From 73ae7e1c7644a8c33ba526302a10267cdbc249f8 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 11 Jan 2024 17:57:44 +0100 Subject: ata: libata-sata: improve sysfs description for ATA_LPM_UNKNOWN Currently, both ATA_LPM_UNKNOWN (0) and ATA_LPM_MAX_POWER (1) displays as "max_performance" in sysfs. This is quite misleading as they are not the same. For ATA_LPM_UNKNOWN, ata_eh_set_lpm() will not be called at all, leaving the configuration in unknown state. For ATA_LPM_MAX_POWER, ata_eh_set_lpm() is called, and setting the policy to ATA_LPM_MAX_POWER. This also matches the description of the SATA_MOBILE_LPM_POLICY Kconfig: 0 => Keep firmware settings 1 => Maximum performance Thus, update the sysfs description for ATA_LPM_UNKNOWN to match reality. While at it, update libata.h to mention that the ascii descriptions are in libata-sata.c and not in libata-scsi.c. Reviewed-by: Damien Le Moal Signed-off-by: Niklas Cassel --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 1dbb14daccfa..26d68115afb8 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -471,7 +471,7 @@ enum ata_completion_errors { /* * Link power management policy: If you alter this, you also need to - * alter libata-scsi.c (for the ascii descriptions) + * alter libata-sata.c (for the ascii descriptions) */ enum ata_lpm_policy { ATA_LPM_UNKNOWN, -- cgit v1.2.3 From 56062d60f117dccfb5281869e0ab61e090baf864 Mon Sep 17 00:00:00 2001 From: Richard Palethorpe Date: Wed, 10 Jan 2024 15:01:22 +0200 Subject: x86/entry/ia32: Ensure s32 is sign extended to s64 Presently ia32 registers stored in ptregs are unconditionally cast to unsigned int by the ia32 stub. They are then cast to long when passed to __se_sys*, but will not be sign extended. This takes the sign of the syscall argument into account in the ia32 stub. It still casts to unsigned int to avoid implementation specific behavior. However then casts to int or unsigned int as necessary. So that the following cast to long sign extends the value. This fixes the io_pgetevents02 LTP test when compiled with -m32. Presently the systemcall io_pgetevents_time64() unexpectedly accepts -1 for the maximum number of events. It doesn't appear other systemcalls with signed arguments are effected because they all have compat variants defined and wired up. Fixes: ebeb8c82ffaf ("syscalls/x86: Use 'struct pt_regs' based syscall calling for IA32_EMULATION and x32") Suggested-by: Arnd Bergmann Signed-off-by: Richard Palethorpe Signed-off-by: Nikolay Borisov Signed-off-by: Thomas Gleixner Reviewed-by: Arnd Bergmann Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240110130122.3836513-1-nik.borisov@suse.com Link: https://lore.kernel.org/ltp/20210921130127.24131-1-rpalethorpe@suse.com/ --- arch/x86/include/asm/syscall_wrapper.h | 25 +++++++++++++++++++++---- include/linux/syscalls.h | 1 + 2 files changed, 22 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index 21f9407be5d3..7e88705e907f 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -58,12 +58,29 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); ,,regs->di,,regs->si,,regs->dx \ ,,regs->r10,,regs->r8,,regs->r9) \ + +/* SYSCALL_PT_ARGS is Adapted from s390x */ +#define SYSCALL_PT_ARG6(m, t1, t2, t3, t4, t5, t6) \ + SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5), m(t6, (regs->bp)) +#define SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5) \ + SYSCALL_PT_ARG4(m, t1, t2, t3, t4), m(t5, (regs->di)) +#define SYSCALL_PT_ARG4(m, t1, t2, t3, t4) \ + SYSCALL_PT_ARG3(m, t1, t2, t3), m(t4, (regs->si)) +#define SYSCALL_PT_ARG3(m, t1, t2, t3) \ + SYSCALL_PT_ARG2(m, t1, t2), m(t3, (regs->dx)) +#define SYSCALL_PT_ARG2(m, t1, t2) \ + SYSCALL_PT_ARG1(m, t1), m(t2, (regs->cx)) +#define SYSCALL_PT_ARG1(m, t1) m(t1, (regs->bx)) +#define SYSCALL_PT_ARGS(x, ...) SYSCALL_PT_ARG##x(__VA_ARGS__) + +#define __SC_COMPAT_CAST(t, a) \ + (__typeof(__builtin_choose_expr(__TYPE_IS_L(t), 0, 0U))) \ + (unsigned int)a + /* Mapping of registers to parameters for syscalls on i386 */ #define SC_IA32_REGS_TO_ARGS(x, ...) \ - __MAP(x,__SC_ARGS \ - ,,(unsigned