diff options
Diffstat (limited to 'include/asm-generic')
-rw-r--r-- | include/asm-generic/Kbuild | 1 | ||||
-rw-r--r-- | include/asm-generic/io.h | 10 | ||||
-rw-r--r-- | include/asm-generic/iomap.h | 36 | ||||
-rw-r--r-- | include/asm-generic/mcs_spinlock.h | 6 | ||||
-rw-r--r-- | include/asm-generic/memory_model.h | 5 | ||||
-rw-r--r-- | include/asm-generic/module.h | 8 | ||||
-rw-r--r-- | include/asm-generic/mshyperv.h | 72 | ||||
-rw-r--r-- | include/asm-generic/percpu.h | 39 | ||||
-rw-r--r-- | include/asm-generic/rqspinlock.h | 250 | ||||
-rw-r--r-- | include/asm-generic/rwonce.h | 10 | ||||
-rw-r--r-- | include/asm-generic/sections.h | 2 | ||||
-rw-r--r-- | include/asm-generic/tlb.h | 45 | ||||
-rw-r--r-- | include/asm-generic/vdso/vsyscall.h | 27 | ||||
-rw-r--r-- | include/asm-generic/vmlinux.lds.h | 49 |
14 files changed, 421 insertions, 139 deletions
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild index 1b43c3a77012..8675b7b4ad23 100644 --- a/include/asm-generic/Kbuild +++ b/include/asm-generic/Kbuild @@ -45,6 +45,7 @@ mandatory-y += pci.h mandatory-y += percpu.h mandatory-y += pgalloc.h mandatory-y += preempt.h +mandatory-y += rqspinlock.h mandatory-y += runtime-const.h mandatory-y += rwonce.h mandatory-y += sections.h diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index a5cbbf3e26ec..11abad6c87e1 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -1111,7 +1111,7 @@ void __iomem *generic_ioremap_prot(phys_addr_t phys_addr, size_t size, pgprot_t prot); void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, - unsigned long prot); + pgprot_t prot); void iounmap(volatile void __iomem *addr); void generic_iounmap(volatile void __iomem *addr); @@ -1120,7 +1120,7 @@ void generic_iounmap(volatile void __iomem *addr); static inline void __iomem *ioremap(phys_addr_t addr, size_t size) { /* _PAGE_IOREMAP needs to be supplied by the architecture */ - return ioremap_prot(addr, size, _PAGE_IOREMAP); + return ioremap_prot(addr, size, __pgprot(_PAGE_IOREMAP)); } #endif #endif /* !CONFIG_MMU || CONFIG_GENERIC_IOREMAP */ @@ -1212,7 +1212,7 @@ static inline void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) #ifndef memset_io /** - * memset_io Set a range of I/O memory to a constant value + * memset_io - Set a range of I/O memory to a constant value * @addr: The beginning of the I/O-memory range to set * @val: The value to set the memory to * @count: The number of bytes to set @@ -1224,7 +1224,7 @@ void memset_io(volatile void __iomem *addr, int val, size_t count); #ifndef memcpy_fromio /** - * memcpy_fromio Copy a block of data from I/O memory + * memcpy_fromio - Copy a block of data from I/O memory * @dst: The (RAM) destination for the copy * @src: The (I/O memory) source for the data * @count: The number of bytes to copy @@ -1236,7 +1236,7 @@ void memcpy_fromio(void *dst, const volatile void __iomem *src, size_t count); #ifndef memcpy_toio /** - * memcpy_toio Copy a block of data into I/O memory + * memcpy_toio - Copy a block of data into I/O memory * @dst: The (I/O memory) destination for the copy * @src: The (RAM) source for the data * @count: The number of bytes to copy diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h index 196087a8126e..9f3f25d7fc58 100644 --- a/include/asm-generic/iomap.h +++ b/include/asm-generic/iomap.h @@ -31,42 +31,22 @@ extern unsigned int ioread16(const void __iomem *); extern unsigned int ioread16be(const void __iomem *); extern unsigned int ioread32(const void __iomem *); extern unsigned int ioread32be(const void __iomem *); -#ifdef CONFIG_64BIT -extern u64 ioread64(const void __iomem *); -extern u64 ioread64be(const void __iomem *); -#endif -#ifdef readq -#define ioread64_lo_hi ioread64_lo_hi -#define ioread64_hi_lo ioread64_hi_lo -#define ioread64be_lo_hi ioread64be_lo_hi -#define ioread64be_hi_lo ioread64be_hi_lo -extern u64 ioread64_lo_hi(const void __iomem *addr); -extern u64 ioread64_hi_lo(const void __iomem *addr); -extern u64 ioread64be_lo_hi(const void __iomem *addr); -extern u64 ioread64be_hi_lo(const void __iomem *addr); -#endif +extern u64 __ioread64_lo_hi(const void __iomem *addr); +extern u64 __ioread64_hi_lo(const void __iomem *addr); +extern u64 __ioread64be_lo_hi(const void __iomem *addr); +extern u64 __ioread64be_hi_lo(const void __iomem *addr); extern void iowrite8(u8, void __iomem *); extern void iowrite16(u16, void __iomem *); extern void iowrite16be(u16, void __iomem *); extern void iowrite32(u32, void __iomem *); extern void iowrite32be(u32, void __iomem *); -#ifdef CONFIG_64BIT -extern void iowrite64(u64, void __iomem *); -extern void iowrite64be(u64, void __iomem *); -#endif -#ifdef writeq -#define iowrite64_lo_hi iowrite64_lo_hi -#define iowrite64_hi_lo iowrite64_hi_lo -#define iowrite64be_lo_hi iowrite64be_lo_hi -#define iowrite64be_hi_lo iowrite64be_hi_lo -extern void iowrite64_lo_hi(u64 val, void __iomem *addr); -extern void iowrite64_hi_lo(u64 val, void __iomem *addr); -extern void iowrite64be_lo_hi(u64 val, void __iomem *addr); -extern void iowrite64be_hi_lo(u64 val, void __iomem *addr); -#endif +extern void __iowrite64_lo_hi(u64 val, void __iomem *addr); +extern void __iowrite64_hi_lo(u64 val, void __iomem *addr); +extern void __iowrite64be_lo_hi(u64 val, void __iomem *addr); +extern void __iowrite64be_hi_lo(u64 val, void __iomem *addr); /* * "string" versions of the above. Note that they diff --git a/include/asm-generic/mcs_spinlock.h b/include/asm-generic/mcs_spinlock.h index 10cd4ffc6ba2..39c94012b88a 100644 --- a/include/asm-generic/mcs_spinlock.h +++ b/include/asm-generic/mcs_spinlock.h @@ -1,6 +1,12 @@ #ifndef __ASM_MCS_SPINLOCK_H #define __ASM_MCS_SPINLOCK_H +struct mcs_spinlock { + struct mcs_spinlock *next; + int locked; /* 1 if lock acquired */ + int count; /* nesting count, see qspinlock.c */ +}; + /* * Architectures can define their own: * diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h index 6d1fb6162ac1..a3b5029aebbd 100644 --- a/include/asm-generic/memory_model.h +++ b/include/asm-generic/memory_model.h @@ -19,11 +19,12 @@ #define __page_to_pfn(page) ((unsigned long)((page) - mem_map) + \ ARCH_PFN_OFFSET) +/* avoid <linux/mm.h> include hell */ +extern unsigned long max_mapnr; + #ifndef pfn_valid static inline int pfn_valid(unsigned long pfn) { - /* avoid <linux/mm.h> include hell */ - extern unsigned long max_mapnr; unsigned long pfn_offset = ARCH_PFN_OFFSET; return pfn >= pfn_offset && (pfn - pfn_offset) < max_mapnr; diff --git a/include/asm-generic/module.h b/include/asm-generic/module.h index 98e1541b72b7..a8622501b975 100644 --- a/include/asm-generic/module.h +++ b/include/asm-generic/module.h @@ -19,12 +19,8 @@ struct mod_arch_specific #define Elf_Dyn Elf64_Dyn #define Elf_Ehdr Elf64_Ehdr #define Elf_Addr Elf64_Addr -#ifdef CONFIG_MODULES_USE_ELF_REL #define Elf_Rel Elf64_Rel -#endif -#ifdef CONFIG_MODULES_USE_ELF_RELA #define Elf_Rela Elf64_Rela -#endif #define ELF_R_TYPE(X) ELF64_R_TYPE(X) #define ELF_R_SYM(X) ELF64_R_SYM(X) @@ -36,12 +32,8 @@ struct mod_arch_specific #define Elf_Dyn Elf32_Dyn #define Elf_Ehdr Elf32_Ehdr #define Elf_Addr Elf32_Addr -#ifdef CONFIG_MODULES_USE_ELF_REL #define Elf_Rel Elf32_Rel -#endif -#ifdef CONFIG_MODULES_USE_ELF_RELA #define Elf_Rela Elf32_Rela -#endif #define ELF_R_TYPE(X) ELF32_R_TYPE(X) #define ELF_R_SYM(X) ELF32_R_SYM(X) #endif diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index a7bbe504e4f3..ccccb1cbf7df 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -28,9 +28,15 @@ #define VTPM_BASE_ADDRESS 0xfed40000 +enum hv_partition_type { + HV_PARTITION_TYPE_GUEST, + HV_PARTITION_TYPE_ROOT, +}; + struct ms_hyperv_info { u32 features; u32 priv_high; + u32 ext_features; u32 misc_features; u32 hints; u32 nested_features; @@ -58,15 +64,32 @@ struct ms_hyperv_info { }; extern struct ms_hyperv_info ms_hyperv; extern bool hv_nested; +extern u64 hv_current_partition_id; +extern enum hv_partition_type hv_curr_partition_type; extern void * __percpu *hyperv_pcpu_input_arg; extern void * __percpu *hyperv_pcpu_output_arg; -extern u64 hv_do_hypercall(u64 control, void *inputaddr, void *outputaddr); -extern u64 hv_do_fast_hypercall8(u16 control, u64 input8); +u64 hv_do_hypercall(u64 control, void *inputaddr, void *outputaddr); +u64 hv_do_fast_hypercall8(u16 control, u64 input8); +u64 hv_do_fast_hypercall16(u16 control, u64 input1, u64 input2); + bool hv_isolation_type_snp(void); bool hv_isolation_type_tdx(void); +/* + * On architectures where Hyper-V doesn't support AEOI (e.g., ARM64), + * it doesn't provide a recommendation flag and AEOI must be disabled. + */ +static inline bool hv_recommend_using_aeoi(void) +{ +#ifdef HV_DEPRECATING_AEOI_RECOMMENDED + return !(ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED); +#else + return false; +#endif +} + static inline struct hv_proximity_domain_info hv_numa_node_to_pxm_info(int node) { struct hv_proximity_domain_info pxm_info = {}; @@ -185,12 +208,11 @@ void hv_setup_kexec_handler(void (*handler)(void)); void hv_remove_kexec_handler(void); void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs)); void hv_remove_crash_handler(void); +void hv_setup_mshv_handler(void (*handler)(void)); extern int vmbus_interrupt; extern int vmbus_irq; -extern bool hv_root_partition; - #if IS_ENABLED(CONFIG_HYPERV) /* * Hypervisor's notion of virtual processor ID is different from @@ -207,10 +229,12 @@ extern u64 (*hv_read_reference_counter)(void); #define VP_INVAL U32_MAX int __init hv_common_init(void); +void __init hv_get_partition_id(void); void __init hv_common_free(void); void __init ms_hyperv_late_init(void); int hv_common_cpu_init(unsigned int cpu); int hv_common_cpu_die(unsigned int cpu); +void hv_identify_partition_type(void); void *hv_alloc_hyperv_page(void); void *hv_alloc_hyperv_zeroed_page(void); @@ -291,6 +315,20 @@ static inline int cpumask_to_vpset_skip(struct hv_vpset *vpset, return __cpumask_to_vpset(vpset, cpus, func); } +#define _hv_status_fmt(fmt) "%s: Hyper-V status: %#x = %s: " fmt +#define hv_status_printk(level, status, fmt, ...) \ +do { \ + u64 __status = (status); \ + pr_##level(_hv_status_fmt(fmt), __func__, hv_result(__status), \ + hv_result_to_string(__status), ##__VA_ARGS__); \ +} while (0) +#define hv_status_err(status, fmt, ...) \ + hv_status_printk(err, status, fmt, ##__VA_ARGS__) +#define hv_status_debug(status, fmt, ...) \ + hv_status_printk(debug, status, fmt, ##__VA_ARGS__) + +const char *hv_result_to_string(u64 hv_status); +int hv_result_to_errno(u64 status); void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die); bool hv_is_hyperv_initialized(void); bool hv_is_hibernation_supported(void); @@ -303,6 +341,7 @@ void hyperv_cleanup(void); bool hv_query_ext_cap(u64 cap_query); void hv_setup_dma_ops(struct device *dev, bool coherent); #else /* CONFIG_HYPERV */ +static inline void hv_identify_partition_type(void) {} static inline bool hv_is_hyperv_initialized(void) { return false; } static inline bool hv_is_hibernation_supported(void) { return false; } static inline void hyperv_cleanup(void) {} @@ -314,4 +353,29 @@ static inline enum hv_isolation_type hv_get_isolation_type(void) } #endif /* CONFIG_HYPERV */ +#if IS_ENABLED(CONFIG_MSHV_ROOT) +static inline bool hv_root_partition(void) +{ + return hv_curr_partition_type == HV_PARTITION_TYPE_ROOT; +} +int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages); +int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id); +int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags); + +#else /* CONFIG_MSHV_ROOT */ +static inline bool hv_root_partition(void) { return false; } +static inline int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages) +{ + return -EOPNOTSUPP; +} +static inline int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id) +{ + return -EOPNOTSUPP; +} +static inline int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_MSHV_ROOT */ + #endif diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h index 94cbd50cc870..02aeca21479a 100644 --- a/include/asm-generic/percpu.h +++ b/include/asm-generic/percpu.h @@ -6,6 +6,19 @@ #include <linux/threads.h> #include <linux/percpu-defs.h> +/* + * __percpu_qual is the qualifier for the percpu named address space. + * + * Most arches use generic named