +int vfio_ccw_register_schib_dev_regions(struct vfio_ccw_private *private) +{ + return vfio_ccw_register_dev_region(private, + VFIO_REGION_SUBTYPE_CCW_SCHIB, + &vfio_ccw_schib_region_ops, + sizeof(struct ccw_schib_region), + VFIO_REGION_INFO_FLAG_READ, + private->schib_region); +} diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index fb1275a7d1f5..7aeff42f370d 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -27,6 +27,7 @@ struct workqueue_struct *vfio_ccw_work_q; static struct kmem_cache *vfio_ccw_io_region; static struct kmem_cache *vfio_ccw_cmd_region; +static struct kmem_cache *vfio_ccw_schib_region; debug_info_t *vfio_ccw_debug_msg_id; debug_info_t *vfio_ccw_debug_trace_id; @@ -119,6 +120,8 @@ static void vfio_ccw_sch_irq(struct subchannel *sch) static void vfio_ccw_free_regions(struct vfio_ccw_private *private) { + if (private->schib_region) + kmem_cache_free(vfio_ccw_schib_region, private->schib_region); if (private->cmd_region) kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region); if (private->io_region) @@ -156,6 +159,12 @@ static int vfio_ccw_sch_probe(struct subchannel *sch) if (!private->cmd_region) goto out_free; + private->schib_region = kmem_cache_zalloc(vfio_ccw_schib_region, + GFP_KERNEL | GFP_DMA); + + if (!private->schib_region) + goto out_free; + private->sch = sch; dev_set_drvdata(&sch->dev, private); mutex_init(&private->io_mutex); @@ -357,6 +366,7 @@ static void vfio_ccw_debug_exit(void) static void vfio_ccw_destroy_regions(void) { + kmem_cache_destroy(vfio_ccw_schib_region); kmem_cache_destroy(vfio_ccw_cmd_region); kmem_cache_destroy(vfio_ccw_io_region); } @@ -393,6 +403,16 @@ static int __init vfio_ccw_sch_init(void) goto out_err; } + vfio_ccw_schib_region = kmem_cache_create_usercopy("vfio_ccw_schib_region", + sizeof(struct ccw_schib_region), 0, + SLAB_ACCOUNT, 0, + sizeof(struct ccw_schib_region), NULL); + + if (!vfio_ccw_schib_region) { + ret = -ENOMEM; + goto out_err; + } + isc_register(VFIO_CCW_ISC); ret = css_driver_register(&vfio_ccw_sch_driver); if (ret) { diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c index d4fc84b8867f..22988d67b6bb 100644 --- a/drivers/s390/cio/vfio_ccw_ops.c +++ b/drivers/s390/cio/vfio_ccw_ops.c @@ -172,8 +172,18 @@ static int vfio_ccw_mdev_open(struct mdev_device *mdev) ret = vfio_ccw_register_async_dev_regions(private); if (ret) - vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY, - &private->nb); + goto out_unregister; + + ret = vfio_ccw_register_schib_dev_regions(private); + if (ret) + goto out_unregister; + + return ret; + +out_unregister: + vfio_ccw_unregister_dev_regions(private); + vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY, + &private->nb); return ret; } diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h index ce3834159d98..d6601a8adf13 100644 --- a/drivers/s390/cio/vfio_ccw_private.h +++ b/drivers/s390/cio/vfio_ccw_private.h @@ -56,6 +56,7 @@ int vfio_ccw_register_dev_region(struct vfio_ccw_private *private, void vfio_ccw_unregister_dev_regions(struct vfio_ccw_private *private); int vfio_ccw_register_async_dev_regions(struct vfio_ccw_private *private); +int vfio_ccw_register_schib_dev_regions(struct vfio_ccw_private *private); /** * struct vfio_ccw_private @@ -69,6 +70,7 @@ int vfio_ccw_register_async_dev_regions(struct vfio_ccw_private *private); * @io_mutex: protect against concurrent update of I/O regions * @region: additional regions for other subchannel operations * @cmd_region: MMIO region for asynchronous I/O commands other than START + * @schib_region: MMIO region for SCHIB information * @num_regions: number of additional regions * @cp: channel program for the current I/O operation * @irb: irb info received from interrupt @@ -87,6 +89,7 @@ struct vfio_ccw_private { struct mutex io_mutex; struct vfio_ccw_region *region; struct ccw_cmd_region *cmd_region; + struct ccw_schib_region *schib_region; int num_regions; struct channel_program cp; diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 015516bcfaa3..7a1abbd889bd 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -378,6 +378,7 @@ struct vfio_region_gfx_edid { /* sub-types for VFIO_REGION_TYPE_CCW */ #define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD (1) +#define VFIO_REGION_SUBTYPE_CCW_SCHIB (2) /* * The MSIX mappable capability informs that MSIX data of a BAR can be mmapped diff --git a/include/uapi/linux/vfio_ccw.h b/include/uapi/linux/vfio_ccw.h index cbecbf0cd54f..758bf214898d 100644 --- a/include/uapi/linux/vfio_ccw.h +++ b/include/uapi/linux/vfio_ccw.h @@ -34,4 +34,14 @@ struct ccw_cmd_region { __u32 ret_code; } __packed; +/* + * Used for processing commands that read the subchannel-information block + * Reading this region triggers a stsch() to hardware + * Note: this is controlled by a capability + */ +struct ccw_schib_region { +#define SCHIB_AREA_SIZE 52 + __u8 schib_area[SCHIB_AREA_SIZE]; +} __packed; + #endif -- cgit v1.2.3 From 836e66c218f355ec01ba57671c85abf32961dcea Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 2 Jun 2020 16:58:32 +0200 Subject: bpf: Fix up bpf_skb_adjust_room helper's skb csum setting Lorenz recently reported: In our TC classifier cls_redirect [0], we use the following sequence of helper calls to decapsulate a GUE (basically IP + UDP + custom header) encapsulated packet: bpf_skb_adjust_room(skb, -encap_len, BPF_ADJ_ROOM_MAC, BPF_F_ADJ_ROOM_FIXED_GSO) bpf_redirect(skb->ifindex, BPF_F_INGRESS) It seems like some checksums of the inner headers are not validated in this case. For example, a TCP SYN packet with invalid TCP checksum is still accepted by the network stack and elicits a SYN ACK. [...] That is, we receive the following packet from the driver: | ETH | IP | UDP | GUE | IP | TCP | skb->ip_summed == CHECKSUM_UNNECESSARY ip_summed is CHECKSUM_UNNECESSARY because our NICs do rx checksum offloading. On this packet we run skb_adjust_room_mac(-encap_len), and get the following: | ETH | IP | TCP | skb->ip_summed == CHECKSUM_UNNECESSARY Note that ip_summed is still CHECKSUM_UNNECESSARY. After bpf_redirect()'ing into the ingress, we end up in tcp_v4_rcv(). There, skb_checksum_init() is turned into a no-op due to CHECKSUM_UNNECESSARY. The bpf_skb_adjust_room() helper is not aware of protocol specifics. Internally, it handles the CHECKSUM_COMPLETE case via skb_postpull_rcsum(), but that does not cover CHECKSUM_UNNECESSARY. In this case skb->csum_level of the original skb prior to bpf_skb_adjust_room() call was 0, that is, covering UDP. Right now there is no way to adjust the skb->csum_level. NICs that have checksum offload disabled (CHECKSUM_NONE) or that support CHECKSUM_COMPLETE are not affected. Use a safe default for CHECKSUM_UNNECESSARY by resetting to CHECKSUM_NONE and add a flag to the helper called BPF_F_ADJ_ROOM_NO_CSUM_RESET that allows users from opting out. Opting out is useful for the case where we don't remove/add full protocol headers, or for the case where a user wants to adjust the csum level manually e.g. through bpf_csum_level() helper that is added in subsequent patch. The bpf_skb_proto_{4_to_6,6_to_4}() for NAT64/46 translation from the BPF bpf_skb_change_proto() helper uses bpf_skb_net_hdr_{push,pop}() pair internally as well but doesn't change layers, only transitions between v4 to v6 and vice versa, therefore no adoption is required there. [0] https://lore.kernel.org/bpf/20200424185556.7358-1-lmb@cloudflare.com/ Fixes: 2be7e212d541 ("bpf: add bpf_skb_adjust_room helper") Reported-by: Lorenz Bauer Reported-by: Alan Maguire Signed-off-by: Daniel Borkmann Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Reviewed-by: Alan Maguire Link: https://lore.kernel.org/bpf/CACAyw9-uU_52esMd1JjuA80fRPHJv5vsSg8GnfW3t_qDU4aVKQ@mail.gmail.com/ Link: https://lore.kernel.org/bpf/11a90472e7cce83e76ddbfce81fdfce7bfc68808.1591108731.git.daniel@iogearbox.net --- include/linux/skbuff.h | 8 ++++++++ include/uapi/linux/bpf.h | 8 ++++++++ net/core/filter.c | 8 ++++++-- tools/include/uapi/linux/bpf.h | 8 ++++++++ 4 files changed, 30 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a0d5c2760103..0c0377fc00c2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3919,6 +3919,14 @@ static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) } } +static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb) +{ + if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + skb->ip_summed = CHECKSUM_NONE; + skb->csum_level = 0; + } +} + /* Check if we need to perform checksum complete validation. * * Returns true if checksum complete is needed, false otherwise diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b9ed9f14f2a2..3ba2bbbed80c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1635,6 +1635,13 @@ union bpf_attr { * Grow or shrink the room for data in the packet associated to * *skb* by *len_diff*, and according to the selected *mode*. * + * By default, the helper will reset any offloaded checksum + * indicator of the skb to CHECKSUM_NONE. This can be avoided + * by the following flag: + * + * * **BPF_F_ADJ_ROOM_NO_CSUM_RESET**: Do not reset offloaded + * checksum data of the skb to CHECKSUM_NONE. + * * There are two supported modes at this time: * * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer @@ -3433,6 +3440,7 @@ enum { BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 = (1ULL << 2), BPF_F_ADJ_ROOM_ENCAP_L4_GRE = (1ULL << 3), BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4), + BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5), }; enum { diff --git a/net/core/filter.c b/net/core/filter.c index ae82bcb03124..278dcc0af961 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3113,7 +3113,8 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff, { int ret; - if (flags & ~BPF_F_ADJ_ROOM_FIXED_GSO) + if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO | + BPF_F_ADJ_ROOM_NO_CSUM_RESET))) return -EINVAL; if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) { @@ -3163,7 +3164,8 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32 off; int ret; - if (unlikely(flags & ~BPF_F_ADJ_ROOM_MASK)) + if (unlikely(flags & ~(BPF_F_ADJ_ROOM_MASK | + BPF_F_ADJ_ROOM_NO_CSUM_RESET))) return -EINVAL; if (unlikely(len_diff_abs > 0xfffU)) return -EFAULT; @@ -3191,6 +3193,8 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, ret = shrink ? bpf_skb_net_shrink(skb, off, len_diff_abs, flags) : bpf_skb_net_grow(skb, off, len_diff_abs, flags); + if (!ret && !(flags & BPF_F_ADJ_ROOM_NO_CSUM_RESET)) + __skb_reset_checksum_unnecessary(skb); bpf_compute_data_pointers(skb); return ret; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index b9ed9f14f2a2..3ba2bbbed80c 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1635,6 +1635,13 @@ union bpf_attr { * Grow or shrink the room for data in the packet associated to * *skb* by *len_diff*, and according to the selected *mode*. * + * By default, the helper will reset any offloaded checksum + * indicator of the skb to CHECKSUM_NONE. This can be avoided + * by the following flag: + * + * * **BPF_F_ADJ_ROOM_NO_CSUM_RESET**: Do not reset offloaded + * checksum data of the skb to CHECKSUM_NONE. + * * There are two supported modes at this time: * * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer @@ -3433,6 +3440,7 @@ enum { BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 = (1ULL << 2), BPF_F_ADJ_ROOM_ENCAP_L4_GRE = (1ULL << 3), BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4), + BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5), }; enum { -- cgit v1.2.3 From 7cdec54f9713256bb170873a1fc5c75c9127c9d2 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 2 Jun 2020 16:58:33 +0200 Subject: bpf: Add csum_level helper for fixing up csum levels Add a bpf_csum_level() helper which BPF programs can use in combination with bpf_skb_adjust_room() when they pass in BPF_F_ADJ_ROOM_NO_CSUM_RESET flag to the latter to avoid falling back to CHECKSUM_NONE. The bpf_csum_level() allows to adjust CHECKSUM_UNNECESSARY skb->csum_levels via BPF_CSUM_LEVEL_{INC,DEC} which calls __skb_{incr,decr}_checksum_unnecessary() on the skb. The helper also allows a BPF_CSUM_LEVEL_RESET which sets the skb's csum to CHECKSUM_NONE as well as a BPF_CSUM_LEVEL_QUERY to just return the current level. Without this helper, there is no way to otherwise adjust the skb->csum_level. I did not add an extra dummy flags as there is plenty of free bitspace in level argument itself iff ever needed in future. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Reviewed-by: Alan Maguire Acked-by: Lorenz Bauer Link: https://lore.kernel.org/bpf/279ae3717cb3d03c0ffeb511493c93c450a01e1a.1591108731.git.daniel@iogearbox.net --- include/uapi/linux/bpf.h | 43 +++++++++++++++++++++++++++++++++++++++++- net/core/filter.c | 38 +++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 43 +++++++++++++++++++++++++++++++++++++++++- 3 files changed, 122 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3ba2bbbed80c..c65b374a5090 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3220,6 +3220,38 @@ union bpf_attr { * calculation. * Return * Requested value, or 0, if flags are not recognized. + * + * int bpf_csum_level(struct sk_buff *skb, u64 level) + * Description + * Change the skbs checksum level by one layer up or down, or + * reset it entirely to none in order to have the stack perform + * checksum validation. The level is applicable to the following + * protocols: TCP, UDP, GRE, SCTP, FCOE. For example, a decap of + * | ETH | IP | UDP | GUE | IP | TCP | into | ETH | IP | TCP | + * through **bpf_skb_adjust_room**\ () helper with passing in + * **BPF_F_ADJ_ROOM_NO_CSUM_RESET** flag would require one call + * to **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_DEC** since + * the UDP header is removed. Similarly, an encap of the latter + * into the former could be accompanied by a helper call to + * **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_INC** if the + * skb is still intended to be processed in higher layers of the + * stack instead of just egressing at tc. + * + * There are three supported level settings at this time: + * + * * **BPF_CSUM_LEVEL_INC**: Increases skb->csum_level for skbs + * with CHECKSUM_UNNECESSARY. + * * **BPF_CSUM_LEVEL_DEC**: Decreases skb->csum_level for skbs + * with CHECKSUM_UNNECESSARY. + * * **BPF_CSUM_LEVEL_RESET**: Resets skb->csum_level to 0 and + * sets CHECKSUM_NONE to force checksum validation by the stack. + * * **BPF_CSUM_LEVEL_QUERY**: No-op, returns the current + * skb->csum_level. + * Return + * 0 on success, or a negative error in case of failure. In the + * case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level + * is returned or the error code -EACCES in case the skb is not + * subject to CHECKSUM_UNNECESSARY. