diff options
Diffstat (limited to 'arch/um/include')
50 files changed, 605 insertions, 650 deletions
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild index b2d834a29f3a..1b9b82bbe322 100644 --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -1,14 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 -generic-y += bpf_perf_event.h generic-y += bug.h generic-y += compat.h -generic-y += current.h generic-y += device.h generic-y += dma-mapping.h generic-y += emergency-restart.h generic-y += exec.h -generic-y += extable.h -generic-y += fb.h generic-y += ftrace.h generic-y += hw_irq.h generic-y += irq_regs.h @@ -16,11 +12,12 @@ generic-y += irq_work.h generic-y += kdebug.h generic-y += mcs_spinlock.h generic-y += mmiowb.h +generic-y += module.h generic-y += module.lds.h -generic-y += param.h generic-y += parport.h generic-y += percpu.h generic-y += preempt.h +generic-y += runtime-const.h generic-y += softirq_stack.h generic-y += switch_to.h generic-y += topology.h @@ -28,3 +25,4 @@ generic-y += trace_clock.h generic-y += kprobes.h generic-y += mm_hooks.h generic-y += vga.h +generic-y += video.h diff --git a/arch/um/include/asm/asm-prototypes.h b/arch/um/include/asm/asm-prototypes.h index 5898a26daa0d..408b31d59127 100644 --- a/arch/um/include/asm/asm-prototypes.h +++ b/arch/um/include/asm/asm-prototypes.h @@ -1 +1,6 @@ #include <asm-generic/asm-prototypes.h> +#include <asm/checksum.h> + +#ifdef CONFIG_UML_X86 +extern void cmpxchg8b_emu(void); +#endif diff --git a/arch/um/include/asm/bpf_perf_event.h b/arch/um/include/asm/bpf_perf_event.h new file mode 100644 index 000000000000..287221342d2c --- /dev/null +++ b/arch/um/include/asm/bpf_perf_event.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * asm-generic/bpf_perf_event.h is part of the uapi headers, but since + * arch/um has no uapi of its on, we can't use the "generic-y" + * Kbuild rule to generate the wrapper + */ + +#include <asm-generic/bpf_perf_event.h> diff --git a/arch/um/include/asm/bugs.h b/arch/um/include/asm/bugs.h deleted file mode 100644 index 4473942a0839..000000000000 --- a/arch/um/include/asm/bugs.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __UM_BUGS_H -#define __UM_BUGS_H - -void check_bugs(void); - -#endif diff --git a/arch/um/include/asm/cpufeature.h b/arch/um/include/asm/cpufeature.h index 4b6d1b526bc1..4354f6984271 100644 --- a/arch/um/include/asm/cpufeature.h +++ b/arch/um/include/asm/cpufeature.h @@ -4,7 +4,7 @@ #include <asm/processor.h> -#if defined(__KERNEL__) && !defined(__ASSEMBLY__) +#if defined(__KERNEL__) && !defined(__ASSEMBLER__) #include <asm/asm.h> #include <linux/bitops.h> @@ -38,8 +38,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; #define this_cpu_has(bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ - x86_this_cpu_test_bit(bit, \ - (unsigned long __percpu *)&cpu_info.x86_capability)) + x86_this_cpu_test_bit(bit, cpu_info.x86_capability)) /* * This macro is for detection of features which need kernel @@ -75,7 +74,7 @@ extern void setup_clear_cpu_cap(unsigned int bit); */ static __always_inline bool _static_cpu_has(u16 bit) { - asm_volatile_goto("1: jmp 6f\n" + asm goto("1: jmp 6f\n" "2:\n" ".skip -(((5f-4f) - (2b-1b)) > 0) * " "((5f-4f) - (2b-1b)),0x90\n" @@ -138,5 +137,5 @@ t_no: #define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \ boot_cpu_data.x86_model -#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */ +#endif /* defined(__KERNEL__) && !defined(__ASSEMBLER__) */ #endif /* _ASM_UM_CPUFEATURE_H */ diff --git a/arch/um/include/asm/current.h b/arch/um/include/asm/current.h new file mode 100644 index 000000000000..159a29b3d4cc --- /dev/null +++ b/arch/um/include/asm/current.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_CURRENT_H +#define __ASM_CURRENT_H + +#include <linux/compiler.h> +#include <linux/threads.h> + +#ifndef __ASSEMBLER__ + +#include <shared/smp.h> + +struct task_struct; +extern struct task_struct *cpu_tasks[NR_CPUS]; + +static __always_inline struct task_struct *get_current(void) +{ + return cpu_tasks[uml_curr_cpu()]; +} + +#define current get_current() + +#endif /* __ASSEMBLER__ */ + +#endif /* __ASM_CURRENT_H */ diff --git a/arch/um/include/asm/fixmap.h b/arch/um/include/asm/fixmap.h deleted file mode 100644 index 2efac5827188..000000000000 --- a/arch/um/include/asm/fixmap.h +++ /dev/null @@ -1,56 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __UM_FIXMAP_H -#define __UM_FIXMAP_H - -#include <asm/processor.h> -#include <asm/archparam.h> -#include <asm/page.h> -#include <linux/threads.h> - -/* - * Here we define all the compile-time 'special' virtual - * addresses. The point is to have a constant address at - * compile time, but to set the physical address only - * in the boot process. We allocate these special addresses - * from the end of virtual memory (0xfffff000) backwards. - * Also this lets us do fail-safe vmalloc(), we - * can guarantee that these special addresses and - * vmalloc()-ed addresses never overlap. - * - * these 'compile-time allocated' memory buffers are - * fixed-size 4k pages. (or larger if used with an increment - * highger than 1) use fixmap_set(idx,phys) to associate - * physical memory with fixmap indices. - * - * TLB entries of such buffers will not be flushed across - * task switches. - */ - -/* - * on UP currently we will have no trace of the fixmap mechanizm, - * no page table allocations, etc. This might change in the - * future, say framebuffers for the console driver(s) could be - * fix-mapped? - */ -enum fixed_addresses { - __end_of_fixed_addresses -}; - -extern void __set_fixmap (enum fixed_addresses idx, - unsigned long phys, pgprot_t flags); - -/* - * used by vmalloc.c. - * - * Leave one empty page between vmalloc'ed areas and - * the start of the fixmap, and leave one page empty - * at the top of mem.. - */ - -#define FIXADDR_TOP (TASK_SIZE - 2 * PAGE_SIZE) -#define FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) - -#include <asm-generic/fixmap.h> - -#endif diff --git a/arch/um/include/asm/fpu/api.h b/arch/um/include/asm/fpu/api.h index 71bfd9ef3938..3abf67c83c40 100644 --- a/arch/um/include/asm/fpu/api.h +++ b/arch/um/include/asm/fpu/api.h @@ -2,6 +2,8 @@ #ifndef _ASM_UM_FPU_API_H #define _ASM_UM_FPU_API_H +#include <linux/types.h> + /* Copyright (c) 2020 Cambridge Greys Ltd * Copyright (c) 2020 Red Hat Inc. * A set of "dummy" defines to allow the direct inclusion diff --git a/arch/um/include/asm/hardirq.h b/arch/um/include/asm/hardirq.h index 52e2c36267a9..8de71752a9b8 100644 --- a/arch/um/include/asm/hardirq.h +++ b/arch/um/include/asm/hardirq.h @@ -2,8 +2,30 @@ #ifndef __ASM_UM_HARDIRQ_H #define __ASM_UM_HARDIRQ_H -#include <asm-generic/hardirq.h> +#include <linux/cache.h> +#include <linux/threads.h> #define __ARCH_IRQ_EXIT_IRQS_DISABLED 1 +typedef struct { + unsigned int __softirq_pending; +#if IS_ENABLED(CONFIG_SMP) + unsigned int irq_resched_count; + unsigned int irq_call_count; +#endif +} ____cacheline_aligned irq_cpustat_t; + +DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); + +#define __ARCH_IRQ_STAT + +#define inc_irq_stat(member) this_cpu_inc(irq_stat.member) + +#include <linux/irq.h> + +static inline void ack_bad_irq(unsigned int irq) +{ + pr_crit("unexpected IRQ trap at vector %02x\n", irq); +} + #endif /* __ASM_UM_HARDIRQ_H */ diff --git a/arch/um/include/asm/irq.h b/arch/um/include/asm/irq.h index 749dfe8512e8..36dbedd1af48 100644 --- a/arch/um/include/asm/irq.h +++ b/arch/um/include/asm/irq.h @@ -13,17 +13,18 @@ #define TELNETD_IRQ 8 #define XTERM_IRQ 9 #define RANDOM_IRQ 10 +#define SIGCHLD_IRQ 11 #ifdef CONFIG_UML_NET_VECTOR -#define VECTOR_BASE_IRQ (RANDOM_IRQ + 1) +#define VECTOR_BASE_IRQ (SIGCHLD_IRQ + 1) #define VECTOR_IRQ_SPACE 8 #define UM_FIRST_DYN_IRQ (VECTOR_IRQ_SPACE + VECTOR_BASE_IRQ) #else -#define UM_FIRST_DYN_IRQ (RANDOM_IRQ + 1) +#define UM_FIRST_DYN_IRQ (SIGCHLD_IRQ + 1) #endif diff --git a/arch/um/include/asm/irqflags.h b/arch/um/include/asm/irqflags.h index 1e69ef5bc35e..31e49e0894c5 100644 --- a/arch/um/include/asm/irqflags.h +++ b/arch/um/include/asm/irqflags.h @@ -2,7 +2,7 @@ #ifndef __UM_IRQFLAGS_H #define __UM_IRQFLAGS_H -extern int signals_enabled; +int um_get_signals(void); int um_set_signals(int enable); void block_signals(void); void unblock_signals(void); @@ -10,7 +10,7 @@ void unblock_signals(void); #define arch_local_save_flags arch_local_save_flags static inline unsigned long arch_local_save_flags(void) { - return signals_enabled; + return um_get_signals(); } #define arch_local_irq_restore arch_local_irq_restore diff --git a/arch/um/include/asm/kasan.h b/arch/um/include/asm/kasan.h index 0d6547f4ec85..81bcdc0f962e 100644 --- a/arch/um/include/asm/kasan.h +++ b/arch/um/include/asm/kasan.h @@ -24,12 +24,6 @@ #ifdef CONFIG_KASAN void kasan_init(void); -void kasan_map_memory(void *start, unsigned long len); -extern int kasan_um_is_ready; - -#ifdef CONFIG_STATIC_LINK -#define kasan_arch_is_ready() (kasan_um_is_ready) -#endif #else static inline void kasan_init(void) { } #endif /* CONFIG_KASAN */ diff --git a/arch/um/include/asm/mmu.h b/arch/um/include/asm/mmu.h index 5b072aba5b65..07d48738b402 100644 --- a/arch/um/include/asm/mmu.h +++ b/arch/um/include/asm/mmu.h @@ -6,19 +6,27 @@ #ifndef __ARCH_UM_MMU_H #define __ARCH_UM_MMU_H +#include "linux/types.h" +#include <linux/mutex.h> +#include <linux/spinlock.h> #include <mm_id.h> -#include <asm/mm_context.h> typedef struct mm_context { struct mm_id id; - struct uml_arch_mm_context arch; - struct page *stub_pages[2]; -} mm_context_t; + struct mutex turnstile; + + struct list_head list; -extern void __switch_mm(struct mm_id * mm_idp); + /* Address range in need of a TLB sync */ + spinlock_t sync_tlb_lock; + unsigned long sync_tlb_range_from; + unsigned long sync_tlb_range_to; +} mm_context_t; -/* Avoid tangled inclusion with asm/ldt.h */ -extern long init_new_ldt(struct mm_context *to_mm, struct mm_context *from_mm); -extern void free_ldt(struct mm_context *mm); +#define INIT_MM_CONTEXT(mm) \ + .context = { \ + .turnstile = __MUTEX_INITIALIZER(mm.context.turnstile), \ + .sync_tlb_lock = __SPIN_LOCK_INITIALIZER(mm.context.sync_tlb_lock), \ + } #endif diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h index 68e2eb9cfb47..c727e56ba116 100644 --- a/arch/um/include/asm/mmu_context.h +++ b/arch/um/include/asm/mmu_context.h @@ -13,29 +13,9 @@ #include <asm/mm_hooks.h> #include <asm/mmu.h> -extern void force_flush_all(void); - -#define activate_mm activate_mm -static inline void activate_mm(struct mm_struct *old, struct mm_struct *new) -{ - /* - * This is called by fs/exec.c and sys_unshare() - * when the new ->mm is used for the first time. - */ - __switch_mm(&new->context.id); -} - static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { - unsigned cpu = smp_processor_id(); - - if(prev != next){ - cpumask_clear_cpu(cpu, mm_cpumask(prev)); - cpumask_set_cpu(cpu, mm_cpumask(next)); - if(next != &init_mm) - __switch_mm(&next->context.id); - } } #define init_new_context init_new_context diff --git a/arch/um/include/asm/page.h b/arch/um/include/asm/page.h index cdbd9653aa14..2d363460d896 100644 --- a/arch/um/include/asm/page.h +++ b/arch/um/include/asm/page.h @@ -9,12 +9,9 @@ #include <linux/const.h> -/* PAGE_SHIFT determines the page size */ -#define PAGE_SHIFT 12 -#define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE-1)) +#include <vdso/page.h> -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ struct page; @@ -32,51 +29,35 @@ struct page; #define clear_user_page(page, vaddr, pg) clear_page(page) #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) -#if defined(CONFIG_3_LEVEL_PGTABLES) && !defined(CONFIG_64BIT) - typedef struct { unsigned long pte; } pte_t; -typedef struct { unsigned long pmd; } pmd_t; typedef struct { unsigned long pgd; } pgd_t; -#define pte_val(p) ((p).pte) -#define pte_get_bits(p, bits) ((p).pte & (bits)) -#define pte_set_bits(p, bits) ((p).pte |= (bits)) -#define pte_clear_bits(p, bits) ((p).pte &= ~(bits)) -#define pte_copy(to, from) ({ (to).pte = (from).pte; }) -#define pte_is_zero(p) (!