address space for percpu variables but + * some arches define percpu variables in different named address space + * (on the x86 arch, percpu variable may be declared as being relative + * to the %fs or %gs segments using __seg_fs or __seg_gs named address + * space qualifier). + */ +#ifndef __percpu_qual +# define __percpu_qual +#endif + #ifdef CONFIG_SMP /* @@ -74,7 +87,7 @@ do { \ #define raw_cpu_generic_add_return(pcp, val) \ ({ \ - typeof(pcp) *__p = raw_cpu_ptr(&(pcp)); \ + TYPEOF_UNQUAL(pcp) *__p = raw_cpu_ptr(&(pcp)); \ \ *__p += val; \ *__p; \ @@ -82,8 +95,8 @@ do { \ #define raw_cpu_generic_xchg(pcp, nval) \ ({ \ - typeof(pcp) *__p = raw_cpu_ptr(&(pcp)); \ - typeof(pcp) __ret; \ + TYPEOF_UNQUAL(pcp) *__p = raw_cpu_ptr(&(pcp)); \ + TYPEOF_UNQUAL(pcp) __ret; \ __ret = *__p; \ *__p = nval; \ __ret; \ @@ -91,7 +104,7 @@ do { \ #define __cpu_fallback_try_cmpxchg(pcp, ovalp, nval, _cmpxchg) \ ({ \ - typeof(pcp) __val, __old = *(ovalp); \ + TYPEOF_UNQUAL(pcp) __val, __old = *(ovalp); \ __val = _cmpxchg(pcp, __old, nval); \ if (__val != __old) \ *(ovalp) = __val; \ @@ -100,8 +113,8 @@ do { \ #define raw_cpu_generic_try_cmpxchg(pcp, ovalp, nval) \ ({ \ - typeof(pcp) *__p = raw_cpu_ptr(&(pcp)); \ - typeof(pcp) __val = *__p, ___old = *(ovalp); \ + TYPEOF_UNQUAL(pcp) *__p = raw_cpu_ptr(&(pcp)); \ + TYPEOF_UNQUAL(pcp) __val = *__p, ___old = *(ovalp); \ bool __ret; \ if (__val == ___old) { \ *__p = nval; \ @@ -115,14 +128,14 @@ do { \ #define raw_cpu_generic_cmpxchg(pcp, oval, nval) \ ({ \ - typeof(pcp) __old = (oval); \ + TYPEOF_UNQUAL(pcp) __old = (oval); \ raw_cpu_generic_try_cmpxchg(pcp, &__old, nval); \ __old; \ }) #define __this_cpu_generic_read_nopreempt(pcp) \ ({ \ - typeof(pcp) ___ret; \ + TYPEOF_UNQUAL(pcp) ___ret; \ preempt_disable_notrace(); \ ___ret = READ_ONCE(*raw_cpu_ptr(&(pcp))); \ preempt_enable_notrace(); \ @@ -131,7 +144,7 @@ do { \ #define __this_cpu_generic_read_noirq(pcp) \ ({ \ - typeof(pcp) ___ret; \ + TYPEOF_UNQUAL(pcp) ___ret; \ unsigned long ___flags; \ raw_local_irq_save(___flags); \ ___ret = raw_cpu_generic_read(pcp); \ @@ -141,7 +154,7 @@ do { \ #define this_cpu_generic_read(pcp) \ ({ \ - typeof(pcp) __ret; \ + TYPEOF_UNQUAL(pcp) __ret; \ if (__native_word(pcp)) \ __ret = __this_cpu_generic_read_nopreempt(pcp); \ else \ @@ -160,7 +173,7 @@ do { \ #define this_cpu_generic_add_return(pcp, val) \ ({ \ - typeof(pcp) __ret; \ + TYPEOF_UNQUAL(pcp) __ret; \ unsigned long __flags; \ raw_local_irq_save(__flags); \ __ret = raw_cpu_generic_add_return(pcp, val); \ @@ -170,7 +183,7 @@ do { \ #define this_cpu_generic_xchg(pcp, nval) \ ({ \ - typeof(pcp) __ret; \ + TYPEOF_UNQUAL(pcp) __ret; \ unsigned long __flags; \ raw_local_irq_save(__flags); \ __ret = raw_cpu_generic_xchg(pcp, nval); \ @@ -190,7 +203,7 @@ do { \ #define this_cpu_generic_cmpxchg(pcp, oval, nval) \ ({ \ - typeof(pcp) __ret; \ + TYPEOF_UNQUAL(pcp) __ret; \ unsigned long __flags; \ raw_local_irq_save(__flags); \ __ret = raw_cpu_generic_cmpxchg(pcp, oval, nval); \ diff --git a/include/asm-generic/rqspinlock.h b/include/asm-generic/rqspinlock.h new file mode 100644 index 000000000000..6d4244d643df --- /dev/null +++ b/include/asm-generic/rqspinlock.h @@ -0,0 +1,250 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Resilient Queued Spin Lock + * + * (C) Copyright 2024-2025 Meta Platforms, Inc. and affiliates. + * + * Authors: Kumar Kartikeya Dwivedi <memxor@gmail.com> + */ +#ifndef __ASM_GENERIC_RQSPINLOCK_H +#define __ASM_GENERIC_RQSPINLOCK_H + +#include <linux/types.h> +#include <vdso/time64.h> +#include <linux/percpu.h> +#ifdef CONFIG_QUEUED_SPINLOCKS +#include <asm/qspinlock.h> +#endif + +struct rqspinlock { + union { + atomic_t val; + u32 locked; + }; +}; + +/* Even though this is same as struct rqspinlock, we need to emit a distinct + * type in BTF for BPF programs. + */ +struct bpf_res_spin_lock { + u32 val; +}; + +struct qspinlock; +#ifdef CONFIG_QUEUED_SPINLOCKS +typedef struct qspinlock rqspinlock_t; +#else +typedef struct rqspinlock rqspinlock_t; +#endif + +extern int resilient_tas_spin_lock(rqspinlock_t *lock); +#ifdef