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3356,7 +3388,8 @@ union bpf_attr { FN(ringbuf_reserve), \ FN(ringbuf_submit), \ FN(ringbuf_discard), \ - FN(ringbuf_query), + FN(ringbuf_query), \ + FN(csum_level), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3433,6 +3466,14 @@ enum { BPF_F_CURRENT_NETNS = (-1L), }; +/* BPF_FUNC_csum_level level values. */ +enum { + BPF_CSUM_LEVEL_QUERY, + BPF_CSUM_LEVEL_INC, + BPF_CSUM_LEVEL_DEC, + BPF_CSUM_LEVEL_RESET, +}; + /* BPF_FUNC_skb_adjust_room flags. */ enum { BPF_F_ADJ_ROOM_FIXED_GSO = (1ULL << 0), diff --git a/net/core/filter.c b/net/core/filter.c index 278dcc0af961..d01a244b5087 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2015,6 +2015,40 @@ static const struct bpf_func_proto bpf_csum_update_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_2(bpf_csum_level, struct sk_buff *, skb, u64, level) +{ + /* The interface is to be used in combination with bpf_skb_adjust_room() + * for encap/decap of packet headers when BPF_F_ADJ_ROOM_NO_CSUM_RESET + * is passed as flags, for example. + */ + switch (level) { + case BPF_CSUM_LEVEL_INC: + __skb_incr_checksum_unnecessary(skb); + break; + case BPF_CSUM_LEVEL_DEC: + __skb_decr_checksum_unnecessary(skb); + break; + case BPF_CSUM_LEVEL_RESET: + __skb_reset_checksum_unnecessary(skb); + break; + case BPF_CSUM_LEVEL_QUERY: + return skb->ip_summed == CHECKSUM_UNNECESSARY ? + skb->csum_level : -EACCES; + default: + return -EINVAL; + } + + return 0; +} + +static const struct bpf_func_proto bpf_csum_level_proto = { + .func = bpf_csum_level, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb) { return dev_forward_skb(dev, skb); @@ -6280,6 +6314,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_csum_diff_proto; case BPF_FUNC_csum_update: return &bpf_csum_update_proto; + case BPF_FUNC_csum_level: + return &bpf_csum_level_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: @@ -6613,6 +6649,8 @@ lwt_xmit_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skb_store_bytes_proto; case BPF_FUNC_csum_update: return &bpf_csum_update_proto; + case BPF_FUNC_csum_level: + return &bpf_csum_level_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3ba2bbbed80c..c65b374a5090 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3220,6 +3220,38 @@ union bpf_attr { * calculation. * Return * Requested value, or 0, if flags are not recognized. + * + * int bpf_csum_level(struct sk_buff *skb, u64 level) + * Description + * Change the skbs checksum level by one layer up or down, or + * reset it entirely to none in order to have the stack perform + * checksum validation. The level is applicable to the following + * protocols: TCP, UDP, GRE, SCTP, FCOE. For example, a decap of + * | ETH | IP | UDP | GUE | IP | TCP | into | ETH | IP | TCP | + * through **bpf_skb_adjust_room**\ () helper with passing in + * **BPF_F_ADJ_ROOM_NO_CSUM_RESET** flag would require one call + * to **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_DEC** since + * the UDP header is removed. Similarly, an encap of the latter + * into the former could be accompanied by a helper call to + * **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_INC** if the + * skb is still intended to be processed in higher layers of the + * stack instead of just egressing at tc. + * + * There are three supported level settings at this time: + * + * * **BPF_CSUM_LEVEL_INC**: Increases skb->csum_level for skbs + * with CHECKSUM_UNNECESSARY. + * * **BPF_CSUM_LEVEL_DEC**: Decreases skb->csum_level for skbs + * with CHECKSUM_UNNECESSARY. + * * **BPF_CSUM_LEVEL_RESET**: Resets skb->csum_level to 0 and + * sets CHECKSUM_NONE to force checksum validation by the stack. + * * **BPF_CSUM_LEVEL_QUERY**: No-op, returns the current + * skb->csum_level. + * Return + * 0 on success, or a negative error in case of failure. In the + * case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level + * is returned or the error code -EACCES in case the skb is not + * subject to CHECKSUM_UNNECESSARY. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3356,7 +3388,8 @@ union bpf_attr { FN(ringbuf_reserve), \ FN(ringbuf_submit), \ FN(ringbuf_discard), \ - FN(ringbuf_query), + FN(ringbuf_query), \ + FN(csum_level), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3433,6 +3466,14 @@ enum { BPF_F_CURRENT_NETNS = (-1L), }; +/* BPF_FUNC_csum_level level values. */ +enum { + BPF_CSUM_LEVEL_QUERY, + BPF_CSUM_LEVEL_INC, + BPF_CSUM_LEVEL_DEC, + BPF_CSUM_LEVEL_RESET, +}; + /* BPF_FUNC_skb_adjust_room flags. */ enum { BPF_F_ADJ_ROOM_FIXED_GSO = (1ULL << 0), -- cgit v1.2.3 From 56f2e3b7d819f4fa44857ba81aa6870f18714ea0 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Tue, 2 Jun 2020 10:17:28 +0100 Subject: capabilities: add description for CAP_SETFCAP Document the purpose of CAP_SETFCAP. For some reason this capability had no description while the others did. Signed-off-by: Stefan Hajnoczi Signed-off-by: James Morris --- include/uapi/linux/capability.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index 240fdb9a60f6..877972fdfda3 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -331,6 +331,8 @@ struct vfs_ns_cap_data { #define CAP_AUDIT_CONTROL 30 +/* Set or remove capabilities on files */ + #define CAP_SETFCAP 31 /* Override MAC access. -- cgit v1.2.3 From d8cac29b1d52204e6632d2887eff766acd02b9aa Mon Sep 17 00:00:00 2001 From: Farhan Ali Date: Tue, 5 May 2020 14:27:43 +0200 Subject: vfio-ccw: Introduce a new CRW region This region provides a mechanism to pass a Channel Report Word that affect vfio-ccw devices, and needs to be passed to the guest for its awareness and/or processing. The base driver (see crw_collect_info()) provides space for two CRWs, as a subchannel event may have two CRWs chained together (one for the ssid, one for the subchannel). As vfio-ccw will deal with everything at the subchannel level, provide space for a single CRW to be transferred in one shot. Signed-off-by: Farhan Ali Signed-off-by: Eric Farman Reviewed-by: Cornelia Huck Message-Id: <20200505122745.53208-7-farman@linux.ibm.com> [CH: added padding to ccw_crw_region] Signed-off-by: Cornelia Huck --- Documentation/s390/vfio-ccw.rst | 20 ++++++++++++++ drivers/s390/cio/vfio_ccw_chp.c | 55 +++++++++++++++++++++++++++++++++++++ drivers/s390/cio/vfio_ccw_drv.c | 20 ++++++++++++++ drivers/s390/cio/vfio_ccw_ops.c | 8 ++++++ drivers/s390/cio/vfio_ccw_private.h | 4 +++ include/uapi/linux/vfio.h | 2 ++ include/uapi/linux/vfio_ccw.h | 9 ++++++ 7 files changed, 118 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/s390/vfio-ccw.rst b/Documentation/s390/vfio-ccw.rst index 32310df525ba..8aad08a8b8a5 100644 --- a/Documentation/s390/vfio-ccw.rst +++ b/Documentation/s390/vfio-ccw.rst @@ -298,6 +298,26 @@ This region is exposed via region type VFIO_REGION_SUBTYPE_CCW_SCHIB. Reading this region triggers a STORE SUBCHANNEL to be issued to the associated hardware. +vfio-ccw crw region +--------------------- + +The vfio-ccw crw region is used to return Channel Report Word (CRW) +data to userspace:: + + struct ccw_crw_region { + __u32 crw; + __u32 pad; + } __packed; + +This region is exposed via region type VFIO_REGION_SUBTYPE_CCW_CRW. + +Reading this region returns a CRW if one that is relevant for this +subchannel (e.g. one reporting changes in channel path state) is +pending, or all zeroes if not. If multiple CRWs are pending (including +possibly chained CRWs), reading this region again will return the next +one, until no more CRWs are pending and zeroes are returned. This is +similar to how STORE CHANNEL REPORT WORD works. + vfio-ccw operation details -------------------------- diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c index 18f3b3e873a9..37ea344a4d72 100644 --- a/drivers/s390/cio/vfio_ccw_chp.c +++ b/drivers/s390/cio/vfio_ccw_chp.c @@ -74,3 +74,58 @@ int vfio_ccw_register_schib_dev_regions(struct vfio_ccw_private *private) VFIO_REGION_INFO_FLAG_READ, private->schib_region); } + +static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private, + char __user *buf, size_t count, + loff_t *ppos) +{ + unsigned int i = VFIO_CCW_OFFSET_TO_INDEX(*ppos) - VFIO_CCW_NUM_REGIONS; + loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK; + struct ccw_crw_region *region; + int ret; + + if (pos + count > sizeof(*region)) + return -EINVAL; + + mutex_lock(&private->io_mutex); + region = private->region[i].data; + + if (copy_to_user(buf, (void *)region + pos, count)) + ret = -EFAULT; + else + ret = count; + + region->crw = 0; + + mutex_unlock(&private->io_mutex); + return ret; +} + +static ssize_t vfio_ccw_crw_region_write(struct vfio_ccw_private *private, + const char __user *buf, size_t count, + loff_t *ppos) +{ + return -EINVAL; +} + +static void vfio_ccw_crw_region_release(struct vfio_ccw_private *private, + struct vfio_ccw_region *region) +{ + +} + +const struct vfio_ccw_regops vfio_ccw_crw_region_ops = { + .read = vfio_ccw_crw_region_read, + .write = vfio_ccw_crw_region_write, + .release = vfio_ccw_crw_region_release, +}; + +int vfio_ccw_register_crw_dev_regions(struct vfio_ccw_private *private) +{ + return vfio_ccw_register_dev_region(private, + VFIO_REGION_SUBTYPE_CCW_CRW, + &vfio_ccw_crw_region_ops, + sizeof(struct ccw_crw_region), + VFIO_REGION_INFO_FLAG_READ, + private->crw_region); +} diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index 7aeff42f370d..e4deae6fd525 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -28,6 +28,7 @@ struct workqueue_struct *vfio_ccw_work_q; static struct kmem_cache *vfio_ccw_io_region; static struct kmem_cache *vfio_ccw_cmd_region; static struct kmem_cache *vfio_ccw_schib_region; +static struct kmem_cache *vfio_ccw_crw_region; debug_info_t *vfio_ccw_debug_msg_id; debug_info_t *vfio_ccw_debug_trace_id; @@ -120,6 +121,8 @@ static void vfio_ccw_sch_irq(struct subchannel *sch) static void vfio_ccw_free_regions(struct vfio_ccw_private *private) { + if (private->crw_region) + kmem_cache_free(vfio_ccw_crw_region, private->crw_region); if (private->schib_region) kmem_cache_free(vfio_ccw_schib_region, private->schib_region); if (private->cmd_region) @@ -165,6 +168,12 @@ static int vfio_ccw_sch_probe(struct subchannel *sch) if (!private->schib_region) goto out_free; + private->crw_region = kmem_cache_zalloc(vfio_ccw_crw_region, + GFP_KERNEL | GFP_DMA); + + if (!private->crw_region) + goto out_free; + private->sch = sch; dev_set_drvdata(&sch->dev, private); mutex_init(&private->io_mutex); @@ -366,6 +375,7 @@ static void vfio_ccw_debug_exit(void) static void vfio_ccw_destroy_regions(void) { + kmem_cache_destroy(vfio_ccw_crw_region); kmem_cache_destroy(vfio_ccw_schib_region); kmem_cache_destroy(vfio_ccw_cmd_region); kmem_cache_destroy(vfio_ccw_io_region); @@ -413,6 +423,16 @@ static int __init vfio_ccw_sch_init(void) goto out_err; } + vfio_ccw_crw_region = kmem_cache_create_usercopy("vfio_ccw_crw_region", + sizeof(struct ccw_crw_region), 0, + SLAB_ACCOUNT, 0, + sizeof(struct ccw_crw_region), NULL); + + if (!vfio_ccw_crw_region) { + ret = -ENOMEM; + goto out_err; + } + isc_register(VFIO_CCW_ISC); ret = css_driver_register(&vfio_ccw_sch_driver); if (ret) { diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c index c3a74ab7bb86..8b3ed5b45277 100644 --- a/drivers/s390/cio/vfio_ccw_ops.c +++ b/drivers/s390/cio/vfio_ccw_ops.c @@ -178,6 +178,10 @@ static int vfio_ccw_mdev_open(struct mdev_device *mdev) if (ret) goto out_unregister; + ret = vfio_ccw_register_crw_dev_regions(private); + if (ret) + goto out_unregister; + return ret; out_unregister: @@ -389,6 +393,7 @@ static int vfio_ccw_mdev_get_irq_info(struct vfio_irq_info *info) { switch (info->index) { case VFIO_CCW_IO_IRQ_INDEX: + case VFIO_CCW_CRW_IRQ_INDEX: info->count = 1; info->flags = VFIO_IRQ_INFO_EVENTFD; break; @@ -416,6 +421,9 @@ static int vfio_ccw_mdev_set_irqs(struct mdev_device *mdev, case VFIO_CCW_IO_IRQ_INDEX: ctx = &private->io_trigger; break; + case VFIO_CCW_CRW_IRQ_INDEX: + ctx = &private->crw_trigger; + break; default: return -EINVAL; } diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h index d6601a8adf13..97131b4df0b9 100644 --- a/drivers/s390/cio/vfio_ccw_private.h +++ b/drivers/s390/cio/vfio_ccw_private.h @@ -57,6 +57,7 @@ void vfio_ccw_unregister_dev_regions(struct vfio_ccw_private *private); int vfio_ccw_register_async_dev_regions(struct vfio_ccw_private *private); int vfio_ccw_register_schib_dev_regions(struct vfio_ccw_private *private); +int vfio_ccw_register_crw_dev_regions(struct vfio_ccw_private *private); /** * struct vfio_ccw_private @@ -71,6 +72,7 @@ int vfio_ccw_register_schib_dev_regions(struct vfio_ccw_private *private); * @region: additional regions for other subchannel operations * @cmd_region: MMIO region for asynchronous I/O commands other than START * @schib_region: MMIO region for SCHIB information + * @crw_region: MMIO region for getting channel report words * @num_regions: number of additional regions * @cp: channel program for the current I/O operation * @irb: irb info