int)regs->bx,,(unsigned int)regs->cx \ - ,,(unsigned int)regs->dx,,(unsigned int)regs->si \ - ,,(unsigned int)regs->di,,(unsigned int)regs->bp) + SYSCALL_PT_ARGS(x, __SC_COMPAT_CAST, \ + __MAP(x, __SC_TYPE, __VA_ARGS__)) \ #define __SYS_STUB0(abi, name) \ long __##abi##_##name(const struct pt_regs *regs); \ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index cdba4d0c6d4a..77eb9b0e7685 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -128,6 +128,7 @@ struct mnt_id_req; #define __TYPE_IS_LL(t) (__TYPE_AS(t, 0LL) || __TYPE_AS(t, 0ULL)) #define __SC_LONG(t, a) __typeof(__builtin_choose_expr(__TYPE_IS_LL(t), 0LL, 0L)) a #define __SC_CAST(t, a) (__force t) a +#define __SC_TYPE(t, a) t #define __SC_ARGS(t, a) a #define __SC_TEST(t, a) (void)BUILD_BUG_ON_ZERO(!__TYPE_IS_LL(t) && sizeof(t) > sizeof(long)) -- cgit v1.2.3 From 2f8c7c3715f2c6fb51a4ecc0905c04dd78a3da29 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 24 Jan 2024 13:24:24 +0000 Subject: spi: Raise limit on number of chip selects As reported by Guenter the limit we've got on the number of chip selects is set too low for some systems, raise the limit. We should really remove the hard coded limit but this is needed as a fix so let's do the simple thing and raise the limit for now. Fixes: 4d8ff6b0991d ("spi: Add multi-cs memories support in SPI core") Reported-by: Guenter Roeck Suggested-by: Guenter Roeck Signed-off-by: Mark Brown Link: https://msgid.link/r/20240124-spi-multi-cs-max-v2-1-df6fc5ab1abc@kernel.org Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 471fe2ff9066..600fbd5daf68 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -21,7 +21,7 @@ #include /* Max no. of CS supported per spi device */ -#define SPI_CS_CNT_MAX 4 +#define SPI_CS_CNT_MAX 16 struct dma_chan; struct software_node; -- cgit v1.2.3 From c4608d1bf7c6536d1a3d233eb21e50678681564e Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Wed, 20 Dec 2023 22:59:43 -0800 Subject: mm: mmap: map MAP_STACK to VM_NOHUGEPAGE commit efa7df3e3bb5 ("mm: align larger anonymous mappings on THP boundaries") incured regression for stress-ng pthread benchmark [1]. It is because THP get allocated to pthread's stack area much more possible than before. Pthread's stack area is allocated by mmap without VM_GROWSDOWN or VM_GROWSUP flag, so kernel can't tell whether it is a stack area or not. The MAP_STACK flag is used to mark the stack area, but it is a no-op on Linux. Mapping MAP_STACK to VM_NOHUGEPAGE to prevent from allocating THP for such stack area. With this change the stack area looks like: fffd18e10000-fffd19610000 rw-p 00000000 00:00 0 Size: 8192 kB KernelPageSize: 4 kB MMUPageSize: 4 kB Rss: 12 kB Pss: 12 kB Pss_Dirty: 12 kB Shared_Clean: 0 kB Shared_Dirty: 0 kB Private_Clean: 0 kB Private_Dirty: 12 kB Referenced: 12 kB Anonymous: 12 kB KSM: 0 kB LazyFree: 0 kB AnonHugePages: 0 kB ShmemPmdMapped: 0 kB FilePmdMapped: 0 kB Shared_Hugetlb: 0 kB Private_Hugetlb: 0 kB Swap: 0 kB SwapPss: 0 kB Locked: 0 kB THPeligible: 0 VmFlags: rd wr mr mw me ac nh The "nh" flag is set. [1] https://lore.kernel.org/linux-mm/202312192310.56367035-oliver.sang@intel.com/ Link: https://lkml.kernel.org/r/20231221065943.2803551-2-shy828301@gmail.com Fixes: efa7df3e3bb5 ("mm: align larger anonymous mappings on THP boundaries") Signed-off-by: Yang Shi Reported-by: kernel test robot Tested-by: Oliver Sang Reviewed-by: Yin Fengwei Cc: Rik van Riel Cc: Matthew Wilcox Cc: Christopher Lameter Cc: Huang, Ying Cc: Signed-off-by: Andrew Morton --- include/linux/mman.