CONFIG_QUEUED_SPINLOCKS +extern int resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val); +#endif + +#ifndef resilient_virt_spin_lock_enabled +static __always_inline bool resilient_virt_spin_lock_enabled(void) +{ + return false; +} +#endif + +#ifndef resilient_virt_spin_lock +static __always_inline int resilient_virt_spin_lock(rqspinlock_t *lock) +{ + return 0; +} +#endif + +/* + * Default timeout for waiting loops is 0.25 seconds + */ +#define RES_DEF_TIMEOUT (NSEC_PER_SEC / 4) + +/* + * Choose 31 as it makes rqspinlock_held cacheline-aligned. + */ +#define RES_NR_HELD 31 + +struct rqspinlock_held { + int cnt; + void *locks[RES_NR_HELD]; +}; + +DECLARE_PER_CPU_ALIGNED(struct rqspinlock_held, rqspinlock_held_locks); + +static __always_inline void grab_held_lock_entry(void *lock) +{ + int cnt = this_cpu_inc_return(rqspinlock_held_locks.cnt); + + if (unlikely(cnt > RES_NR_HELD)) { + /* Still keep the inc so we decrement later. */ + return; + } + + /* + * Implied compiler barrier in per-CPU operations; otherwise we can have + * the compiler reorder inc with write to table, allowing interrupts to + * overwrite and erase our write to the table (as on interrupt exit it + * will be reset to NULL). + * + * It is fine for cnt inc to be reordered wrt remote readers though, + * they won't observe our entry until the cnt update is visible, that's + * all. + */ + this_cpu_write(rqspinlock_held_locks.locks[cnt - 1], lock); +} + +/* + * We simply don't support out-of-order unlocks, and keep the logic simple here. + * The verifier prevents BPF programs from unlocking out-of-order, and the same + * holds for in-kernel users. + * + * It is possible to run into misdetection scenarios of AA deadlocks on the same + * CPU, and missed ABBA deadlocks on remote CPUs if this function pops entries + * out of order (due to lock A, lock B, unlock A, unlock B) pattern. The correct + * logic to preserve right entries in the table would be to walk the array of + * held locks and swap and clear out-of-order entries, but that's too + * complicated and we don't have a compelling use case for out of order unlocking. + */ +static __always_inline void release_held_lock_entry(void) +{ + struct rqspinlock_held *rqh = this_cpu_ptr(&rqspinlock_held_locks); + + if (unlikely(rqh->cnt > RES_NR_HELD)) + goto dec; + WRITE_ONCE(rqh->locks[rqh->cnt - 1], NULL); +dec: + /* + * Reordering of clearing above with inc and its write in + * grab_held_lock_entry that came before us (in same acquisition + * attempt) is ok, we either see a valid entry or NULL when it's + * visible. + * + * But this helper is invoked when we unwind upon failing to acquire the + * lock. Unlike the unlock path which constitutes a release store after + * we clear the entry, we need to emit a write barrier here. Otherwise, + * we may have a situation as follows: + * + * <error> for lock B + * release_held_lock_entry + * + * try_cmpxchg_acquire for lock A + * grab_held_lock_entry + * + * Lack of any ordering means reordering may occur such that dec, inc + * are done before entry is overwritten. This permits a remote lock + * holder of lock B (which this CPU failed to acquire) to now observe it + * as being attempted on this CPU, and may lead to misdetection (if this + * CPU holds a lock it is attempting to acquire, leading to false ABBA + * diagnosis). + * + * In case of unlock, we will always do a release on the lock word after + * releasing the entry, ensuring that other CPUs cannot hold the lock + * (and make conclusions about deadlocks) until the entry has been + * cleared on the local CPU, preventing any anomalies. Reordering is + * still possible there, but a remote CPU cannot observe a lock in our + * table which it is already holding, since visibility entails our + * release store for the said lock has not retired. + * + * In theory we don't have a problem if the dec and WRITE_ONCE above get + * reordered with each other, we either notice an empty NULL entry on + * top (if dec succeeds WRITE_ONCE), or a potentially stale entry which + * cannot be observed (if dec