received from interrupt @@ -90,6 +92,7 @@ struct vfio_ccw_private { struct vfio_ccw_region *region; struct ccw_cmd_region *cmd_region; struct ccw_schib_region *schib_region; + struct ccw_crw_region *crw_region; int num_regions; struct channel_program cp; @@ -97,6 +100,7 @@ struct vfio_ccw_private { union scsw scsw; struct eventfd_ctx *io_trigger; + struct eventfd_ctx *crw_trigger; struct work_struct io_work; } __aligned(8); diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 7a1abbd889bd..907758cf6d60 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -379,6 +379,7 @@ struct vfio_region_gfx_edid { /* sub-types for VFIO_REGION_TYPE_CCW */ #define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD (1) #define VFIO_REGION_SUBTYPE_CCW_SCHIB (2) +#define VFIO_REGION_SUBTYPE_CCW_CRW (3) /* * The MSIX mappable capability informs that MSIX data of a BAR can be mmapped @@ -578,6 +579,7 @@ enum { enum { VFIO_CCW_IO_IRQ_INDEX, + VFIO_CCW_CRW_IRQ_INDEX, VFIO_CCW_NUM_IRQS }; diff --git a/include/uapi/linux/vfio_ccw.h b/include/uapi/linux/vfio_ccw.h index 758bf214898d..aa04f3aa6db0 100644 --- a/include/uapi/linux/vfio_ccw.h +++ b/include/uapi/linux/vfio_ccw.h @@ -44,4 +44,13 @@ struct ccw_schib_region { __u8 schib_area[SCHIB_AREA_SIZE]; } __packed; +/* + * Used for returning a Channel Report Word to userspace. + * Note: this is controlled by a capability + */ +struct ccw_crw_region { + __u32 crw; + __u32 pad; +} __packed; + #endif -- cgit v1.2.3 From 10c5db286452b8c60e8f58e9a4c1cbc5a91e4e5b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 May 2020 09:30:11 +0200 Subject: fs: move the fiemap definitions out of fs.h No need to pull the fiemap definitions into almost every file in the kernel build. Signed-off-by: Christoph Hellwig Reviewed-by: Ritesh Harjani Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20200523073016.2944131-5-hch@lst.de Signed-off-by: Theodore Ts'o --- fs/bad_inode.c | 1 + fs/btrfs/extent_io.h | 1 + fs/cifs/inode.c | 1 + fs/cifs/smb2ops.c | 1 + fs/ext2/inode.c | 1 + fs/ext4/ext4.h | 1 + fs/f2fs/data.c | 1 + fs/f2fs/inline.c | 1 + fs/gfs2/inode.c | 1 + fs/hpfs/file.c | 1 + fs/ioctl.c | 1 + fs/iomap/fiemap.c | 1 + fs/nilfs2/inode.c | 1 + fs/overlayfs/inode.c | 1 + fs/xfs/xfs_iops.c | 1 + include/linux/fiemap.h | 24 ++++++++++++++++++++++++ include/linux/fs.h | 19 +------------------ include/uapi/linux/fiemap.h | 6 +++--- 18 files changed, 43 insertions(+), 21 deletions(-) create mode 100644 include/linux/fiemap.h (limited to 'include/uapi/linux') diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 8035d2a44561..54f0ce444272 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -15,6 +15,7 @@ #include #include #include +#include static int bad_file_open(struct inode *inode, struct file *filp) { diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 2ed65bd0760e..817698bc0669 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -5,6 +5,7 @@ #include #include +#include #include "ulist.h" /* diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 390d2b15ef6e..3f276eb8ca68 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include "cifsfs.h" diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index f829f4165d38..09047f1ddfb6 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "cifsfs.h" #include "cifsglob.h" #include "smb2pdu.h" diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index c885cf7d724b..0f12a0e8a8d9 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -36,6 +36,7 @@ #include #include #include +#include #include "ext2.h" #include "acl.h" #include "xattr.h" diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1eb07ca91fca..9e5c332a2b94 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -36,6 +36,7 @@ #include #include #include +#include #ifdef __KERNEL__ #include #endif diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index cdf2f626bea7..25abbbb65ba0 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -19,6 +19,7 @@ #include #include #include +#include #include "f2fs.h" #include "node.h" diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 4167e5408151..9686ffea177e 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -8,6 +8,7 @@ #include #include +#include #include "f2fs.h" #include "node.h" diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 70b2d3a1e866..4842f313a808 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include "gfs2.h" diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index b36abf9cb345..62959a8e43ad 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -9,6 +9,7 @@ #include "hpfs_fn.h" #include +#include #define BLOCKS(size) (((size) + 511) >> 9) diff --git a/fs/ioctl.c b/fs/ioctl.c index 8fe5131b1dee..3f300cc07dee 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -18,6 +18,7 @@ #include #include #include +#include #include "internal.h" diff --git a/fs/iomap/fiemap.c b/fs/iomap/fiemap.c index d55e8f491a5e..0a807bbb2b4a 100644 --- a/fs/iomap/fiemap.c +++ b/fs/iomap/fiemap.c @@ -6,6 +6,7 @@ #include #include #include +#include struct fiemap_ctx { struct fiemap_extent_info *fi; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 671085512e0f..6e1aca38931f 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "nilfs.h" #include "btnode.h" #include "segment.h" diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index b0d42ece4d7c..b5fec3410556 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "overlayfs.h" diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index f7a99b3bbcf7..44c353998ac5 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -25,6 +25,7 @@ #include #include #include +#include /* * Directories have different lock order w.r.t. mmap_sem compared to regular diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h new file mode 100644 index 000000000000..240d4f7d9116 --- /dev/null +++ b/include/linux/fiemap.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_FIEMAP_H +#define _LINUX_FIEMAP_H 1 + +#include +#include + +struct fiemap_extent_info { + unsigned int fi_flags; /* Flags as passed from user */ + unsigned int fi_extents_mapped; /* Number of mapped extents */ + unsigned int fi_extents_max; /* Size of fiemap_extent array */ + struct fiemap_extent __user *fi_extents_start; /* Start of + fiemap_extent array */ +}; + +int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, + u64 phys, u64 len, u32 flags); +int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); + +int generic_block_fiemap(struct inode *inode, + struct fiemap_extent_info *fieinfo, u64 start, u64 len, + get_block_t *get_block); + +#endif /* _LINUX_FIEMAP_H 1 */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 3104c6f7527b..09bcd329c062 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -24,7 +24,6 @@ #include #include #include -#include #include #include #include @@ -48,6 +47,7 @@ struct backing_dev_info; struct bdi_writeback; struct bio; struct export_operations; +struct fiemap_extent_info; struct hd_geometry; struct iovec; struct kiocb; @@ -1745,19 +1745,6 @@ extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, extern void inode_init_owner(struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); -/* - * VFS FS_IOC_FIEMAP helper definitions. - */ -struct fiemap_extent_info { - unsigned int fi_flags; /* Flags as passed from user */ - unsigned int fi_extents_mapped; /* Number of mapped extents */ - unsigned int fi_extents_max; /* Size of fiemap_extent array */ - struct fiemap_extent __user *fi_extents_start; /* Start of - fiemap_extent array */ -}; -int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, - u64 phys, u64 len, u32 flags); -int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); /* * This is the "filldir" function type, used by readdir() to let @@ -3299,10 +3286,6 @@ static inline int vfs_fstat(int fd, struct kstat *stat) extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); -extern int generic_block_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, u64 start, - u64 len, get_block_t *get_block); - extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); diff --git a/include/uapi/linux/fiemap.h b/include/uapi/linux/fiemap.h index 7a900b2377b6..24ca0c00cae3 100644 --- a/include/uapi/linux/fiemap.h +++ b/include/uapi/linux/fiemap.h @@ -9,8 +9,8 @@ * Andreas Dilger */ -#ifndef _LINUX_FIEMAP_H -#define _LINUX_FIEMAP_H +#ifndef _UAPI_LINUX_FIEMAP_H +#define _UAPI_LINUX_FIEMAP_H #include @@ -67,4 +67,4 @@ struct fiemap { #define FIEMAP_EXTENT_SHARED 0x00002000 /* Space shared with other * files. */ -#endif /* _LINUX_FIEMAP_H */ +#endif /* _UAPI_LINUX_FIEMAP_H */ -- cgit v1.2.3 From 5f1f79bbc9e26fa9412fa9522f957bb8f030c442 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 7 May 2020 16:01:25 +0200 Subject: virtio-mem: Paravirtualized memory hotplug Each virtio-mem device owns exactly one memory region. It is responsible for adding/removing memory from that memory region on request. When the device driver starts up, the requested amount of memory is queried and then plugged to Linux. On request, further memory can be plugged or unplugged. This patch only implements the plugging part. On x86-64, memory can currently be plugged in 4MB ("subblock") granularity. When required, a new memory block will be added (e.g., usually 128MB on x86-64) in order to plug more subblocks. Only x86-64 was tested for now. The online_page callback is used to keep unplugged subblocks offline when onlining memory - similar to the Hyper-V balloon driver. Unplugged pages are marked PG_offline, to tell dump tools (e.g., makedumpfile) to skip them. User space is usually responsible for onlining the added memory. The memory hotplug notifier is used to synchronize virtio-mem activity against memory onlining/offlining. Each virtio-mem device can belong to a NUMA node, which allows us to easily add/remove small chunks of memory to/from a specific NUMA node by using multiple virtio-mem devices. Something that works even when the guest has no idea about the NUMA topology. One way to view virtio-mem is as a "resizable DIMM" or a DIMM with many "sub-DIMMS". This patch directly introduces the basic infrastructure to implement memory unplug. Especially the memory block states and subblock bitmaps will be heavily used there. Notes: - In case memory is to be onlined by user space, we limit the amount of offline memory blocks, to not run out of memory. This is esp. an issue if memory is added faster than it is getting onlined. - Suspend/Hibernate is not supported due to the way virtio-mem devices behave. Limited support might be possible in the future. - Reloading the device driver is not supported. Reviewed-by: Pankaj Gupta Tested-by: Pankaj Gupta Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Oscar Salvador Cc: Michal Hocko Cc: Igor Mammedov Cc: Dave Young Cc: Andrew Morton Cc: Dan Williams Cc: Pavel Tatashin Cc: Stefan Hajnoczi Cc: Vlastimil Babka Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: linux-acpi@vger.kernel.org Signed-off-by: David Hildenbrand Link: https://lore.kernel.org/r/20200507140139.17083-2-david@redhat.com Signed-off-by: Michael S. Tsirkin --- drivers/virtio/Kconfig | 16 + drivers/virtio/Makefile | 1 + drivers/virtio/virtio_mem.c | 1533 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/virtio_ids.h | 1 + include/uapi/linux/virtio_mem.h | 200 +++++ 5 files changed, 1751 insertions(+) create mode 100644 drivers/virtio/virtio_mem.c create mode 100644 include/uapi/linux/virtio_mem.h (limited to 'include/uapi/linux') diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 69a32dfc318a..d6dde7d2cf76 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -78,6 +78,22 @@ config VIRTIO_BALLOON If unsure, say M. +config VIRTIO_MEM + tristate "Virtio mem driver" + default m + depends on X86_64 + depends on VIRTIO + depends on MEMORY_HOTPLUG_SPARSE + depends on MEMORY_HOTREMOVE + help + This driver provides access to virtio-mem paravirtualized memory + devices, allowing to hotplug and hotunplug memory. + + This driver was only tested under x86-64, but should theoretically + work on all architectures that support memory hotplug and hotremove. + + If unsure, say M. + config VIRTIO_INPUT tristate "Virtio input driver" depends on VIRTIO diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile index 29a1386ecc03..4d993791f2d7 100644 --- a/drivers/virtio/Makefile +++ b/drivers/virtio/Makefile @@ -7,3 +7,4 @@ virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o obj-$(CONFIG_VIRTIO_VDPA) += virtio_vdpa.o +obj-$(CONFIG_VIRTIO_MEM) += virtio_mem.o diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c new file mode 100644 index 000000000000..5d1dcaa6fc42 --- /dev/null +++ b/drivers/virtio/virtio_mem.c @@ -0,0 +1,1533 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Virtio-mem device driver. + * + * Copyright Red Hat, Inc. 2020 + * + * Author(s): David Hildenbrand + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +enum virtio_mem_mb_state { + /* Unplugged, not added to Linux. Can be reused later. */ + VIRTIO_MEM_MB_STATE_UNUSED = 0, + /* (Partially) plugged, not added to Linux. Error on add_memory(). */ + VIRTIO_MEM_MB_STATE_PLUGGED, + /* Fully plugged, fully added to Linux, offline. */ + VIRTIO_MEM_MB_STATE_OFFLINE, + /* Partially plugged, fully added to Linux, offline. */ + VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL, + /* Fully plugged, fully added to Linux, online (!ZONE_MOVABLE). */ + VIRTIO_MEM_MB_STATE_ONLINE, + /* Partially plugged, fully added to Linux, online (!ZONE_MOVABLE). */ + VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL, + /* + * Fully plugged, fully added to Linux, online (ZONE_MOVABLE). + * We are not allowed to allocate (unplug) parts of this block that + * are not movable (similar to gigantic pages). We will never allow + * to online OFFLINE_PARTIAL to ZONE_MOVABLE (as they would contain + * unmovable parts). + */ + VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE, + VIRTIO_MEM_MB_STATE_COUNT +}; + +struct virtio_mem { + struct virtio_device *vdev; + + /* We might first have to unplug all memory when starting up. */ + bool unplug_all_required; + + /* Workqueue that processes the plug/unplug requests. */ + struct work_struct wq; + atomic_t config_changed; + + /* Virtqueue for guest->host requests. */ + struct virtqueue *vq; + + /* Wait for a host response to a guest request. */ + wait_queue_head_t host_resp; + + /* Space for one guest request and the host response. */ + struct virtio_mem_req req; + struct virtio_mem_resp resp; + + /* The current size of the device. */ + uint64_t plugged_size; + /* The requested size of the device. */ + uint64_t requested_size; + + /* The device block size (for communicating with the device). */ + uint32_t device_block_size; + /* Physical start address of the memory region. */ + uint64_t addr; + /* Maximum region size in bytes. */ + uint64_t region_size; + + /* The subblock size. */ + uint32_t subblock_size; + /* The number of subblocks per memory block. */ + uint32_t nb_sb_per_mb; + + /* Id of the first memory block of this device. */ + unsigned long first_mb_id; + /* Id of the last memory block of this device. */ + unsigned long last_mb_id; + /* Id of the last usable memory block of this device. */ + unsigned long last_usable_mb_id; + /* Id of the next memory bock to prepare when needed. */ + unsigned long next_mb_id; + + /* Summary of all memory block states. */ + unsigned long nb_mb_state[VIRTIO_MEM_MB_STATE_COUNT]; +#define VIRTIO_MEM_NB_OFFLINE_THRESHOLD 10 + + /* + * One byte state per memory block. + * + * Allocated via vmalloc(). When preparing new blocks, resized + * (alloc+copy+free) when needed (crossing pages with the next mb). + * (when crossing pages). + * + * With 128MB memory blocks, we have states for 512GB of memory in one + * page. + */ + uint8_t *mb_state; + + /* + * $nb_sb_per_mb bit per memory block. Handled similar to mb_state. + * + * With 4MB subblocks, we manage 128GB of memory in one page. + */ + unsigned long *sb_bitmap; + + /* + * Mutex that protects the nb_mb_state, mb_state, and sb_bitmap. + * + * When this lock is held the pointers can't change, ONLINE and + * OFFLINE blocks can't change the state and no subblocks will get + * plugged. + */ + struct mutex hotplug_mutex; + bool hotplug_active; + + /* An error occurred we cannot handle - stop processing requests. */ + bool broken; + + /* The driver is being removed. */ + spinlock_t removal_lock; + bool removing; + + /* Timer for retrying to plug/unplug memory. */ + struct hrtimer retry_timer; +#define VIRTIO_MEM_RETRY_TIMER_MS 30000 + + /* Memory notifier (online/offline events). */ + struct notifier_block memory_notifier; + + /* Next device in the list of virtio-mem devices. */ + struct list_head next; +}; + +/* + * We have to share a single online_page callback among all virtio-mem + * devices. We use RCU to iterate the list in the callback. + */ +static DEFINE_MUTEX(virtio_mem_mutex); +static LIST_HEAD(virtio_mem_devices); + +static void virtio_mem_online_page_cb(struct page *page, unsigned int order); + +/* + * Register a virtio-mem device so it will be considered for the online_page + * callback. + */ +static int register_virtio_mem_device(struct virtio_mem *vm) +{ + int rc = 0; + + /* First device registers the callback. */ + mutex_lock(&virtio_mem_mutex); + if (list_empty(&virtio_mem_devices)) + rc = set_online_page_callback(&virtio_mem_online_page_cb); + if (!rc) + list_add_rcu(&vm->next, &virtio_mem_devices); + mutex_unlock(&virtio_mem_mutex); + + return rc; +} + +/* + * Unregister a virtio-mem device so it will no longer be considered for the + * online_page callback. + */ +static void unregister_virtio_mem_device(struct virtio_mem *vm) +{ + /* Last device unregisters the callback. */ + mutex_lock(&virtio_mem_mutex); + list_del_rcu(&vm->next); + if (list_empty(&virtio_mem_devices)) + restore_online_page_callback(&virtio_mem_online_page_cb); + mutex_unlock(&virtio_mem_mutex); + + synchronize_rcu(); +} + +/* + * Calculate the memory block id of a given address. + */ +static unsigned long virtio_mem_phys_to_mb_id(unsigned long addr) +{ + return addr / memory_block_size_bytes(); +} + +/* + * Calculate the physical start address of a given memory block id. + */ +static unsigned long virtio_mem_mb_id_to_phys(unsigned long mb_id) +{ + return mb_id * memory_block_size_bytes(); +} + +/* + * Calculate the subblock id of a given address. + */ +static unsigned long virtio_mem_phys_to_sb_id(struct virtio_mem *vm, + unsigned long addr) +{ + const unsigned long mb_id = virtio_mem_phys_to_mb_id(addr); + const unsigned long mb_addr = virtio_mem_mb_id_to_phys(mb_id); + + return (addr - mb_addr) / vm->subblock_size; +} + +/* + * Set the state of a memory block, taking care of the state counter. + */ +static void virtio_mem_mb_set_state(struct virtio_mem *vm, unsigned long mb_id, + enum virtio_mem_mb_state state) +{ + const unsigned long idx = mb_id - vm->first_mb_id; + enum virtio_mem_mb_state old_state; + + old_state = vm->mb_state[idx]; + vm->mb_state[idx] = state; + + BUG_ON(vm->nb_mb_state[old_state] == 0); + vm->nb_mb_state[old_state]--; + vm->nb_mb_state[state]++; +} + +/* + * Get the state of a memory block. + */ +static enum virtio_mem_mb_state virtio_mem_mb_get_state(struct virtio_mem *vm, + unsigned long mb_id) +{ + const unsigned long idx = mb_id - vm->first_mb_id; + + return vm->mb_state[idx]; +} + +/* + * Prepare the state array for the next memory block. + */ +static int virtio_mem_mb_state_prepare_next_mb(struct virtio_mem *vm) +{ + unsigned long old_bytes = vm->next_mb_id - vm->first_mb_id + 1; + unsigned long new_bytes = vm->next_mb_id - vm->first_mb_id + 2; + int old_pages = PFN_UP(old_bytes); + int new_pages = PFN_UP(new_bytes); + uint8_t *new_mb_state; + + if (vm->mb_state && old_pages == new_pages) + return 0; + + new_mb_state = vzalloc(new_pages * PAGE_SIZE); + if (!new_mb_state) + return -ENOMEM; + + mutex_lock(&vm->hotplug_mutex); + if (vm->mb_state) + memcpy(new_mb_state, vm->mb_state, old_pages * PAGE_SIZE); + vfree(vm->mb_state); + vm->mb_state = new_mb_state; + mutex_unlock(&vm->hotplug_mutex); + + return 0; +} + +#define virtio_mem_for_each_mb_state(_vm, _mb_id, _state) \ + for (_mb_id = _vm->first_mb_id; \ + _mb_id < _vm->next_mb_id && _vm->nb_mb_state[_state]; \ + _mb_id++) \ + if (virtio_mem_mb_get_state(_vm, _mb_id) == _state) + +/* + * Mark all selected subblocks plugged. + * + * Will not modify the state of the memory block. + */ +static void virtio_mem_mb_set_sb_plugged(struct virtio_mem *vm, + unsigned long mb_id, int sb_id, + int count) +{ + const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id; + + __bitmap_set(vm->sb_bitmap, bit, count); +} + +/* + * Mark all selected subblocks unplugged. + * + * Will not modify the state of the memory block. + */ +static void virtio_mem_mb_set_sb_unplugged(struct virtio_mem *vm, + unsigned long mb_id, int sb_id, + int count) +{ + const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id; + + __bitmap_clear(vm->sb_bitmap, bit, count); +} + +/* + * Test if all selected subblocks are plugged. + */ +static bool virtio_mem_mb_test_sb_plugged(struct virtio_mem *vm, + unsigned long mb_id, int sb_id, + int count) +{ + const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id; + + if (count == 1) + return test_bit(bit, vm->sb_bitmap); + + /* TODO: Helper similar to bitmap_set() */ + return find_next_zero_bit(vm->sb_bitmap, bit + count, bit) >= + bit + count; +} + +/* + * Find the first plugged subblock. Returns vm->nb_sb_per_mb in case there is + * none. + */ +static int virtio_mem_mb_first_plugged_sb(struct virtio_mem *vm, + unsigned long mb_id) +{ + const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb; + + return find_next_bit(vm->sb_bitmap, bit + vm->nb_sb_per_mb, bit) - bit; +} + +/* + * Find the first unplugged subblock. Returns vm->nb_sb_per_mb in case there is + * none. + */ +static int virtio_mem_mb_first_unplugged_sb(struct virtio_mem *vm, + unsigned long mb_id) +{ + const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb; + + return find_next_zero_bit(vm->sb_bitmap, bit + vm->nb_sb_per_mb, bit) - + bit; +} + +/* + * Prepare the subblock bitmap for the next memory block. + */ +static int virtio_mem_sb_bitmap_prepare_next_mb(struct virtio_mem *vm) +{ + const unsigned long old_nb_mb = vm->next_mb_id - vm->first_mb_id; + const unsigned long old_nb_bits = old_nb_mb * vm->nb_sb_per_mb; + const unsigned long new_nb_bits = (old_nb_mb + 1) * vm->nb_sb_per_mb; + int old_pages = PFN_UP(BITS_TO_LONGS(old_nb_bits) * sizeof(long)); + int new_pages = PFN_UP(BITS_TO_LONGS(new_nb_bits) * sizeof(long)); + unsigned long *new_sb_bitmap, *old_sb_bitmap; + + if (vm->sb_bitmap && old_pages == new_pages) + return 0; + + new_sb_bitmap = vzalloc(new_pages * PAGE_SIZE); + if (!new_sb_bitmap) + return -ENOMEM; + + mutex_lock(&vm->hotplug_mutex); + if (new_sb_bitmap) + memcpy(new_sb_bitmap, vm->sb_bitmap, old_pages * PAGE_SIZE); + + old_sb_bitmap = vm->sb_bitmap; + vm->sb_bitmap = new_sb_bitmap; + mutex_unlock(&vm->hotplug_mutex); + + vfree(old_sb_bitmap); + return 0; +} + +/* + * Try to add a memory block to Linux. This will usually only fail + * if out of memory. + * + * Must not be called with the vm->hotplug_mutex held (possible deadlock with + * onlining code). + * + * Will not modify the state of the memory block. + */ +static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id) +{ + const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id); + int nid = memory_add_physaddr_to_nid(addr); + + dev_dbg(&vm->vdev->dev, "adding memory block: %lu\n", mb_id); + return add_memory(nid, addr, memory_block_size_bytes()); +} + +/* + * Try to remove a memory block from Linux. Will only fail if the memory block + * is not offline. + * + * Must not be called with the vm->hotplug_mutex held (possible deadlock with + * onlining code). + * + * Will not modify the state of the memory block. + */ +static int virtio_mem_mb_remove(struct virtio_mem *vm, unsigned long mb_id) +{ + const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id); + int nid = memory_add_physaddr_to_nid(addr); + + dev_dbg(&vm->vdev->dev, "removing memory block: %lu\n", mb_id); + return remove_memory(nid, addr, memory_block_size_bytes()); +} + +/* + * Trigger the workqueue so the device can perform its magic. + */ +static void virtio_mem_retry(struct virtio_mem *vm) +{ + unsigned long flags; + + spin_lock_irqsave(&vm->removal_lock, flags); + if (!vm->removing) + queue_work(system_freezable_wq, &vm->wq); + spin_unlock_irqrestore(&vm->removal_lock, flags); +} + +/* + * Test if a virtio-mem device overlaps with the given range. Can be called + * from (notifier) callbacks lockless. + */ +static bool virtio_mem_overlaps_range(struct virtio_mem *vm, + unsigned long start, unsigned long size) +{ + unsigned long dev_start = virtio_mem_mb_id_to_phys(vm->first_mb_id); + unsigned long dev_end = virtio_mem_mb_id_to_phys(vm->last_mb_id) + + memory_block_size_bytes(); + + return start < dev_end && dev_start < start + size; +} + +/* + * Test if a virtio-mem device owns a memory block. Can be called from + * (notifier) callbacks lockless. + */ +static bool virtio_mem_owned_mb(struct virtio_mem *vm, unsigned long mb_id) +{ + return mb_id >= vm->first_mb_id && mb_id <= vm->last_mb_id; +} + +static int virtio_mem_notify_going_online(struct virtio_mem *vm, + unsigned long mb_id, + enum zone_type zone) +{ + switch (virtio_mem_mb_get_state(vm, mb_id)) { + case VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL: + /* + * We won't allow to online a partially plugged memory block + * to the MOVABLE zone - it would contain unmovable parts. + */ + if (zone == ZONE_MOVABLE) { + dev_warn_ratelimited(&vm->vdev->dev, + "memory block has holes, MOVABLE not supported\n"); + return NOTIFY_BAD; + } + return NOTIFY_OK; + case VIRTIO_MEM_MB_STATE_OFFLINE: + return NOTIFY_OK; + default: + break; + } + dev_warn_ratelimited(&vm->vdev->dev, + "memory block onlining denied\n"); + return NOTIFY_BAD; +} + +static void virtio_mem_notify_offline(struct virtio_mem *vm, + unsigned long mb_id) +{ + switch (virtio_mem_mb_get_state(vm, mb_id)) { + case VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL: + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL); + break; + case VIRTIO_MEM_MB_STATE_ONLINE: + case VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE: + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE); + break; + default: + BUG(); + break; + } +} + +static void virtio_mem_notify_online(struct virtio_mem *vm, unsigned long mb_id, + enum zone_type zone) +{ + unsigned long nb_offline; + + switch (virtio_mem_mb_get_state(vm, mb_id)) { + case VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL: + BUG_ON(zone == ZONE_MOVABLE); + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL); + break; + case VIRTIO_MEM_MB_STATE_OFFLINE: + if (zone == ZONE_MOVABLE) + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE); + else + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_ONLINE); + break; + default: + BUG(); + break; + } + nb_offline = vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] + + vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL]; + + /* see if we can add new blocks now that we onlined one block */ + if (nb_offline == VIRTIO_MEM_NB_OFFLINE_THRESHOLD - 1) + virtio_mem_retry(vm); +} + +/* + * This callback will either be called synchronously from add_memory() or + * asynchronously (e.g., triggered via user space). We have to be careful + * with locking when calling add_memory(). + */ +static int virtio_mem_memory_notifier_cb(struct notifier_block *nb, + unsigned long action, void *arg) +{ + struct virtio_mem *vm = container_of(nb, struct