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mman.h b/include/linux/mman.h index 40d94411d492..dc7048824be8 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -156,6 +156,7 @@ calc_vm_flag_bits(unsigned long flags) return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | + _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | arch_calc_vm_flag_bits(flags); } -- cgit v1.2.3 From f6564fce256a3944aa1bc76cb3c40e792d97c1eb Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 18 Jan 2024 11:59:14 +0100 Subject: mm, kmsan: fix infinite recursion due to RCU critical section Alexander Potapenko writes in [1]: "For every memory access in the code instrumented by KMSAN we call kmsan_get_metadata() to obtain the metadata for the memory being accessed. For virtual memory the metadata pointers are stored in the corresponding `struct page`, therefore we need to call virt_to_page() to get them. According to the comment in arch/x86/include/asm/page.h, virt_to_page(kaddr) returns a valid pointer iff virt_addr_valid(kaddr) is true, so KMSAN needs to call virt_addr_valid() as well. To avoid recursion, kmsan_get_metadata() must not call instrumented code, therefore ./arch/x86/include/asm/kmsan.h forks parts of arch/x86/mm/physaddr.c to check whether a virtual address is valid or not. But the introduction of rcu_read_lock() to pfn_valid() added instrumented RCU API calls to virt_to_page_or_null(), which is called by kmsan_get_metadata(), so there is an infinite recursion now. I do not think it is correct to stop that recursion by doing kmsan_enter_runtime()/kmsan_exit_runtime() in kmsan_get_metadata(): that would prevent instrumented functions called from within the runtime from tracking the shadow values, which might introduce false positives." Fix the issue by switching pfn_valid() to the _sched() variant of rcu_read_lock/unlock(), which does not require calling into RCU. Given the critical section in pfn_valid() is very small, this is a reasonable trade-off (with preemptible RCU). KMSAN further needs to be careful to suppress calls into the scheduler, which would be another source of recursion. This can be done by wrapping the call to pfn_valid() into preempt_disable/enable_no_resched(). The downside is that this sacrifices breaking scheduling guarantees; however, a kernel compiled with KMSAN has already given up any performance guarantees due to being heavily instrumented. Note, KMSAN code already disables tracing via Makefile, and since mmzone.h is included, it is not necessary to use the notrace variant, which is generally preferred in all other cases. Link: https://lkml.kernel.org/r/20240115184430.2710652-1-glider@google.com [1] Link: https://lkml.kernel.org/r/20240118110022.2538350-1-elver@google.com Fixes: 5ec8e8ea8b77 ("mm/sparsemem: fix race in accessing memory_section->usage") Signed-off-by: Marco Elver Reported-by: Alexander Potapenko Reported-by: syzbot+93a9e8a3dea8d6085e12@syzkaller.appspotmail.com Reviewed-by: Alexander Potapenko Tested-by: Alexander Potapenko Cc: Charan Teja Kalla Cc: Borislav Petkov (AMD) Cc: Dave Hansen Cc: Dmitry Vyukov Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- arch/x86/include/asm/kmsan.h | 17 ++++++++++++++++- include/linux/mmzone.h | 6 +++--- 2 files changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/kmsan.h b/arch/x86/include/asm/kmsan.h index 8fa6ac0e2d76..d91b37f5b4bb 100644 --- a/arch/x86/include/asm/kmsan.h +++ b/arch/x86/include/asm/kmsan.h @@ -64,6 +64,7 @@ static inline bool kmsan_virt_addr_valid(void *addr) { unsigned long x = (unsigned long)addr; unsigned long y = x - __START_KERNEL_map; + bool ret; /* use the carry flag to determine if x was < __START_KERNEL_map */ if (unlikely(x > y)) { @@ -79,7 +80,21 @@ static inline bool kmsan_virt_addr_valid(void *addr) return false; } - return pfn_valid(x >> PAGE_SHIFT); + /* + * pfn_valid() relies on RCU, and may call into the scheduler on exiting + * the critical section. However, this would result in recursion with + * KMSAN. Therefore, disable preemption here, and re-enable preemption + * below while suppressing reschedules to avoid recursion. + * + * Note, this sacrifices occasionally breaking scheduling guarantees. + * Although, a kernel compiled with KMSAN has already given up on any + * performance guarantees due to being heavily instrumented. + */ + preempt_disable(); + ret = pfn_valid(x >> PAGE_SHIFT); + preempt_enable_no_resched(); + + return ret; } #endif /* !MODULE */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 4ed33b127821..a497f189d988 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -2013,9 +2013,9 @@ static inline int pfn_valid(unsigned long pfn) if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __pfn_to_section(pfn); - rcu_read_lock(); + rcu_read_lock_sched(); if (!valid_section(ms)) { - rcu_read_unlock(); + rcu_read_unlock_sched(); return 0; } /* @@ -2023,7 +2023,7 @@ static inline int pfn_valid(unsigned long pfn) * the entire section-sized span. */ ret = early_section(ms) || pfn_section_valid(ms, pfn); - rcu_read_unlock(); + rcu_read_unlock_sched(); return ret; } -- cgit v1.2.3 From 5a287d3d2b9de2b3e747132c615599907ba5c3c1 Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Fri, 26 Jan 2024 19:45:31 +0100 Subject: lsm: fix default return value of the socket_getpeersec_*() hooks For these hooks the true "neutral" value is -EOPNOTSUPP, which is currently what is returned when no LSM provides this hook and what LSMs return when there is no security context set on the socket. Correct the value in and adjust the dispatch functions in security/security.c to avoid issues when the BPF LSM is enabled. Cc: stable@vger.kernel.org Fixes: 98e828a0650f ("security: Refactor declaration of LSM hooks") Signed-off-by: Ondrej Mosnacek [PM: subject line tweak] Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 4 ++-- security/security.c | 31 +++++++++++++++++++++++++++---- 2 files changed, 29 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 185924c56378..76458b6d53da 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -315,9 +315,9 @@ LSM_HOOK(int, 0, socket_getsockopt, struct socket *sock, int level, int optname) LSM_HOOK(int, 0, socket_setsockopt, struct socket *sock, int level, int optname) LSM_HOOK(int, 0, socket_shutdown, struct socket *sock, int how) LSM_HOOK(int, 0, socket_sock_rcv_skb, struct sock *sk, struct sk_buff *skb) -LSM_HOOK(int, 0, socket_getpeersec_stream, struct socket *sock, +LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_stream, struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) -LSM_HOOK(int, 0, socket_getpeersec_dgram, struct socket *sock, +LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_dgram, struct socket *sock, struct sk_buff *skb, u32 *secid) LSM_HOOK(int, 0, sk_alloc_security, struct sock *sk, int family, gfp_t priority) LSM_HOOK(void, LSM_RET_VOID, sk_free_security, struct sock *sk) diff --git a/security/security.c b/security/security.c index 6196ccaba433..3aaad75c9ce8 100644 --- a/security/security.c +++ b/security/security.c @@ -4624,8 +4624,20 @@ EXPORT_SYMBOL(security_sock_rcv_skb); int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) { - return call_int_hook(socket_getpeersec_stream, -ENOPROTOOPT, sock, - optval, optlen, len); + struct security_hook_list *hp; + int rc; + + /* + * Only one module will provide a security context. + */ + hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_stream, + list) { + rc = hp->hook.socket_getpeersec_stream(sock, optval, optlen, + len); + if (rc != LSM_RET_DEFAULT(socket_getpeersec_stream)) + return rc; + } + return LSM_RET_DEFAULT(socket_getpeersec_stream); } /** @@ -4645,8 +4657,19 @@ int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { - return call_int_hook(socket_getpeersec_dgram, -ENOPROTOOPT, sock, - skb, secid); + struct security_hook_list *hp; + int rc; + + /* + * Only one module will provide a security context. + */ + hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_dgram, + list) { + rc = hp->hook.socket_getpeersec_dgram(sock, skb, secid); + if (rc != LSM_RET_DEFAULT(socket_getpeersec_dgram)) + return rc; + } + return LSM_RET_DEFAULT(socket_getpeersec_dgram); } EXPORT_SYMBOL(security_socket_getpeersec_dgram); -- cgit v1.2.3 From 764ad6b02777d77dca3659ca490f0898aa593670 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Wed, 24 Jan 2024 12:26:59 +0100 Subject: HID: bpf: use __bpf_kfunc instead of noinline Follow the docs at Documentation/bpf/kfuncs.rst: - declare the function with `__bpf_kfunc` - disables missing prototype warnings, which allows to remove them from include/linux/hid-bpf.h Removing the prototypes is not an issue because we currently