precedes WRITE_ONCE). + * + * Emit the write barrier _before_ the dec, this permits dec-inc + * reordering but that is harmless as we'd have new entry set to NULL + * already, i.e. they cannot precede the NULL store above. + */ + smp_wmb(); + this_cpu_dec(rqspinlock_held_locks.cnt); +} + +#ifdef CONFIG_QUEUED_SPINLOCKS + +/** + * res_spin_lock - acquire a queued spinlock + * @lock: Pointer to queued spinlock structure + * + * Return: + * * 0 - Lock was acquired successfully. + * * -EDEADLK - Lock acquisition failed because of AA/ABBA deadlock. + * * -ETIMEDOUT - Lock acquisition failed because of timeout. + */ +static __always_inline int res_spin_lock(rqspinlock_t *lock) +{ + int val = 0; + + if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL))) { + grab_held_lock_entry(lock); + return 0; + } + return resilient_queued_spin_lock_slowpath(lock, val); +} + +#else + +#define res_spin_lock(lock) resilient_tas_spin_lock(lock) + +#endif /* CONFIG_QUEUED_SPINLOCKS */ + +static __always_inline void res_spin_unlock(rqspinlock_t *lock) +{ + struct rqspinlock_held *rqh = this_cpu_ptr(&rqspinlock_held_locks); + + if (unlikely(rqh->cnt > RES_NR_HELD)) + goto unlock; + WRITE_ONCE(rqh->locks[rqh->cnt - 1], NULL); +unlock: + /* + * Release barrier, ensures correct ordering. See release_held_lock_entry + * for details. Perform release store instead of queued_spin_unlock, + * since we use this function for test-and-set fallback as well. When we + * have CONFIG_QUEUED_SPINLOCKS=n, we clear the full 4-byte lockword. + * + * Like release_held_lock_entry, we can do the release before the dec. + * We simply care about not seeing the 'lock' in our table from a remote + * CPU once the lock has been released, which doesn't rely on the dec. + * + * Unlike smp_wmb(), release is not a two way fence, hence it is + * possible for a inc to move up and reorder with our clearing of the + * entry. This isn't a problem however, as for a misdiagnosis of ABBA, + * the remote CPU needs to hold this lock, which won't be released until + * the store below is done, which would ensure the entry is overwritten + * to NULL, etc. + */ + smp_store_release(&lock->locked, 0); + this_cpu_dec(rqspinlock_held_locks.cnt); +} + +#ifdef CONFIG_QUEUED_SPINLOCKS +#define raw_res_spin_lock_init(lock) ({ *(lock) = (rqspinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; }) +#else +#define raw_res_spin_lock_init(lock) ({ *(lock) = (rqspinlock_t){0}; }) +#endif + +#define raw_res_spin_lock(lock) \ + ({ \ + int __ret; \ + preempt_disable(); \ + __ret = res_spin_lock(lock); \ + if (__ret) \ + preempt_enable(); \ + __ret; \ + }) + +#define raw_res_spin_unlock(lock) ({ res_spin_unlock(lock); preempt_enable(); }) + +#define raw_res_spin_lock_irqsave(lock, flags) \ + ({ \ + int __ret; \ + local_irq_save(flags); \ + __ret = raw_res_spin_lock(lock); \ + if (__ret) \ + local_irq_restore(flags); \ + __ret; \ + }) + +#define raw_res_spin_unlock_irqrestore(lock, flags) ({ raw_res_spin_unlock(lock); local_irq_restore(flags); }) + +#endif /* __ASM_GENERIC_RQSPINLOCK_H */ diff --git a/include/asm-generic/rwonce.h b/include/asm-generic/rwonce.h index 8d0a6280e982..52b969c7cef9 100644 --- a/include/asm-generic/rwonce.h +++ b/include/asm-generic/rwonce.h @@ -79,10 +79,18 @@ unsigned long __read_once_word_nocheck(const void *addr) (typeof(x))__read_once_word_nocheck(&(x)); \ }) -static __no_kasan_or_inline +static __no_sanitize_or_inline unsigned long read_word_at_a_time(const void *addr) { + /* open-coded instrument_read(addr, 1) */ kasan_check_read(addr, 1); + kcsan_check_read(addr, 1); + + /* + * This load can race with concurrent stores to out-of-bounds memory, + * but READ_ONCE() can't be used because it requires higher alignment + * than plain loads in arm64 builds with LTO. + */ return *(unsigned long *)addr; } diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index c768de6f19a9..0755bc39b0d8 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -39,7 +39,7 @@ extern char __init_begin[], __init_end[]; extern char _sinittext[], _einittext[]; extern char __start_ro_after_init[], __end_ro_after_init[]; extern char _end[]; -extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[]; +extern char __per_cpu_start[], __per_cpu_end[]; extern char __kprobes_text_start[], __kprobes_text_end[]; extern char __entry_text_start[], __entry_text_end[]; extern char __start_rodata[], __end_rodata[]; diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index e402aef79c93..88a42973fa47 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -67,22 +67,21 @@ * * See also MMU_GATHER_TABLE_FREE and MMU_GATHER_RCU_TABLE_FREE. * - * - tlb_remove_page() / __tlb_remove_page() - * - tlb_remove_page_size() / __tlb_remove_page_size() - * - __tlb_remove_folio_pages() + * - tlb_remove_page() / tlb_remove_page_size() + * - __tlb_remove_folio_pages() / __tlb_remove_page_size() + * - __tlb_remove_folio_pages_size() * - * __tlb_remove_page_size() is the basic primitive that queues a page for - * freeing. __tlb_remove_page() assumes PAGE_SIZE. Both will return a - * boolean indicating if the queue is (now) full and a call to - * tlb_flush_mmu() is required. + * __tlb_remove_folio_pages_size() is the basic primitive that queues pages + * for freeing. It will return a boolean indicating if the queue is (now) + * full and a call to tlb_flush_mmu() is required. * * tlb_remove_page() and tlb_remove_page_size() imply the call to * tlb_flush_mmu() when required and has no return value. * - * __tlb_remove_folio_pages() is similar to __tlb_remove_page(), however, - * instead of removing a single page, remove the given number of consecutive - * pages that are all part of the same (large) folio: just like calling - * __tlb_remove_page() on each page individually. + * __tlb_remove_folio_pages() is similar to __tlb_remove_page_size(), + * however, instead of removing a single page, assume PAGE_SIZE and remove + * the given number of consecutive pages that are all part of the + * same (large) folio. * * - tlb_change_page_size() * @@ -228,10 +227,10 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page); */ static inline void tlb_remove_table(struct mmu_gather *tlb, void *table) { - struct page *page = (struct page *)table; + struct ptdesc *ptdesc = (struct ptdesc *)table; - pagetable_dtor(page_ptdesc(page)); - tlb_remove_page(tlb, page); + pagetable_dtor(ptdesc); + tlb_remove_page(tlb, ptdesc_page(ptdesc)); } #endif /* CONFIG_MMU_GATHER_TABLE_FREE */ @@ -489,32 +488,16 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb, tlb_flush_mmu(tlb); } -static __always_inline bool __tlb_remove_page(struct mmu_gather *tlb, - struct page *page, bool delay_rmap) -{ - return __tlb_remove_page_size(tlb, page, delay_rmap, PAGE_SIZE); -} - -/* tlb_remove_page - * Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when - * required. - */ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) { return tlb_remove_page_size(tlb, page, PAGE_SIZE); } -static inline void tlb_remove_ptdesc(struct mmu_gather *tlb, void *pt) +static inline void tlb_remove_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt) { tlb_remove_table(tlb, pt); } -/* Like tlb_remove_ptdesc, but for page-like page directories. */ -static inline void tlb_remove_page_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt) -{ - tlb_remove_page(tlb, ptdesc_page(pt)); -} - static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { diff --git a/include/asm-generic/vdso/vsyscall.h b/include/asm-generic/vdso/vsyscall.h index 01dafd604188..b550afa15ecd 100644 --- a/include/asm-generic/vdso/vsyscall.h +++ b/include/asm-generic/vdso/vsyscall.h @@ -4,24 +4,35 @@ #ifndef __ASSEMBLY__ -#ifndef __arch_get_k_vdso_data -static __always_inline struct vdso_data *__arch_get_k_vdso_data(void) +#ifdef CONFIG_GENERIC_VDSO_DATA_STORE + +#ifndef __arch_get_vdso_u_time_data +static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void) { - return NULL; + return &vdso_u_time_data; } -#endif /* __arch_get_k_vdso_data */ +#endif + +#ifndef __arch_get_vdso_u_rng_data +static __always_inline const struct vdso_rng_data *__arch_get_vdso_u_rng_data(void) +{ + return &vdso_u_rng_data; +} +#endif + +#endif /* CONFIG_GENERIC_VDSO_DATA_STORE */ #ifndef __arch_update_vsyscall -static __always_inline void __arch_update_vsyscall(struct vdso_data *vdata) +static __always_inline void __arch_update_vsyscall(struct vdso_time_data *vdata) { } #endif /* __arch_update_vsyscall */ -#ifndef __arch_sync_vdso_data -static __always_inline void __arch_sync_vdso_data(struct vdso_data *vdata) +#ifndef __arch_sync_vdso_time_data +static __always_inline void __arch_sync_vdso_time_data(struct vdso_time_data *vdata) { } -#endif /* __arch_sync_vdso_data */ +#endif /* __arch_sync_vdso_time_data */ #endif /* !