virtio_mem, + memory_notifier); + struct memory_notify *mhp = arg; + const unsigned long start = PFN_PHYS(mhp->start_pfn); + const unsigned long size = PFN_PHYS(mhp->nr_pages); + const unsigned long mb_id = virtio_mem_phys_to_mb_id(start); + enum zone_type zone; + int rc = NOTIFY_OK; + + if (!virtio_mem_overlaps_range(vm, start, size)) + return NOTIFY_DONE; + + /* + * Memory is onlined/offlined in memory block granularity. We cannot + * cross virtio-mem device boundaries and memory block boundaries. Bail + * out if this ever changes. + */ + if (WARN_ON_ONCE(size != memory_block_size_bytes() || + !IS_ALIGNED(start, memory_block_size_bytes()))) + return NOTIFY_BAD; + + /* + * Avoid circular locking lockdep warnings. We lock the mutex + * e.g., in MEM_GOING_ONLINE and unlock it in MEM_ONLINE. The + * blocking_notifier_call_chain() has it's own lock, which gets unlocked + * between both notifier calls and will bail out. False positive. + */ + lockdep_off(); + + switch (action) { + case MEM_GOING_OFFLINE: + mutex_lock(&vm->hotplug_mutex); + if (vm->removing) { + rc = notifier_from_errno(-EBUSY); + mutex_unlock(&vm->hotplug_mutex); + break; + } + vm->hotplug_active = true; + break; + case MEM_GOING_ONLINE: + mutex_lock(&vm->hotplug_mutex); + if (vm->removing) { + rc = notifier_from_errno(-EBUSY); + mutex_unlock(&vm->hotplug_mutex); + break; + } + vm->hotplug_active = true; + zone = page_zonenum(pfn_to_page(mhp->start_pfn)); + rc = virtio_mem_notify_going_online(vm, mb_id, zone); + break; + case MEM_OFFLINE: + virtio_mem_notify_offline(vm, mb_id); + vm->hotplug_active = false; + mutex_unlock(&vm->hotplug_mutex); + break; + case MEM_ONLINE: + zone = page_zonenum(pfn_to_page(mhp->start_pfn)); + virtio_mem_notify_online(vm, mb_id, zone); + vm->hotplug_active = false; + mutex_unlock(&vm->hotplug_mutex); + break; + case MEM_CANCEL_OFFLINE: + case MEM_CANCEL_ONLINE: + if (!vm->hotplug_active) + break; + vm->hotplug_active = false; + mutex_unlock(&vm->hotplug_mutex); + break; + default: + break; + } + + lockdep_on(); + + return rc; +} + +/* + * Set a range of pages PG_offline. + */ +static void virtio_mem_set_fake_offline(unsigned long pfn, + unsigned int nr_pages) +{ + for (; nr_pages--; pfn++) + __SetPageOffline(pfn_to_page(pfn)); +} + +/* + * Clear PG_offline from a range of pages. + */ +static void virtio_mem_clear_fake_offline(unsigned long pfn, + unsigned int nr_pages) +{ + for (; nr_pages--; pfn++) + __ClearPageOffline(pfn_to_page(pfn)); +} + +/* + * Release a range of fake-offline pages to the buddy, effectively + * fake-onlining them. + */ +static void virtio_mem_fake_online(unsigned long pfn, unsigned int nr_pages) +{ + const int order = MAX_ORDER - 1; + int i; + + /* + * We are always called with subblock granularity, which is at least + * aligned to MAX_ORDER - 1. + */ + virtio_mem_clear_fake_offline(pfn, nr_pages); + + for (i = 0; i < nr_pages; i += 1 << order) + generic_online_page(pfn_to_page(pfn + i), order); +} + +static void virtio_mem_online_page_cb(struct page *page, unsigned int order) +{ + const unsigned long addr = page_to_phys(page); + const unsigned long mb_id = virtio_mem_phys_to_mb_id(addr); + struct virtio_mem *vm; + int sb_id; + + /* + * We exploit here that subblocks have at least MAX_ORDER - 1 + * size/alignment and that this callback is is called with such a + * size/alignment. So we cannot cross subblocks and therefore + * also not memory blocks. + */ + rcu_read_lock(); + list_for_each_entry_rcu(vm, &virtio_mem_devices, next) { + if (!virtio_mem_owned_mb(vm, mb_id)) + continue; + + sb_id = virtio_mem_phys_to_sb_id(vm, addr); + /* + * If plugged, online the pages, otherwise, set them fake + * offline (PageOffline). + */ + if (virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1)) + generic_online_page(page, order); + else + virtio_mem_set_fake_offline(PFN_DOWN(addr), 1 << order); + rcu_read_unlock(); + return; + } + rcu_read_unlock(); + + /* not virtio-mem memory, but e.g., a DIMM. online it */ + generic_online_page(page, order); +} + +static uint64_t virtio_mem_send_request(struct virtio_mem *vm, + const struct virtio_mem_req *req) +{ + struct scatterlist *sgs[2], sg_req, sg_resp; + unsigned int len; + int rc; + + /* don't use the request residing on the stack (vaddr) */ + vm->req = *req; + + /* out: buffer for request */ + sg_init_one(&sg_req, &vm->req, sizeof(vm->req)); + sgs[0] = &sg_req; + + /* in: buffer for response */ + sg_init_one(&sg_resp, &vm->resp, sizeof(vm->resp)); + sgs[1] = &sg_resp; + + rc = virtqueue_add_sgs(vm->vq, sgs, 1, 1, vm, GFP_KERNEL); + if (rc < 0) + return rc; + + virtqueue_kick(vm->vq); + + /* wait for a response */ + wait_event(vm->host_resp, virtqueue_get_buf(vm->vq, &len)); + + return virtio16_to_cpu(vm->vdev, vm->resp.type); +} + +static int virtio_mem_send_plug_request(struct virtio_mem *vm, uint64_t addr, + uint64_t size) +{ + const uint64_t nb_vm_blocks = size / vm->device_block_size; + const struct virtio_mem_req req = { + .type = cpu_to_virtio16(vm->vdev, VIRTIO_MEM_REQ_PLUG), + .u.plug.addr = cpu_to_virtio64(vm->vdev, addr), + .u.plug.nb_blocks = cpu_to_virtio16(vm->vdev, nb_vm_blocks), + }; + + if (atomic_read(&vm->config_changed)) + return -EAGAIN; + + switch (virtio_mem_send_request(vm, &req)) { + case VIRTIO_MEM_RESP_ACK: + vm->plugged_size += size; + return 0; + case VIRTIO_MEM_RESP_NACK: + return -EAGAIN; + case VIRTIO_MEM_RESP_BUSY: + return -EBUSY; + case VIRTIO_MEM_RESP_ERROR: + return -EINVAL; + default: + return -ENOMEM; + } +} + +static int virtio_mem_send_unplug_request(struct virtio_mem *vm, uint64_t addr, + uint64_t size) +{ + const uint64_t nb_vm_blocks = size / vm->device_block_size; + const struct virtio_mem_req req = { + .type = cpu_to_virtio16(vm->vdev, VIRTIO_MEM_REQ_UNPLUG), + .u.unplug.addr = cpu_to_virtio64(vm->vdev, addr), + .u.unplug.nb_blocks = cpu_to_virtio16(vm->vdev, nb_vm_blocks), + }; + + if (atomic_read(&vm->config_changed)) + return -EAGAIN; + + switch (virtio_mem_send_request(vm, &req)) { + case VIRTIO_MEM_RESP_ACK: + vm->plugged_size -= size; + return 0; + case VIRTIO_MEM_RESP_BUSY: + return -EBUSY; + case VIRTIO_MEM_RESP_ERROR: + return -EINVAL; + default: + return -ENOMEM; + } +} + +static int virtio_mem_send_unplug_all_request(struct virtio_mem *vm) +{ + const struct virtio_mem_req req = { + .type = cpu_to_virtio16(vm->vdev, VIRTIO_MEM_REQ_UNPLUG_ALL), + }; + + switch (virtio_mem_send_request(vm, &req)) { + case VIRTIO_MEM_RESP_ACK: + vm->unplug_all_required = false; + vm->plugged_size = 0; + /* usable region might have shrunk */ + atomic_set(&vm->config_changed, 1); + return 0; + case VIRTIO_MEM_RESP_BUSY: + return -EBUSY; + default: + return -ENOMEM; + } +} + +/* + * Plug selected subblocks. Updates the plugged state, but not the state + * of the memory block. + */ +static int virtio_mem_mb_plug_sb(struct virtio_mem *vm, unsigned long mb_id, + int sb_id, int count) +{ + const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id) + + sb_id * vm->subblock_size; + const uint64_t size = count * vm->subblock_size; + int rc; + + dev_dbg(&vm->vdev->dev, "plugging memory block: %lu : %i - %i\n", mb_id, + sb_id, sb_id + count - 1); + + rc = virtio_mem_send_plug_request(vm, addr, size); + if (!rc) + virtio_mem_mb_set_sb_plugged(vm, mb_id, sb_id, count); + return rc; +} + +/* + * Unplug selected subblocks. Updates the plugged state, but not the state + * of the memory block. + */ +static int virtio_mem_mb_unplug_sb(struct virtio_mem *vm, unsigned long mb_id, + int sb_id, int count) +{ + const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id) + + sb_id * vm->subblock_size; + const uint64_t size = count * vm->subblock_size; + int rc; + + dev_dbg(&vm->vdev->dev, "unplugging memory block: %lu : %i - %i\n", + mb_id, sb_id, sb_id + count - 1); + + rc = virtio_mem_send_unplug_request(vm, addr, size); + if (!rc) + virtio_mem_mb_set_sb_unplugged(vm, mb_id, sb_id, count); + return rc; +} + +/* + * Unplug the desired number of plugged subblocks of a offline or not-added + * memory block. Will fail if any subblock cannot get unplugged (instead of + * skipping it). + * + * Will not modify the state of the memory block. + * + * Note: can fail after some subblocks were unplugged. + */ +static int virtio_mem_mb_unplug_any_sb(struct virtio_mem *vm, + unsigned long mb_id, uint64_t *nb_sb) +{ + int sb_id, count; + int rc; + + while (*nb_sb) { + sb_id = virtio_mem_mb_first_plugged_sb(vm, mb_id); + if (sb_id >= vm->nb_sb_per_mb) + break; + count = 1; + while (count < *nb_sb && + sb_id + count < vm->nb_sb_per_mb && + virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id + count, + 1)) + count++; + + rc = virtio_mem_mb_unplug_sb(vm, mb_id, sb_id, count); + if (rc) + return rc; + *nb_sb -= count; + } + + return 0; +} + +/* + * Unplug all plugged subblocks of an offline or not-added memory block. + * + * Will not modify the state of the memory block. + * + * Note: can fail after some subblocks were unplugged. + */ +static int virtio_mem_mb_unplug(struct virtio_mem *vm, unsigned long mb_id) +{ + uint64_t nb_sb = vm->nb_sb_per_mb; + + return virtio_mem_mb_unplug_any_sb(vm, mb_id, &nb_sb); +} + +/* + * Prepare tracking data for the next memory block. + */ +static int virtio_mem_prepare_next_mb(struct virtio_mem *vm, + unsigned long *mb_id) +{ + int rc; + + if (vm->next_mb_id > vm->last_usable_mb_id) + return -ENOSPC; + + /* Resize the state array if required. */ + rc = virtio_mem_mb_state_prepare_next_mb(vm); + if (rc) + return rc; + + /* Resize the subblock bitmap if required. */ + rc = virtio_mem_sb_bitmap_prepare_next_mb(vm); + if (rc) + return rc; + + vm->nb_mb_state[VIRTIO_MEM_MB_STATE_UNUSED]++; + *mb_id = vm->next_mb_id++; + return 0; +} + +/* + * Don't add too many blocks that are not onlined yet to avoid running OOM. + */ +static bool virtio_mem_too_many_mb_offline(struct virtio_mem *vm) +{ + unsigned long nb_offline; + + nb_offline = vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] + + vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL]; + return nb_offline >= VIRTIO_MEM_NB_OFFLINE_THRESHOLD; +} + +/* + * Try to plug the desired number of subblocks and add the memory block + * to Linux. + * + * Will modify the state of the memory block. + */ +static int virtio_mem_mb_plug_and_add(struct virtio_mem *vm, + unsigned long mb_id, + uint64_t *nb_sb) +{ + const int count = min_t(int, *nb_sb, vm->nb_sb_per_mb); + int rc, rc2; + + if (WARN_ON_ONCE(!count)) + return -EINVAL; + + /* + * Plug the requested number of subblocks before adding it to linux, + * so that onlining will directly online all plugged subblocks. + */ + rc = virtio_mem_mb_plug_sb(vm, mb_id, 0, count); + if (rc) + return rc; + + /* + * Mark the block properly offline before adding it to Linux, + * so the memory notifiers will find the block in the right state. + */ + if (count == vm->nb_sb_per_mb) + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE); + else + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL); + + /* Add the memory block to linux - if that fails, try to unplug. */ + rc = virtio_mem_mb_add(vm, mb_id); + if (rc) { + enum virtio_mem_mb_state new_state = VIRTIO_MEM_MB_STATE_UNUSED; + + dev_err(&vm->vdev->dev, + "adding memory block %lu failed with %d\n", mb_id, rc); + rc2 = virtio_mem_mb_unplug_sb(vm, mb_id, 0, count); + + /* + * TODO: Linux MM does not properly clean up yet in all cases + * where adding of memory failed - especially on -ENOMEM. + */ + if (rc2) + new_state = VIRTIO_MEM_MB_STATE_PLUGGED; + virtio_mem_mb_set_state(vm, mb_id, new_state); + return rc; + } + + *nb_sb -= count; + return 0; +} + +/* + * Try to plug the desired number of subblocks of a memory block that + * is already added to Linux. + * + * Will modify the state of the memory block. + * + * Note: Can fail after some subblocks were successfully plugged. + */ +static int virtio_mem_mb_plug_any_sb(struct virtio_mem *vm, unsigned long mb_id, + uint64_t *nb_sb, bool online) +{ + unsigned long pfn, nr_pages; + int sb_id, count; + int rc; + + if (WARN_ON_ONCE(!