have to redeclare them when writing the BPF program. They will eventually be generated by bpftool directly AFAIU. Link: https://lore.kernel.org/r/20240124-b4-hid-bpf-fixes-v2-3-052520b1e5e6@kernel.org Signed-off-by: Benjamin Tissoires --- drivers/hid/bpf/hid_bpf_dispatch.c | 18 +++++++++++++----- include/linux/hid_bpf.h | 11 ----------- 2 files changed, 13 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c index 7903c8638e81..470ae2c29c94 100644 --- a/drivers/hid/bpf/hid_bpf_dispatch.c +++ b/drivers/hid/bpf/hid_bpf_dispatch.c @@ -143,6 +143,9 @@ u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *s } EXPORT_SYMBOL_GPL(call_hid_bpf_rdesc_fixup); +/* Disables missing prototype warnings */ +__bpf_kfunc_start_defs(); + /** * hid_bpf_get_data - Get the kernel memory pointer associated with the context @ctx * @@ -152,7 +155,7 @@ EXPORT_SYMBOL_GPL(call_hid_bpf_rdesc_fixup); * * @returns %NULL on error, an %__u8 memory pointer on success */ -noinline __u8 * +__bpf_kfunc __u8 * hid_bpf_get_data(struct hid_bpf_ctx *ctx, unsigned int offset, const size_t rdwr_buf_size) { struct hid_bpf_ctx_kern *ctx_kern; @@ -167,6 +170,7 @@ hid_bpf_get_data(struct hid_bpf_ctx *ctx, unsigned int offset, const size_t rdwr return ctx_kern->data + offset; } +__bpf_kfunc_end_defs(); /* * The following set contains all functions we agree BPF programs @@ -274,6 +278,9 @@ static int do_hid_bpf_attach_prog(struct hid_device *hdev, int prog_fd, struct b return fd; } +/* Disables missing prototype warnings */ +__bpf_kfunc_start_defs(); + /** * hid_bpf_attach_prog - Attach the given @prog_fd to the given HID device * @@ -286,7 +293,7 @@ static int do_hid_bpf_attach_prog(struct hid_device *hdev, int prog_fd, struct b * is pinned to the BPF file system). */ /* called from syscall */ -noinline int +__bpf_kfunc int hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, __u32 flags) { struct hid_device *hdev; @@ -338,7 +345,7 @@ hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, __u32 flags) * * @returns A pointer to &struct hid_bpf_ctx on success, %NULL on error. */ -noinline struct hid_bpf_ctx * +__bpf_kfunc struct hid_bpf_ctx * hid_bpf_allocate_context(unsigned int hid_id) { struct hid_device *hdev; @@ -371,7 +378,7 @@ hid_bpf_allocate_context(unsigned int hid_id) * @ctx: the HID-BPF context to release * */ -noinline void +__bpf_kfunc void hid_bpf_release_context(struct hid_bpf_ctx *ctx) { struct hid_bpf_ctx_kern *ctx_kern; @@ -397,7 +404,7 @@ hid_bpf_release_context(struct hid_bpf_ctx *ctx) * * @returns %0 on success, a negative error code otherwise. */ -noinline int +__bpf_kfunc int hid_bpf_hw_request(struct hid_bpf_ctx *ctx, __u8 *buf, size_t buf__sz, enum hid_report_type rtype, enum hid_class_request reqtype) { @@ -465,6 +472,7 @@ hid_bpf_hw_request(struct hid_bpf_ctx *ctx, __u8 *buf, size_t buf__sz, kfree(dma_data); return ret; } +__bpf_kfunc_end_defs(); /* our HID-BPF entrypoints */ BTF_SET8_START(hid_bpf_fmodret_ids) diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h index 840cd254172d..7118ac28d468 100644 --- a/include/linux/hid_bpf.h +++ b/include/linux/hid_bpf.h @@ -77,17 +77,6 @@ enum hid_bpf_attach_flags { int hid_bpf_device_event(struct hid_bpf_ctx *ctx); int hid_bpf_rdesc_fixup(struct hid_bpf_ctx *ctx); -/* Following functions are kfunc that we export to BPF programs */ -/* available everywhere in HID-BPF */ -__u8 *hid_bpf_get_data(struct hid_bpf_ctx *ctx, unsigned int offset, const size_t __sz); - -/* only available in syscall */ -int hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, __u32 flags); -int hid_bpf_hw_request(struct hid_bpf_ctx *ctx, __u8 *buf, size_t buf__sz, - enum hid_report_type rtype, enum hid_class_request reqtype); -struct hid_bpf_ctx *hid_bpf_allocate_context(unsigned int hid_id); -void hid_bpf_release_context(struct hid_bpf_ctx *ctx); - /* * Below is HID internal */ -- cgit v1.2.3 From 97f7cf1cd80eeed3b7c808b7c12463295c751001 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 29 Jan 2024 10:57:01 +0100 Subject: netfilter: ipset: fix performance regression in swap