__ASSEMBLY__ */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 0d5b186abee8..58a635a6d5bd 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -385,6 +385,11 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) . = ALIGN(PAGE_SIZE); \ __nosave_end = .; +#define CACHE_HOT_DATA(align) \ + . = ALIGN(align); \ + *(SORT_BY_ALIGNMENT(.data..hot.*)) \ + . = ALIGN(align); + #define PAGE_ALIGNED_DATA(page_align) \ . = ALIGN(page_align); \ *(.data..page_aligned) \ @@ -404,7 +409,6 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) __start_init_stack = .; \ init_thread_union = .; \ init_stack = .; \ - KEEP(*(.data..init_task)) \ KEEP(*(.data..init_thread_info)) \ . = __start_init_stack + THREAD_SIZE; \ __end_init_stack = .; @@ -1062,10 +1066,13 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) */ #define PERCPU_INPUT(cacheline) \ __per_cpu_start = .; \ - *(.data..percpu..first) \ . = ALIGN(PAGE_SIZE); \ *(.data..percpu..page_aligned) \ . = ALIGN(cacheline); \ + __per_cpu_hot_start = .; \ + *(SORT_BY_ALIGNMENT(.data..percpu..hot.*)) \ + __per_cpu_hot_end = .; \ + . = ALIGN(cacheline); \ *(.data..percpu..read_mostly) \ . = ALIGN(cacheline); \ *(.data..percpu) \ @@ -1074,52 +1081,17 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) __per_cpu_end = .; /** - * PERCPU_VADDR - define output section for percpu area + * PERCPU_SECTION - define output section for percpu area * @cacheline: cacheline size - * @vaddr: explicit base address (optional) - * @phdr: destination PHDR (optional) * * Macro which expands to output section for percpu area. * * @cacheline is used to align subsections to avoid false cacheline * sharing between subsections for different purposes. - * - * If @vaddr is not blank, it specifies explicit base address and all - * percpu symbols will be offset from the given address. If blank, - * @vaddr always equals @laddr + LOAD_OFFSET. - * - * @phdr defines the output PHDR to use if not blank. Be warned that - * output PHDR is sticky. If @phdr is specified, the next output - * section in the linker script will go there too. @phdr should have - * a leading colon. - * - * Note that this macros defines __per_cpu_load as an absolute symbol. - * If there is no need to put the percpu section at a predetermined - * address, use PERCPU_SECTION. - */ -#define PERCPU_VADDR(cacheline, vaddr, phdr) \ - __per_cpu_load = .; \ - .data..percpu vaddr : AT(__per_cpu_load - LOAD_OFFSET) { \ - PERCPU_INPUT(cacheline) \ - } phdr \ - . = __per_cpu_load + SIZEOF(.data..percpu); - -/** - * PERCPU_SECTION - define output section for percpu area, simple version - * @cacheline: cacheline size - * - * Align to PAGE_SIZE and outputs output section for percpu area. This - * macro doesn't manipulate @vaddr or @phdr and __per_cpu_load and - * __per_cpu_start will be identical. - * - * This macro is equivalent to ALIGN(PAGE_SIZE); PERCPU_VADDR(@cacheline,,) - * except that __per_cpu_load is defined as a relative symbol against - * .data..percpu which is required for relocatable x86_32 configuration. */ #define PERCPU_SECTION(cacheline) \ . = ALIGN(PAGE_SIZE); \ .data..percpu : AT(ADDR(.data..percpu) - LOAD_OFFSET) { \ - __per_cpu_load = .; \ PERCPU_INPUT(cacheline) \ } @@ -1148,6 +1120,7 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) INIT_TASK_DATA(inittask) \ NOSAVE_DATA \ PAGE_ALIGNED_DATA(pagealigned) \ + CACHE_HOT_DATA(cacheline) \ CACHELINE_ALIGNED_DATA(cacheline) \ READ_MOSTLY_DATA(cacheline) \ DATA_DATA \ |