*nb_sb)) + return -EINVAL; + + while (*nb_sb) { + sb_id = virtio_mem_mb_first_unplugged_sb(vm, mb_id); + if (sb_id >= vm->nb_sb_per_mb) + break; + count = 1; + while (count < *nb_sb && + sb_id + count < vm->nb_sb_per_mb && + !virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id + count, + 1)) + count++; + + rc = virtio_mem_mb_plug_sb(vm, mb_id, sb_id, count); + if (rc) + return rc; + *nb_sb -= count; + if (!online) + continue; + + /* fake-online the pages if the memory block is online */ + pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) + + sb_id * vm->subblock_size); + nr_pages = PFN_DOWN(count * vm->subblock_size); + virtio_mem_fake_online(pfn, nr_pages); + } + + if (virtio_mem_mb_test_sb_plugged(vm, mb_id, 0, vm->nb_sb_per_mb)) { + if (online) + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_ONLINE); + else + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE); + } + + return rc; +} + +/* + * Try to plug the requested amount of memory. + */ +static int virtio_mem_plug_request(struct virtio_mem *vm, uint64_t diff) +{ + uint64_t nb_sb = diff / vm->subblock_size; + unsigned long mb_id; + int rc; + + if (!nb_sb) + return 0; + + /* Don't race with onlining/offlining */ + mutex_lock(&vm->hotplug_mutex); + + /* Try to plug subblocks of partially plugged online blocks. */ + virtio_mem_for_each_mb_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL) { + rc = virtio_mem_mb_plug_any_sb(vm, mb_id, &nb_sb, true); + if (rc || !nb_sb) + goto out_unlock; + cond_resched(); + } + + /* Try to plug subblocks of partially plugged offline blocks. */ + virtio_mem_for_each_mb_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL) { + rc = virtio_mem_mb_plug_any_sb(vm, mb_id, &nb_sb, false); + if (rc || !nb_sb) + goto out_unlock; + cond_resched(); + } + + /* + * We won't be working on online/offline memory blocks from this point, + * so we can't race with memory onlining/offlining. Drop the mutex. + */ + mutex_unlock(&vm->hotplug_mutex); + + /* Try to plug and add unused blocks */ + virtio_mem_for_each_mb_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED) { + if (virtio_mem_too_many_mb_offline(vm)) + return -ENOSPC; + + rc = virtio_mem_mb_plug_and_add(vm, mb_id, &nb_sb); + if (rc || !nb_sb) + return rc; + cond_resched(); + } + + /* Try to prepare, plug and add new blocks */ + while (nb_sb) { + if (virtio_mem_too_many_mb_offline(vm)) + return -ENOSPC; + + rc = virtio_mem_prepare_next_mb(vm, &mb_id); + if (rc) + return rc; + rc = virtio_mem_mb_plug_and_add(vm, mb_id, &nb_sb); + if (rc) + return rc; + cond_resched(); + } + + return 0; +out_unlock: + mutex_unlock(&vm->hotplug_mutex); + return rc; +} + +/* + * Try to unplug all blocks that couldn't be unplugged before, for example, + * because the hypervisor was busy. + */ +static int virtio_mem_unplug_pending_mb(struct virtio_mem *vm) +{ + unsigned long mb_id; + int rc; + + virtio_mem_for_each_mb_state(vm, mb_id, VIRTIO_MEM_MB_STATE_PLUGGED) { + rc = virtio_mem_mb_unplug(vm, mb_id); + if (rc) + return rc; + virtio_mem_mb_set_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED); + } + + return 0; +} + +/* + * Update all parts of the config that could have changed. + */ +static void virtio_mem_refresh_config(struct virtio_mem *vm) +{ + const uint64_t phys_limit = 1UL << MAX_PHYSMEM_BITS; + uint64_t new_plugged_size, usable_region_size, end_addr; + + /* the plugged_size is just a reflection of what _we_ did previously */ + virtio_cread(vm->vdev, struct virtio_mem_config, plugged_size, + &new_plugged_size); + if (WARN_ON_ONCE(new_plugged_size != vm->plugged_size)) + vm->plugged_size = new_plugged_size; + + /* calculate the last usable memory block id */ + virtio_cread(vm->vdev, struct virtio_mem_config, + usable_region_size, &usable_region_size); + end_addr = vm->addr + usable_region_size; + end_addr = min(end_addr, phys_limit); + vm->last_usable_mb_id = virtio_mem_phys_to_mb_id(end_addr) - 1; + + /* see if there is a request to change the size */ + virtio_cread(vm->vdev, struct virtio_mem_config, requested_size, + &vm->requested_size); + + dev_info(&vm->vdev->dev, "plugged size: 0x%llx", vm->plugged_size); + dev_info(&vm->vdev->dev, "requested size: 0x%llx", vm->requested_size); +} + +/* + * Workqueue function for handling plug/unplug requests and config updates. + */ +static void virtio_mem_run_wq(struct work_struct *work) +{ + struct virtio_mem *vm = container_of(work, struct virtio_mem, wq); + uint64_t diff; + int rc; + + hrtimer_cancel(&vm->retry_timer); + + if (vm->broken) + return; + +retry: + rc = 0; + + /* Make sure we start with a clean state if there are leftovers. */ + if (unlikely(vm->unplug_all_required)) + rc = virtio_mem_send_unplug_all_request(vm); + + if (atomic_read(&vm->config_changed)) { + atomic_set(&vm->config_changed, 0); + virtio_mem_refresh_config(vm); + } + + /* Unplug any leftovers from previous runs */ + if (!rc) + rc = virtio_mem_unplug_pending_mb(vm); + + if (!rc && vm->requested_size != vm->plugged_size) { + if (vm->requested_size > vm->plugged_size) { + diff = vm->requested_size - vm->plugged_size; + rc = virtio_mem_plug_request(vm, diff); + } + /* TODO: try to unplug memory */ + } + + switch (rc) { + case 0: + break; + case -ENOSPC: + /* + * We cannot add any more memory (alignment, physical limit) + * or we have too many offline memory blocks. + */ + break; + case -EBUSY: + /* + * The hypervisor cannot process our request right now + * (e.g., out of memory, migrating). + */ + case -ENOMEM: + /* Out of memory, try again later. */ + hrtimer_start(&vm->retry_timer, + ms_to_ktime(VIRTIO_MEM_RETRY_TIMER_MS), + HRTIMER_MODE_REL); + break; + case -EAGAIN: + /* Retry immediately (e.g., the config changed). */ + goto retry; + default: + /* Unknown error, mark as broken */ + dev_err(&vm->vdev->dev, + "unknown error, marking device broken: %d\n", rc); + vm->broken = true; + } +} + +static enum hrtimer_restart virtio_mem_timer_expired(struct hrtimer *timer) +{ + struct virtio_mem *vm = container_of(timer, struct virtio_mem, + retry_timer); + + virtio_mem_retry(vm); + return HRTIMER_NORESTART; +} + +static void virtio_mem_handle_response(struct virtqueue *vq) +{ + struct virtio_mem *vm = vq->vdev->priv; + + wake_up(&vm->host_resp); +} + +static int virtio_mem_init_vq(struct virtio_mem *vm) +{ + struct virtqueue *vq; + + vq = virtio_find_single_vq(vm->vdev, virtio_mem_handle_response, + "guest-request"); + if (IS_ERR(vq)) + return PTR_ERR(vq); + vm->vq = vq; + + return 0; +} + +/* + * Test if any memory in the range is present in Linux. + */ +static bool virtio_mem_any_memory_present(unsigned long start, + unsigned long size) +{ + const unsigned long start_pfn = PFN_DOWN(start); + const unsigned long end_pfn = PFN_UP(start + size); + unsigned long pfn; + + for (pfn = start_pfn; pfn != end_pfn; pfn++) + if (present_section_nr(pfn_to_section_nr(pfn))) + return true; + + return false; +} + +static int virtio_mem_init(struct virtio_mem *vm) +{ + const uint64_t phys_limit = 1UL << MAX_PHYSMEM_BITS; + + if (!vm->vdev->config->get) { + dev_err(&vm->vdev->dev, "config access disabled\n"); + return -EINVAL; + } + + /* + * We don't want to (un)plug or reuse any memory when in kdump. The + * memory is still accessible (but not mapped). + */ + if (is_kdump_kernel()) { + dev_warn(&vm->vdev->dev, "disabled in kdump kernel\n"); + return -EBUSY; + } + + /* Fetch all properties that can't change. */ + virtio_cread(vm->vdev, struct virtio_mem_config, plugged_size, + &vm->plugged_size); + virtio_cread(vm->vdev, struct virtio_mem_config, block_size, + &vm->device_block_size); + virtio_cread(vm->vdev, struct virtio_mem_config, addr, &vm->addr); + virtio_cread(vm->vdev, struct virtio_mem_config, region_size, + &vm->region_size); + + /* + * If we still have memory plugged, we might have to unplug all + * memory first. However, if somebody simply unloaded the driver + * we would have to reinitialize the old state - something we don't + * support yet. Detect if we have any memory in the area present. + */ + if (vm->plugged_size) { + uint64_t usable_region_size; + + virtio_cread(vm->vdev, struct virtio_mem_config, + usable_region_size, &usable_region_size); + + if (virtio_mem_any_memory_present(vm->addr, + usable_region_size)) { + dev_err(&vm->vdev->dev, + "reloading the driver is not supported\n"); + return -EINVAL; + } + /* + * Note: it might happen that the device is busy and + * unplugging all memory might take some time. + */ + dev_info(&vm->vdev->dev, "unplugging all memory required\n"); + vm->unplug_all_required = 1; + } + + /* + * We always hotplug memory in memory block granularity. This way, + * we have to wait for exactly one memory block to online. + */ + if (vm->device_block_size > memory_block_size_bytes()) { + dev_err(&vm->vdev->dev, + "The block size is not supported (too big).\n"); + return -EINVAL; + } + + /* bad device setup - warn only */ + if (!IS_ALIGNED(vm->addr, memory_block_size_bytes())) + dev_warn(&vm->vdev->dev, + "The alignment of the physical start address can make some memory unusable.\n"); + if (!IS_ALIGNED(vm->addr + vm->region_size, memory_block_size_bytes())) + dev_warn(&vm->vdev->dev, + "The alignment of the physical end address can make some memory unusable.\n"); + if (vm->addr + vm->region_size > phys_limit) + dev_warn(&vm->vdev->dev, + "Some memory is not addressable. This can make some memory unusable.\n"); + + /* + * Calculate the subblock size: + * - At least MAX_ORDER - 1 / pageblock_order. + * - At least the device block size. + * In the worst case, a single subblock per memory block. + */ + vm->subblock_size = PAGE_SIZE * 1u << max_t(uint32_t, MAX_ORDER - 1, + pageblock_order); + vm->subblock_size = max_t(uint32_t, vm->device_block_size, + vm->subblock_size); + vm->nb_sb_per_mb = memory_block_size_bytes() / vm->subblock_size; + + /* Round up to the next full memory block */ + vm->first_mb_id = virtio_mem_phys_to_mb_id(vm->addr - 1 + + memory_block_size_bytes()); + vm->next_mb_id = vm->first_mb_id; + vm->last_mb_id = virtio_mem_phys_to_mb_id(vm->addr + + vm->region_size) - 1; + + dev_info(&vm->vdev->dev, "start address: 0x%llx", vm->addr); + dev_info(&vm->vdev->dev, "region size: 0x%llx", vm->region_size); + dev_info(&vm->vdev->dev, "device block size: 0x%x", + vm->device_block_size); + dev_info(&vm->vdev->dev, "memory block size: 0x%lx", + memory_block_size_bytes()); + dev_info(&vm->vdev->dev, "subblock size: 0x%x", + vm->subblock_size); + + return 0; +} + +static int virtio_mem_probe(struct virtio_device *vdev) +{ + struct virtio_mem *vm; + int rc = -EINVAL; + + vdev->priv = vm = kzalloc(sizeof(*vm), GFP_KERNEL); + if (!vm) + return -ENOMEM; + + init_waitqueue_head(&vm->host_resp); + vm->vdev = vdev; + INIT_WORK(&vm->wq, virtio_mem_run_wq); + mutex_init(&vm->hotplug_mutex); + INIT_LIST_HEAD(&vm->next); + spin_lock_init(&vm->removal_lock); + hrtimer_init(&vm->retry_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + vm->retry_timer.function = virtio_mem_timer_expired; + + /* register the virtqueue */ + rc = virtio_mem_init_vq(vm); + if (rc) + goto out_free_vm; + + /* initialize the device by querying the config */ + rc = virtio_mem_init(vm); + if (rc) + goto out_del_vq; + + /* register callbacks */ + vm->memory_notifier.notifier_call = virtio_mem_memory_notifier_cb; + rc = register_memory_notifier(&vm->memory_notifier); + if (rc) + goto out_del_vq; + rc = register_virtio_mem_device(vm); + if (rc) + goto out_unreg_mem; + + virtio_device_ready(vdev); + + /* trigger a config update to start processing the requested_size */ + atomic_set(&vm->config_changed, 1); + queue_work(system_freezable_wq, &vm->wq); + + return 0; +out_unreg_mem: + unregister_memory_notifier(&vm->memory_notifier); +out_del_vq: + vdev->config->del_vqs(vdev); +out_free_vm: + kfree(vm); + vdev->priv = NULL; + + return rc; +} + +static void virtio_mem_remove(struct virtio_device *vdev) +{ + struct virtio_mem *vm = vdev->priv; + unsigned long mb_id; + int rc; + + /* + * Make sure the workqueue won't be triggered anymore and no memory + * blocks can be onlined/offlined until we're finished here. + */ + mutex_lock(&vm->hotplug_mutex); + spin_lock_irq(&vm->removal_lock); + vm->removing = true; + spin_unlock_irq(&vm->removal_lock); + mutex_unlock(&vm->hotplug_mutex); + + /* wait until the workqueue stopped */ + cancel_work_sync(&vm->wq); + hrtimer_cancel(&vm->retry_timer); + + /* + * After we unregistered our callbacks, user space can online partially + * plugged offline blocks. Make sure to remove them. + */ + virtio_mem_for_each_mb_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL) { + rc = virtio_mem_mb_remove(vm, mb_id); + BUG_ON(rc); + virtio_mem_mb_set_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED); + } + + /* unregister callbacks */ + unregister_virtio_mem_device(vm); + unregister_memory_notifier(&vm->memory_notifier); + + /* + * There is no way we could reliably remove all memory we have added to + * the system. And there is no way to stop the driver/device from going + * away. Warn at least. + */ + if (vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] || + vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL] || + vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE] || + vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL] || + vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE]) + dev_warn(&vdev->dev, "device still has system memory added\n"); + + /* remove all tracking data - no locking needed */ + vfree(vm->mb_state); + vfree(vm->sb_bitmap); + + /* reset the device and cleanup the queues */ + vdev->config->reset(vdev); + vdev->config->del_vqs(vdev); + + kfree(vm); + vdev->priv = NULL; +} + +static void virtio_mem_config_changed(struct virtio_device *vdev) +{ + struct virtio_mem *vm = vdev->priv; + + atomic_set(&vm->config_changed, 1); + virtio_mem_retry(vm); +} + +#ifdef CONFIG_PM_SLEEP +static int virtio_mem_freeze(struct virtio_device *vdev) +{ + /* + * When restarting the VM, all memory is usually unplugged. Don't + * allow to suspend/hibernate. + */ + dev_err(&vdev->dev, "save/restore not supported.