operation The patch "netfilter: ipset: fix race condition between swap/destroy and kernel side add/del/test", commit 28628fa9 fixes a race condition. But the synchronize_rcu() added to the swap function unnecessarily slows it down: it can safely be moved to destroy and use call_rcu() instead. Eric Dumazet pointed out that simply calling the destroy functions as rcu callback does not work: sets with timeout use garbage collectors which need cancelling at destroy which can wait. Therefore the destroy functions are split into two: cancelling garbage collectors safely at executing the command received by netlink and moving the remaining part only into the rcu callback. Link: https://lore.kernel.org/lkml/C0829B10-EAA6-4809-874E-E1E9C05A8D84@automattic.com/ Fixes: 28628fa952fe ("netfilter: ipset: fix race condition between swap/destroy and kernel side add/del/test") Reported-by: Ale Crismani Reported-by: David Wang <00107082@163.com> Tested-by: David Wang <00107082@163.com> Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 4 ++++ net/netfilter/ipset/ip_set_bitmap_gen.h | 14 ++++++++++--- net/netfilter/ipset/ip_set_core.c | 37 +++++++++++++++++++++++++-------- net/netfilter/ipset/ip_set_hash_gen.h | 15 ++++++++++--- net/netfilter/ipset/ip_set_list_set.c | 13 +++++++++--- 5 files changed, 65 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index e8c350a3ade1..e9f4f845d760 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -186,6 +186,8 @@ struct ip_set_type_variant { /* Return true if "b" set is the same as "a" * according to the create set parameters */ bool (*same_set)(const struct ip_set *a, const struct ip_set *b); + /* Cancel ongoing garbage collectors before destroying the set*/ + void (*cancel_gc)(struct ip_set *set); /* Region-locking is used */ bool region_lock; }; @@ -242,6 +244,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type); /* A generic IP set */ struct ip_set { + /* For call_cru in destroy */ + struct rcu_head rcu; /* The name of the set */ char name[IPSET_MAXNAMELEN]; /* Lock protecting the set data */ diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 21f7860e8fa1..cb48a2b9cb9f 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -30,6 +30,7 @@ #define mtype_del IPSET_TOKEN(MTYPE, _del) #define mtype_list IPSET_TOKEN(MTYPE, _list) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype MTYPE #define get_ext(set, map, id) ((map)->extensions + ((set)->dsize * (id))) @@ -59,9 +60,6 @@ mtype_destroy(struct ip_set *set) { struct mtype *map = set->data; - if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&map->gc); - if (set->dsize && set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set); ip_set_free(map->members); @@ -290,6 +288,15 @@ mtype_gc(struct timer_list *t) add_timer(&map->gc); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct mtype *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + del_timer_sync(&map->gc); +} + static const struct ip_set_type_variant mtype = { .kadt = mtype_kadt, .uadt = mtype_uadt, @@ -303,6 +310,7 @@ static const struct ip_set_type_variant mtype = { .head = mtype_head, .list = mtype_list, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, }; #endif /* __IP_SET_BITMAP_IP_GEN_H */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 4c133e06be1d..bcaad9c009fe 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1182,6 +1182,14 @@ ip_set_destroy_set(struct ip_set *set) kfree(set); } +static void +ip_set_destroy_set_rcu(struct rcu_head *head) +{ + struct ip_set *set = container_of(head, struct ip_set, rcu); + + ip_set_destroy_set(set); +} + static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const attr[]) { @@ -1193,8 +1201,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, if (unlikely(protocol_min_failed(attr))) return -IPSET_ERR_PROTOCOL; - /* Must wait for flush to be really finished in list:set */ - rcu_barrier(); /* Commands are serialized and references are * protected by the ip_set_ref_lock. @@ -1206,8 +1212,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, * counter, so if it's already zero, we