((p).pte & ~_PAGE_NEWPAGE)) -#define pte_set_val(p, phys, prot) \ - ({ (p).pte = (phys) | pgprot_val(prot); }) +#if CONFIG_PGTABLE_LEVELS > 2 +typedef struct { unsigned long pmd; } pmd_t; #define pmd_val(x) ((x).pmd) #define __pmd(x) ((pmd_t) { (x) } ) -typedef unsigned long long phys_t; +#if CONFIG_PGTABLE_LEVELS > 3 -#else +typedef struct { unsigned long pud; } pud_t; +#define pud_val(x) ((x).pud) +#define __pud(x) ((pud_t) { (x) } ) -typedef struct { unsigned long pte; } pte_t; -typedef struct { unsigned long pgd; } pgd_t; - -#ifdef CONFIG_3_LEVEL_PGTABLES -typedef struct { unsigned long pmd; } pmd_t; -#define pmd_val(x) ((x).pmd) -#define __pmd(x) ((pmd_t) { (x) } ) -#endif +#endif /* CONFIG_PGTABLE_LEVELS > 3 */ +#endif /* CONFIG_PGTABLE_LEVELS > 2 */ #define pte_val(x) ((x).pte) - #define pte_get_bits(p, bits) ((p).pte & (bits)) #define pte_set_bits(p, bits) ((p).pte |= (bits)) #define pte_clear_bits(p, bits) ((p).pte &= ~(bits)) #define pte_copy(to, from) ((to).pte = (from).pte) -#define pte_is_zero(p) (!((p).pte & ~_PAGE_NEWPAGE)) +#define pte_is_zero(p) (!((p).pte & ~_PAGE_NEEDSYNC)) #define pte_set_val(p, phys, prot) (p).pte = (phys | pgprot_val(prot)) typedef unsigned long phys_t; -#endif - typedef struct { unsigned long pgprot; } pgprot_t; typedef struct page *pgtable_t; @@ -108,16 +89,11 @@ extern unsigned long uml_physmem; #define phys_to_pfn(p) ((p) >> PAGE_SHIFT) #define pfn_to_phys(pfn) PFN_PHYS(pfn) -#define pfn_valid(pfn) ((pfn) < max_mapnr) #define virt_addr_valid(v) pfn_valid(phys_to_pfn(__pa(v))) #include <asm-generic/memory_model.h> #include <asm-generic/getorder.h> -#endif /* __ASSEMBLY__ */ - -#ifdef CONFIG_X86_32 -#define __HAVE_ARCH_GATE_AREA 1 -#endif +#endif /* __ASSEMBLER__ */ #endif /* __UM_PAGE_H */ diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h index 8ec7cd46dd96..826ec44b58cd 100644 --- a/arch/um/include/asm/pgalloc.h +++ b/arch/um/include/asm/pgalloc.h @@ -25,20 +25,20 @@ */ extern pgd_t *pgd_alloc(struct mm_struct *); -#define __pte_free_tlb(tlb,pte, address) \ -do { \ - pgtable_pte_page_dtor(pte); \ - tlb_remove_page((tlb),(pte)); \ -} while (0) +#define __pte_free_tlb(tlb, pte, address) \ + tlb_remove_ptdesc((tlb), page_ptdesc(pte)) -#ifdef CONFIG_3_LEVEL_PGTABLES +#if CONFIG_PGTABLE_LEVELS > 2 -#define __pmd_free_tlb(tlb, pmd, address) \ -do { \ - pgtable_pmd_page_dtor(virt_to_page(pmd)); \ - tlb_remove_page((tlb),virt_to_page(pmd)); \ -} while (0) \ +#define __pmd_free_tlb(tlb, pmd, address) \ + tlb_remove_ptdesc((tlb), virt_to_ptdesc(pmd)) +#if CONFIG_PGTABLE_LEVELS > 3 + +#define __pud_free_tlb(tlb, pud, address) \ + tlb_remove_ptdesc((tlb), virt_to_ptdesc(pud)) + +#endif #endif #endif diff --git a/arch/um/include/asm/pgtable-2level.h b/arch/um/include/asm/pgtable-2level.h index 8256ecc5b919..14ec16f92ce4 100644 --- a/arch/um/include/asm/pgtable-2level.h +++ b/arch/um/include/asm/pgtable-2level.h @@ -31,13 +31,12 @@ printk("%s:%d: bad pgd %p(%08lx).