\n"); + return -EPERM; +} + +static int virtio_mem_restore(struct virtio_device *vdev) +{ + return -EPERM; +} +#endif + +static struct virtio_device_id virtio_mem_id_table[] = { + { VIRTIO_ID_MEM, VIRTIO_DEV_ANY_ID }, + { 0 }, +}; + +static struct virtio_driver virtio_mem_driver = { + .driver.name = KBUILD_MODNAME, + .driver.owner = THIS_MODULE, + .id_table = virtio_mem_id_table, + .probe = virtio_mem_probe, + .remove = virtio_mem_remove, + .config_changed = virtio_mem_config_changed, +#ifdef CONFIG_PM_SLEEP + .freeze = virtio_mem_freeze, + .restore = virtio_mem_restore, +#endif +}; + +module_virtio_driver(virtio_mem_driver); +MODULE_DEVICE_TABLE(virtio, virtio_mem_id_table); +MODULE_AUTHOR("David Hildenbrand "); +MODULE_DESCRIPTION("Virtio-mem driver"); +MODULE_LICENSE("GPL"); diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index ecc27a17401a..b052355ac7a3 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -44,6 +44,7 @@ #define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */ #define VIRTIO_ID_CRYPTO 20 /* virtio crypto */ #define VIRTIO_ID_IOMMU 23 /* virtio IOMMU */ +#define VIRTIO_ID_MEM 24 /* virtio mem */ #define VIRTIO_ID_FS 26 /* virtio filesystem */ #define VIRTIO_ID_PMEM 27 /* virtio pmem */ #define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */ diff --git a/include/uapi/linux/virtio_mem.h b/include/uapi/linux/virtio_mem.h new file mode 100644 index 000000000000..1bfade78bdfd --- /dev/null +++ b/include/uapi/linux/virtio_mem.h @@ -0,0 +1,200 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* + * Virtio Mem Device + * + * Copyright Red Hat, Inc. 2020 + * + * Authors: + * David Hildenbrand + * + * This header is BSD licensed so anyone can use the definitions + * to implement compatible drivers/servers: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL IBM OR + * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF + * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT + * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#ifndef _LINUX_VIRTIO_MEM_H +#define _LINUX_VIRTIO_MEM_H + +#include +#include +#include +#include + +/* + * Each virtio-mem device manages a dedicated region in physical address + * space. Each device can belong to a single NUMA node, multiple devices + * for a single NUMA node are possible. A virtio-mem device is like a + * "resizable DIMM" consisting of small memory blocks that can be plugged + * or unplugged. The device driver is responsible for (un)plugging memory + * blocks on demand. + * + * Virtio-mem devices can only operate on their assigned memory region in + * order to (un)plug memory. A device cannot (un)plug memory belonging to + * other devices. + * + * The "region_size" corresponds to the maximum amount of memory that can + * be provided by a device. The "size" corresponds to the amount of memory + * that is currently plugged. "requested_size" corresponds to a request + * from the device to the device driver to (un)plug blocks. The + * device driver should try to (un)plug blocks in order to reach the + * "requested_size". It is impossible to plug more memory than requested. + * + * The "usable_region_size" represents the memory region that can actually + * be used to (un)plug memory. It is always at least as big as the + * "requested_size" and will grow dynamically. It will only shrink when + * explicitly triggered (VIRTIO_MEM_REQ_UNPLUG). + * + * There are no guarantees what will happen if unplugged memory is + * read/written. Such memory should, in general, not be touched. E.g., + * even writing might succeed, but the values will simply be discarded at + * random points in time. + * + * It can happen that the device cannot process a request, because it is + * busy. The device driver has to retry later. + * + * Usually, during system resets all memory will get unplugged, so the + * device driver can start with a clean state. However, in specific + * scenarios (if the device is busy) it can happen that the device still + * has memory plugged. The device driver can request to unplug all memory + * (VIRTIO_MEM_REQ_UNPLUG) - which might take a while to succeed if the + * device is busy. + */ + +/* --- virtio-mem: guest -> host requests --- */ + +/* request to plug memory blocks */ +#define VIRTIO_MEM_REQ_PLUG 0 +/* request to unplug memory blocks */ +#define VIRTIO_MEM_REQ_UNPLUG 1 +/* request to unplug all blocks and shrink the usable size */ +#define VIRTIO_MEM_REQ_UNPLUG_ALL 2 +/* request information about the plugged state of memory blocks */ +#define VIRTIO_MEM_REQ_STATE 3 + +struct virtio_mem_req_plug { + __virtio64 addr; + __virtio16 nb_blocks; +}; + +struct virtio_mem_req_unplug { + __virtio64 addr; + __virtio16 nb_blocks; +}; + +struct virtio_mem_req_state { + __virtio64 addr; + __virtio16 nb_blocks; +}; + +struct virtio_mem_req { + __virtio16 type; + __virtio16 padding[3]; + + union { + struct virtio_mem_req_plug plug; + struct virtio_mem_req_unplug unplug; + struct virtio_mem_req_state state; + } u; +}; + + +/* --- virtio-mem: host -> guest response --- */ + +/* + * Request processed successfully, applicable for + * - VIRTIO_MEM_REQ_PLUG + * - VIRTIO_MEM_REQ_UNPLUG + * - VIRTIO_MEM_REQ_UNPLUG_ALL + * - VIRTIO_MEM_REQ_STATE + */ +#define VIRTIO_MEM_RESP_ACK 0 +/* + * Request denied - e.g. trying to plug more than requested, applicable for + * - VIRTIO_MEM_REQ_PLUG + */ +#define VIRTIO_MEM_RESP_NACK 1 +/* + * Request cannot be processed right now, try again later, applicable for + * - VIRTIO_MEM_REQ_PLUG + * - VIRTIO_MEM_REQ_UNPLUG + * - VIRTIO_MEM_REQ_UNPLUG_ALL + */ +#define VIRTIO_MEM_RESP_BUSY 2 +/* + * Error in request (e.g. addresses/alignment), applicable for + * - VIRTIO_MEM_REQ_PLUG + * - VIRTIO_MEM_REQ_UNPLUG + * - VIRTIO_MEM_REQ_STATE + */ +#define VIRTIO_MEM_RESP_ERROR 3 + + +/* State of memory blocks is "plugged" */ +#define VIRTIO_MEM_STATE_PLUGGED 0 +/* State of memory blocks is "unplugged" */ +#define VIRTIO_MEM_STATE_UNPLUGGED 1 +/* State of memory blocks is "mixed" */ +#define VIRTIO_MEM_STATE_MIXED 2 + +struct virtio_mem_resp_state { + __virtio16 state; +}; + +struct virtio_mem_resp { + __virtio16 type; + __virtio16 padding[3]; + + union { + struct virtio_mem_resp_state state; + } u; +}; + +/* --- virtio-mem: configuration --- */ + +struct virtio_mem_config { + /* Block size and alignment. Cannot change. */ + __u32 block_size; + __u32 padding; + /* Start address of the memory region. Cannot change. */ + __u64 addr; + /* Region size (maximum). Cannot change. */ + __u64 region_size; + /* + * Currently usable region size. Can grow up to region_size. Can + * shrink due to VIRTIO_MEM_REQ_UNPLUG_ALL (in which case no config + * update will be sent). + */ + __u64 usable_region_size; + /* + * Currently used size. Changes due to plug/unplug requests, but no + * config updates will be sent. + */ + __u64 plugged_size; + /* Requested size. New plug requests cannot exceed it. Can change. */ + __u64 requested_size; +}; + +#endif /* _LINUX_VIRTIO_MEM_H */ -- cgit v1.2.3 From f2af6d3978d74a7891d0f428537b4494498202cb Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 7 May 2020 16:01:27 +0200 Subject: virtio-mem: Allow to specify an ACPI PXM as nid We want to allow to specify (similar as for a DIMM), to which node a virtio-mem device (and, therefore, its memory) belongs. Add a new virtio-mem feature flag and export pxm_to_node, so it can be used in kernel module context. Acked-by: Michal Hocko # for the export Acked-by: "Rafael J. Wysocki" # for the export Acked-by: Pankaj Gupta Tested-by: Pankaj Gupta Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Oscar Salvador Cc: Michal Hocko Cc: Igor Mammedov Cc: Dave Young Cc: Andrew Morton Cc: Dan Williams Cc: Pavel Tatashin Cc: Stefan Hajnoczi Cc: Vlastimil Babka Cc: Len Brown Cc: linux-acpi@vger.kernel.org Signed-off-by: David Hildenbrand Link: https://lore.kernel.org/r/20200507140139.17083-4-david@redhat.com Signed-off-by: Michael S. Tsirkin --- drivers/acpi/numa/srat.c | 1 + drivers/virtio/virtio_mem.c | 39 +++++++++++++++++++++++++++++++++++++-- include/uapi/linux/virtio_mem.h | 10 +++++++++- 3 files changed, 47 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index 47b4969d9b93..5be5a977da1b 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -35,6 +35,7 @@ int pxm_to_node(int pxm) return NUMA_NO_NODE; return pxm_to_node_map[pxm]; } +EXPORT_SYMBOL(pxm_to_node); int node_to_pxm(int node) { diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 5d1dcaa6fc42..270ddeaec059 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -21,6 +21,8 @@ #include #include +#include + enum virtio_mem_mb_state { /* Unplugged, not added to Linux. Can be reused later. */ VIRTIO_MEM_MB_STATE_UNUSED = 0, @@ -72,6 +74,8 @@ struct virtio_mem { /* The device block size (for communicating with the device). */ uint32_t device_block_size; + /* The translated node id. NUMA_NO_NODE in case not specified. */ + int nid; /* Physical start address of the memory region. */ uint64_t addr; /* Maximum region size in bytes. */ @@ -389,7 +393,10 @@ static int virtio_mem_sb_bitmap_prepare_next_mb(struct virtio_mem *vm) static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id) { const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id); - int nid = memory_add_physaddr_to_nid(addr); + int nid = vm->nid; + + if (nid == NUMA_NO_NODE) + nid = memory_add_physaddr_to_nid(addr); dev_dbg(&vm->vdev->dev, "adding memory block: %lu\n", mb_id); return add_memory(nid, addr, memory_block_size_bytes()); @@ -407,7 +414,10 @@ static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id) static int virtio_mem_mb_remove(struct virtio_mem *vm, unsigned long mb_id) { const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id); - int nid = memory_add_physaddr_to_nid(addr); + int nid = vm->nid; + + if (nid == NUMA_NO_NODE) + nid = memory_add_physaddr_to_nid(addr); dev_dbg(&vm->vdev->dev, "removing memory block: %lu\n", mb_id); return remove_memory(nid, addr, memory_block_size_bytes()); @@ -426,6 +436,17 @@ static void virtio_mem_retry(struct virtio_mem *vm) spin_unlock_irqrestore(&vm->removal_lock, flags); } +static int virtio_mem_translate_node_id(struct virtio_mem *vm, uint16_t node_id) +{ + int node = NUMA_NO_NODE; + +#if defined(CONFIG_ACPI_NUMA) + if (virtio_has_feature(vm->vdev, VIRTIO_MEM_F_ACPI_PXM)) + node = pxm_to_node(node_id); +#endif + return node; +} + /* * Test if a virtio-mem device overlaps with the given range. Can be called * from (notifier) callbacks lockless. @@ -1267,6 +1288,7 @@ static bool virtio_mem_any_memory_present(unsigned long start, static int virtio_mem_init(struct virtio_mem *vm) { const uint64_t phys_limit = 1UL << MAX_PHYSMEM_BITS; + uint16_t node_id; if (!vm->vdev->config->get) { dev_err(&vm->vdev->dev, "config access disabled\n"); @@ -1287,6 +1309,9 @@ static int virtio_mem_init(struct virtio_mem *vm) &vm->plugged_size); virtio_cread(vm->vdev, struct virtio_mem_config, block_size, &vm->device_block_size); + virtio_cread(vm->vdev, struct virtio_mem_config, node_id, + &node_id); + vm->nid = virtio_mem_translate_node_id(vm, node_id); virtio_cread(vm->vdev, struct virtio_mem_config, addr, &vm->addr); virtio_cread(vm->vdev, struct virtio_mem_config, region_size, &vm->region_size); @@ -1365,6 +1390,8 @@ static int virtio_mem_init(struct virtio_mem *vm) memory_block_size_bytes()); dev_info(&vm->vdev->dev, "subblock size: 0x%x", vm->subblock_size); + if (vm->nid != NUMA_NO_NODE) + dev_info(&vm->vdev->dev, "nid: %d", vm->nid); return 0; } @@ -1508,12 +1535,20 @@ static int virtio_mem_restore(struct virtio_device *vdev) } #endif +static unsigned int virtio_mem_features[] = { +#if defined(CONFIG_NUMA) && defined(CONFIG_ACPI_NUMA) + VIRTIO_MEM_F_ACPI_PXM, +#endif +}; + static struct virtio_device_id virtio_mem_id_table[] = { { VIRTIO_ID_MEM, VIRTIO_DEV_ANY_ID }, { 0 }, }; static struct virtio_driver virtio_mem_driver = { + .feature_table = virtio_mem_features, + .feature_table_size = ARRAY_SIZE(virtio_mem_features), .driver.name = KBUILD_MODNAME, .driver.owner = THIS_MODULE, .id_table = virtio_mem_id_table, diff --git a/include/uapi/linux/virtio_mem.h b/include/uapi/linux/virtio_mem.h index 1bfade78bdfd..e0a9dc7397c3 100644 --- a/include/uapi/linux/virtio_mem.h +++ b/include/uapi/linux/virtio_mem.h @@ -83,6 +83,12 @@ * device is busy. */ +/* --- virtio-mem: feature bits --- */ + +/* node_id is an ACPI PXM and is valid */ +#define VIRTIO_MEM_F_ACPI_PXM 0 + + /* --- virtio-mem: guest -> host requests --- */ /* request to plug memory blocks */ @@ -177,7 +183,9 @@ struct virtio_mem_resp { struct virtio_mem_config { /* Block size and alignment. Cannot change. */ __u32 block_size; - __u32 padding; + /* Valid with VIRTIO_MEM_F_ACPI_PXM. Cannot change. */ + __u16 node_id; + __u16 padding; /* Start address of the memory region. Cannot change. */ __u64 addr; /* Region size (maximum). Cannot change. */ -- cgit v1.2.3 From fce8afd76e3a4d8c59c92f84f8027569fd7031d0 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 15 May 2020 12:14:02 +0200 Subject: virtio-mem: Don't rely on implicit compiler padding for requests The compiler will add padding after the last member, make that explicit. The size of a request is always 24 bytes. The size of a response always 10 bytes. Add compile-time checks. Cc: "Michael S. Tsirkin" Cc: Pankaj Gupta Cc: teawater Signed-off-by: David Hildenbrand Link: https://lore.kernel.org/r/20200515101402.16597-1-david@redhat.com Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_mem.c | 3 +++ include/uapi/linux/virtio_mem.