can proceed * without holding the lock. */ - read_lock_bh(&ip_set_ref_lock); if (!attr[IPSET_ATTR_SETNAME]) { + /* Must wait for flush to be really finished in list:set */ + rcu_barrier(); + read_lock_bh(&ip_set_ref_lock); for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); if (s && (s->ref || s->ref_netlink)) { @@ -1221,6 +1229,8 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, s = ip_set(inst, i); if (s) { ip_set(inst, i) = NULL; + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); ip_set_destroy_set(s); } } @@ -1228,6 +1238,9 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, inst->is_destroyed = false; } else { u32 flags = flag_exist(info->nlh); + u16 features = 0; + + read_lock_bh(&ip_set_ref_lock); s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]), &i); if (!s) { @@ -1238,10 +1251,16 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, ret = -IPSET_ERR_BUSY; goto out; } + features = s->type->features; ip_set(inst, i) = NULL; read_unlock_bh(&ip_set_ref_lock); - - ip_set_destroy_set(s); + if (features & IPSET_TYPE_NAME) { + /* Must wait for flush to be really finished */ + rcu_barrier(); + } + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); + call_rcu(&s->rcu, ip_set_destroy_set_rcu); } return 0; out: @@ -1394,9 +1413,6 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info, ip_set(inst, to_id) = from; write_unlock_bh(&ip_set_ref_lock); - /* Make sure all readers of the old set pointers are completed. */ - synchronize_rcu(); - return 0; } @@ -2409,8 +2425,11 @@ ip_set_fini(void) { nf_unregister_sockopt(&so_set); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); - unregister_pernet_subsys(&ip_set_net_ops); + + /* Wait for call_rcu() in destroy */ + rcu_barrier(); + pr_debug("these are the famous last words\n"); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index cbf80da9a01c..1136510521a8 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -222,6 +222,7 @@ static const union nf_inet_addr zeromask = {}; #undef mtype_gc_do #undef mtype_gc #undef mtype_gc_init +#undef mtype_cancel_gc #undef mtype_variant #undef mtype_data_match @@ -266,6 +267,7 @@ static const union nf_inet_addr zeromask = {}; #define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) #define mtype_data_match IPSET_TOKEN(MTYPE, _data_match) @@ -450,9 +452,6 @@ mtype_destroy(struct ip_set *set) struct htype *h = set->data; struct list_head *l, *lt; - if (SET_WITH_TIMEOUT(set)) - cancel_delayed_work_sync(&h->gc.dwork); - mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true); list_for_each_safe(l, lt, &h->ad) { list_del(l); @@ -599,6 +598,15 @@ mtype_gc_init(struct htable_gc *gc) queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct htype *h = set->data; + + if (SET_WITH_TIMEOUT(set)) + cancel_delayed_work_sync(&h->gc.dwork); +} + static int mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags); @@ -1441,6 +1449,7 @@ static const struct ip_set_type_variant mtype_variant = { .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, .region_lock = true, }; diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index e162636525cf..6c3f28bc59b3 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -426,9 +426,6 @@ list_set_destroy(struct ip_set *set) struct list_set *map = set->data; struct set_elem *e, *n; - if (SET_WITH_TIMEOUT(set)) - timer_shutdown_sync(&map->gc); - list_for_each_entry_safe(e, n, &map->members, list) { list_del(&e->list); ip_set_put_byindex(map->net, e->id); @@ -545,6 +542,15 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b) a->extensions == b->extensions; } +static void +list_set_cancel_gc(struct ip_set *set) +{ + struct list_set *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + timer_shutdown_sync(&map->gc); +} + static const struct ip_set_type_variant set_variant = { .kadt = list_set_kadt, .uadt = list_set_uadt, @@ -558,6 +564,7 @@ static const struct ip_set_type_variant set_variant = { .head = list_set_head, .list = list_set_list, .same_set = list_set_same_set, + .cancel_gc = list_set_cancel_gc, }; static void -- cgit v1.2.3