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 9e523db3bee1..f658fe9149be 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -1770,6 +1770,9 @@ static int virtio_mem_probe(struct virtio_device *vdev) struct virtio_mem *vm; int rc = -EINVAL; + BUILD_BUG_ON(sizeof(struct virtio_mem_req) != 24); + BUILD_BUG_ON(sizeof(struct virtio_mem_resp) != 10); + vdev->priv = vm = kzalloc(sizeof(*vm), GFP_KERNEL); if (!vm) return -ENOMEM; diff --git a/include/uapi/linux/virtio_mem.h b/include/uapi/linux/virtio_mem.h index e0a9dc7397c3..a455c488a995 100644 --- a/include/uapi/linux/virtio_mem.h +++ b/include/uapi/linux/virtio_mem.h @@ -103,16 +103,19 @@ struct virtio_mem_req_plug { __virtio64 addr; __virtio16 nb_blocks; + __virtio16 padding[3]; }; struct virtio_mem_req_unplug { __virtio64 addr; __virtio16 nb_blocks; + __virtio16 padding[3]; }; struct virtio_mem_req_state { __virtio64 addr; __virtio16 nb_blocks; + __virtio16 padding[3]; }; struct virtio_mem_req { -- cgit v1.2.3 From f286d627ef026a4d04b41ae5917d58ddf243c3c5 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 13 Jan 2020 21:21:49 +0100 Subject: gfs2: Keep track of deleted inode generations in LVBs When deleting an inode, keep track of the generation of the deleted inode in the inode glock Lock Value Block (LVB). When trying to delete an inode remotely, check the last-known inode generation against the deleted inode generation to skip duplicate remote deletes. This avoids taking the resource group glock in order to verify the block type. Signed-off-by: Andreas Gruenbacher --- fs/gfs2/glock.c | 19 +++++++++++++++++++ fs/gfs2/glock.h | 3 +++ fs/gfs2/glops.c | 2 +- fs/gfs2/super.c | 3 +++ include/uapi/linux/gfs2_ondisk.h | 6 ++++++ 5 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 86e9e621f346..12681616eb76 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -755,6 +755,25 @@ out_unlock: return; } +void gfs2_inode_remember_delete(struct gfs2_glock *gl, u64 generation) +{ + struct gfs2_inode_lvb *ri = (void *)gl->gl_lksb.sb_lvbptr; + + if (ri->ri_magic == 0) + ri->ri_magic = cpu_to_be32(GFS2_MAGIC); + if (ri->ri_magic == cpu_to_be32(GFS2_MAGIC)) + ri->ri_generation_deleted = cpu_to_be64(generation); +} + +bool gfs2_inode_already_deleted(struct gfs2_glock *gl, u64 generation) +{ + struct gfs2_inode_lvb *ri = (void *)gl->gl_lksb.sb_lvbptr; + + if (ri->ri_magic != cpu_to_be32(GFS2_MAGIC)) + return false; + return generation <= be64_to_cpu(ri->ri_generation_deleted); +} + static void delete_work_func(struct work_struct *work) { struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_delete); diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index b8adaf80e4c5..5c1b60fdedcf 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -306,4 +306,7 @@ static inline void glock_clear_object(struct gfs2_glock *gl, void *object) spin_unlock(&gl->gl_lockref.lock); } +extern void gfs2_inode_remember_delete(struct gfs2_glock *gl, u64 generation); +extern bool gfs2_inode_already_deleted(struct gfs2_glock *gl, u64 generation); + #endif /* __GLOCK_DOT_H__ */ diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 9e9c7a4b8c66..63ae9e45ce34 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -692,7 +692,7 @@ const struct gfs2_glock_operations gfs2_inode_glops = { .go_lock = inode_go_lock, .go_dump = inode_go_dump, .go_type = LM_TYPE_INODE, - .go_flags = GLOF_ASPACE | GLOF_LRU, + .go_flags = GLOF_ASPACE | GLOF_LRU | GLOF_LVB, .go_free = inode_go_free, }; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 956fced0a8ec..e69efed9fb51 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1315,6 +1315,8 @@ static void gfs2_evict_inode(struct inode *inode) goto out; } + if (gfs2_inode_already_deleted(ip->i_gl, ip->i_no_formal_ino)) + goto out_truncate; error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED); if (error) goto out_truncate; @@ -1368,6 +1370,7 @@ alloc_failed: that subsequent inode creates don't see an old gl_object. */ glock_clear_object(ip->i_gl, ip); error = gfs2_dinode_dealloc(ip); + gfs2_inode_remember_delete(ip->i_gl, ip->i_no_formal_ino); goto out_unlock; out_truncate: diff --git a/include/uapi/linux/gfs2_ondisk.h b/include/uapi/linux/gfs2_ondisk.h index 2dc10a034de1..07e508e6691b 100644 --- a/include/uapi/linux/gfs2_ondisk.h +++ b/include/uapi/linux/gfs2_ondisk.h @@ -171,6 +171,12 @@ struct gfs2_rindex { #define GFS2_RGF_NOALLOC 0x00000008 #define GFS2_RGF_TRIMMED 0x00000010 +struct gfs2_inode_lvb { + __be32 ri_magic; + __be32 __pad; + __be64 ri_generation_deleted; +}; + struct gfs2_rgrp_lvb { __be32 rl_magic; __be32 rl_flags; -- cgit v1.2.3 From 776f395004d829bbbf18c159ed9beb517a208c71 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Fri, 5 Jun 2020 18:27:13 +0800 Subject: vhost_vdpa: Support config interrupt in vdpa This commit implements config interrupt support in vhost_vdpa layer. Signed-off-by: Zhu Lingshan Acked-by: Jason Wang Link: https://lore.kernel.org/r/1591352835-22441-4-git-send-email-lingshan.zhu@intel.com Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vdpa.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/vhost.h | 4 ++++ 2 files changed, 51 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 6ca7660ee6b5..77a0c9fb6cc3 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "vhost.h" @@ -71,6 +72,7 @@ struct vhost_vdpa { int nvqs; int virtio_id; int minor; + struct eventfd_ctx *config_ctx; }; static DEFINE_IDA(vhost_vdpa_ida); @@ -102,6 +104,17 @@ static irqreturn_t vhost_vdpa_virtqueue_cb(void *private) return IRQ_HANDLED; } +static irqreturn_t vhost_vdpa_config_cb(void *private) +{ + struct vhost_vdpa *v = private; + struct eventfd_ctx *config_ctx = v->config_ctx; + + if (config_ctx) + eventfd_signal(config_ctx, 1); + + return IRQ_HANDLED; +} + static void vhost_vdpa_reset(struct vhost_vdpa *v) { struct vdpa_device *vdpa = v->vdpa; @@ -289,6 +302,36 @@ static long vhost_vdpa_get_vring_num(struct vhost_vdpa *v, u16 __user *argp) return 0; } +static void vhost_vdpa_config_put(struct vhost_vdpa *v) +{ + if (v->config_ctx) + eventfd_ctx_put(v->config_ctx); +} + +static long vhost_vdpa_set_config_call(struct vhost_vdpa *v, u32 __user *argp) +{ + struct vdpa_callback cb; + int fd; + struct eventfd_ctx *ctx; + + cb.callback = vhost_vdpa_config_cb; + cb.private = v->vdpa; + if (copy_from_user(&fd, argp, sizeof(fd))) + return -EFAULT; + + ctx = fd == VHOST_FILE_UNBIND ? NULL : eventfd_ctx_fdget(fd); + swap(ctx, v->config_ctx); + + if (!IS_ERR_OR_NULL(ctx)) + eventfd_ctx_put(ctx); + + if (IS_ERR(v->config_ctx)) + return PTR_ERR(v->config_ctx); + + v->vdpa->config->set_config_cb(v->vdpa, &cb); + + return 0; +} static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, void __user *argp) { @@ -396,6 +439,9 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, case VHOST_SET_LOG_FD: r = -ENOIOCTLCMD; break; + case VHOST_VDPA_SET_CONFIG_CALL: + r = vhost_vdpa_set_config_call(v, argp); + break; default: r = vhost_dev_ioctl(&v->vdev, cmd, argp); if (r == -ENOIOCTLCMD) @@ -730,6 +776,7 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep) vhost_dev_stop(&v->vdev); vhost_vdpa_iotlb_free(v); vhost_vdpa_free_domain(v); + vhost_vdpa_config_put(v); vhost_dev_cleanup(&v->vdev); kfree(v->vdev.vqs); mutex_unlock(&d->mutex); diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 9fe72e4b1373..0c2349612e77 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -15,6 +15,8 @@ #include #include +#define VHOST_FILE_UNBIND -1 + /* ioctls */ #define VHOST_VIRTIO 0xAF @@ -140,4 +142,6 @@ /* Get the max ring size. */ #define VHOST_VDPA_GET_VRING_NUM _IOR(VHOST_VIRTIO, 0x76, __u16) +/* Set event fd for config interrupt*/ +#define VHOST_VDPA_SET_CONFIG_CALL _IOW(VHOST_VIRTIO, 0x77, int) #endif -- cgit v1.2.3 From 97eda66421c44f1449e8d087fd05eab5d466afb7 Mon Sep 17 00:00:00 2001 From: Flavio Suligoi Date: Fri, 5 Jun 2020 17:41:11 +0200 Subject: include: fix wiki website url in netlink interface header The wiki url is still the old "wireless.kernel.org" instead of the new "wireless.wiki.kernel.org" Signed-off-by: Flavio Suligoi Link: https://lore.kernel.org/r/20200605154112.16277-9-f.suligoi@asem.it Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index dad8c8f8581f..4e6339ab1fce 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -794,7 +794,7 @@ * various triggers. These triggers can be configured through this * command with the %NL80211_ATTR_WOWLAN_TRIGGERS attribute. For * more background information, see - * http://wireless.kernel.org/en/users/Documentation/WoWLAN. + * https://wireless.wiki.kernel.org/en/users/Documentation/WoWLAN. * The @NL80211_CMD_SET_WOWLAN command can also be used as a notification * from the driver reporting the wakeup reason. In this case, the * @NL80211_ATTR_WOWLAN_TRIGGERS attribute will contain the reason -- cgit v1.2.3 From 544fc7dbbf920a3e64d109c416ee229e8e1763c5 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 8 Jun 2020 02:03:15 -0400 Subject: virtio_mem: convert device block size into 64bit If subblock size is large (e.g. 1G) 32 bit math involving it can overflow. Rather than try to catch all instances of that, let's tweak block size to 64 bit. It ripples through UAPI which is an ABI change, but it's not too late to make it, and it will allow supporting >4Gbyte blocks while might become necessary down the road. Fixes: 5f1f79bbc9e26 ("virtio-mem: Paravirtualized memory hotplug") Signed-off-by: Michael S. Tsirkin Acked-by: David Hildenbrand --- drivers/virtio/virtio_mem.c | 18 +++++++++--------- include/uapi/linux/virtio_mem.h | 4 ++-- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 2f357142ea5e..50c689f25045 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -77,7 +77,7 @@ struct virtio_mem { uint64_t requested_size; /* The device block size (for communicating with the device). */ - uint32_t device_block_size; + uint64_t device_block_size; /* The translated node id. NUMA_NO_NODE in case not specified. */ int nid; /* Physical start address of the memory region. */ @@ -86,7 +86,7 @@ struct virtio_mem { uint64_t region_size; /* The subblock size. */ - uint32_t subblock_size; + uint64_t subblock_size; /* The number of subblocks per memory block. */ uint32_t nb_sb_per_mb; @@ -1698,9 +1698,9 @@ static int virtio_mem_init(struct virtio_mem *vm) * - At least the device block size. * In the worst case, a single subblock per memory block. */ - vm->subblock_size = PAGE_SIZE * 1u << max_t(uint32_t, MAX_ORDER - 1, - pageblock_order); - vm->subblock_size = max_t(uint32_t, vm->device_block_size, + vm->subblock_size = PAGE_SIZE * 1ul << max_t(uint32_t, MAX_ORDER - 1, + pageblock_order); + vm->subblock_size = max_t(uint64_t, vm->device_block_size, vm->subblock_size); vm->nb_sb_per_mb = memory_block_size_bytes() / vm->subblock_size; @@ -1713,12 +1713,12 @@ static int virtio_mem_init(struct virtio_mem *vm) dev_info(&vm->vdev->dev, "start address: 0x%llx", vm->addr); dev_info(&vm->vdev->dev, "region size: 0x%llx", vm->region_size); - dev_info(&vm->vdev->dev, "device block size: 0x%x", - vm->device_block_size); + dev_info(&vm->vdev->dev, "device block size: 0x%llx", + (unsigned long long)vm->device_block_size); dev_info(&vm->vdev->dev, "memory block size: 0x%lx", memory_block_size_bytes()); - dev_info(&vm->vdev->dev, "subblock size: 0x%x", - vm->subblock_size); + dev_info(&vm->vdev->dev, "subblock size: 0x%llx", + (unsigned long long)vm->subblock_size); if (vm->nid != NUMA_NO_NODE) dev_info(&vm->vdev->dev, "nid: %d", vm->nid); diff --git a/include/uapi/linux/virtio_mem.h b/include/uapi/linux/virtio_mem.h index a455c488a995..a9ffe041843c 100644 --- a/include/uapi/linux/virtio_mem.h +++ b/include/uapi/linux/virtio_mem.h @@ -185,10 +185,10 @@ struct virtio_mem_resp { struct virtio_mem_config { /* Block size and alignment. Cannot change. */ - __u32 block_size; + __u64 block_size; /* Valid with VIRTIO_MEM_F_ACPI_PXM. Cannot change. */ __u16 node_id; - __u16 padding; + __u8 padding[6]; /* Start address of the memory region. Cannot change. */ __u64 addr; /* Region size (maximum). Cannot change. */ -- cgit v1.2.3 From 281920b7e0b31e0a7706433ff58e7d52ac97c327 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 9 Jun 2020 15:31:46 +0200 Subject: bpf: Devmap adjust uapi for attach bpf program V2: - Defer changing BPF-syscall to start at file-descriptor 1 - Use {} to zero initialise struct. The recent commit fbee97feed9b ("bpf: Add support to attach bpf program to a devmap entry"), introduced ability to attach (and run) a separate XDP bpf_prog for each devmap entry. A bpf_prog is added via a file-descriptor. As zero were a valid FD, not using the feature requires using value minus-1. The UAPI is extended via tail-extending struct bpf_devmap_val and using map->value_size to determine the feature set. This will break older userspace applications not using the bpf_prog feature. Consider an old userspace app that is compiled against newer kernel uapi/bpf.h, it will not know that it need to initialise the member bpf_prog.fd to minus-1. Thus, users will be forced to update source code to get program running on newer kernels. This patch remove the minus-1 checks, and have zero mean feature isn't used. Followup patches either for kernel or libbpf should handle and avoid returning file-descriptor zero in the first place. Fixes: fbee97feed9b ("bpf: Add support to attach bpf program to a devmap entry") Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/159170950687.2102545.7235914718298050113.stgit@firesoul --- include/uapi/linux/bpf.h | 13 +++++++++++++ kernel/bpf/devmap.c | 17 ++++------------- 2 files changed, 17 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c65b374a5090..19684813faae 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3761,6 +3761,19 @@ struct xdp_md { __u32 egress_ifindex; /* txq->dev->ifindex */ }; +/* DEVMAP map-value layout + * + * The struct data-layout of map-value is a configuration interface. + * New members can only be added to the end of this structure. + */ +struct bpf_devmap_val { + __u32 ifindex; /* device index */ + union { + int fd; /* prog fd on map write */ + __u32 id; /* prog id on map read */ + } bpf_prog; +}; + enum sk_action { SK_DROP = 0, SK_PASS, diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index bfdff2faf5cb..0cbb72cdaf63 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -60,15 +60,6 @@ struct xdp_dev_bulk_queue { unsigned int count; }; -/* DEVMAP values */ -struct bpf_devmap_val { - u32 ifindex; /* device index */ - union { - int fd; /* prog fd on map write */ - u32 id; /* prog id on map read */ - } bpf_prog; -}; - struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ struct hlist_node index_hlist; @@ -619,7 +610,7 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, if (!dev->dev) goto err_out; - if (val->bpf_prog.fd >= 0) { + if (val->bpf_prog.fd > 0) { prog = bpf_prog_get_type_dev(val->bpf_prog.fd, BPF_PROG_TYPE_XDP, false); if (IS_ERR(prog)) @@ -653,8 +644,8 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - struct bpf_devmap_val val = { .bpf_prog.fd = -1 }; struct bpf_dtab_netdev *dev, *old_dev; + struct bpf_devmap_val val = {}; u32 i = *(u32 *)key; if (unlikely(map_flags > BPF_EXIST)) @@ -670,7 +661,7 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map, if (!val.ifindex) { dev = NULL; /* can not specify fd if ifindex is 0 */ - if (val.bpf_prog.fd != -1) + if (val.bpf_prog.fd > 0) return -EINVAL; } else { dev = __dev_map_alloc_node(net, dtab, &val, i); @@ -700,8 +691,8 @@ static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - struct bpf_devmap_val val = { .bpf_prog.fd = -1 }; struct bpf_dtab_netdev *dev, *old_dev; + struct bpf_devmap_val val = {}; u32 idx = *(u32 *)key; unsigned long flags; int err = -EEXIST; -- cgit v1.2.3