\n", __FILE__, __LINE__, &(e), \ pgd_val(e)) -static inline int pgd_newpage(pgd_t pgd) { return 0; } +static inline int pgd_needsync(pgd_t pgd) { return 0; } static inline void pgd_mkuptodate(pgd_t pgd) { } #define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval)) #define pte_pfn(x) phys_to_pfn(pte_val(x)) -#define pfn_pte(pfn, prot) __pte(pfn_to_phys(pfn) | pgprot_val(prot)) #define pfn_pmd(pfn, prot) __pmd(pfn_to_phys(pfn) | pgprot_val(prot)) #endif diff --git a/arch/um/include/asm/pgtable-3level.h b/arch/um/include/asm/pgtable-4level.h index 8a5032ec231f..7a271b7b83d2 100644 --- a/arch/um/include/asm/pgtable-3level.h +++ b/arch/um/include/asm/pgtable-4level.h @@ -4,21 +4,25 @@ * Derived from include/asm-i386/pgtable.h */ -#ifndef __UM_PGTABLE_3LEVEL_H -#define __UM_PGTABLE_3LEVEL_H +#ifndef __UM_PGTABLE_4LEVEL_H +#define __UM_PGTABLE_4LEVEL_H -#include <asm-generic/pgtable-nopud.h> +#include <asm-generic/pgtable-nop4d.h> -/* PGDIR_SHIFT determines what a third-level page table entry can map */ +/* PGDIR_SHIFT determines what a fourth-level page table entry can map */ -#ifdef CONFIG_64BIT -#define PGDIR_SHIFT 30 -#else -#define PGDIR_SHIFT 31 -#endif +#define PGDIR_SHIFT 39 #define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) +/* PUD_SHIFT determines the size of the area a third-level page table can + * map + */ + +#define PUD_SHIFT 30 +#define PUD_SIZE (1UL << PUD_SHIFT) +#define PUD_MASK (~(PUD_SIZE-1)) + /* PMD_SHIFT determines the size of the area a second-level page table can * map */ @@ -32,13 +36,9 @@ */ #define PTRS_PER_PTE 512 -#ifdef CONFIG_64BIT #define PTRS_PER_PMD 512 +#define PTRS_PER_PUD 512 #define PTRS_PER_PGD 512 -#else -#define PTRS_PER_PMD 1024 -#define PTRS_PER_PGD 1024 -#endif #define USER_PTRS_PER_PGD ((TASK_SIZE + (PGDIR_SIZE - 1)) / PGDIR_SIZE) @@ -48,11 +48,14 @@ #define pmd_ERROR(e) \ printk("%s:%d: bad pmd %p(%016lx).\n", __FILE__, __LINE__, &(e), \ pmd_val(e)) +#define pud_ERROR(e) \ + printk("%s:%d: bad pud %p(%016lx).\n", __FILE__, __LINE__, &(e), \ + pud_val(e)) #define pgd_ERROR(e) \ printk("%s:%d: bad pgd %p(%016lx).\n", __FILE__, __LINE__, &(e), \ pgd_val(e)) -#define pud_none(x) (!(pud_val(x) & ~_PAGE_NEWPAGE)) +#define pud_none(x) (!(pud_val(x) & ~_PAGE_NEEDSYNC)) #define pud_bad(x) ((pud_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE) #define pud_present(x) (pud_val(x) & _PAGE_PRESENT) #define pud_populate(mm, pud, pmd) \ @@ -60,41 +63,48 @@ #define set_pud(pudptr, pudval) (*(pudptr) = (pudval)) -static inline int pgd_newpage(pgd_t pgd) +#define p4d_none(x) (!(p4d_val(x) & ~_PAGE_NEEDSYNC)) +#define p4d_bad(x) ((p4d_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE) +#define p4d_present(x) (p4d_val(x) & _PAGE_PRESENT) +#define p4d_populate(mm, p4d, pud) \ + set_p4d(p4d, __p4d(_PAGE_TABLE + __pa(pud))) + +#define set_p4d(p4dptr, p4dval) (*(p4dptr) = (p4dval)) + + +static inline int pgd_needsync(pgd_t pgd) { - return(pgd_val(pgd) & _PAGE_NEWPAGE); + return pgd_val(pgd) & _PAGE_NEEDSYNC; } -static inline void pgd_mkuptodate(pgd_t pgd) { pgd_val(pgd) &= ~_PAGE_NEWPAGE; } +static inline void pgd_mkuptodate(pgd_t pgd) { pgd_val(pgd) &= ~_PAGE_NEEDSYNC; } #define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval)) static inline void pud_clear (pud_t *pud) { - set_pud(pud, __pud(_PAGE_NEWPAGE)); + set_pud(pud, __pud(_PAGE_NEEDSYNC)); +} + +static inline void p4d_clear (p4d_t *p4d) +{ + set_p4d(p4d, __p4d(_PAGE_NEEDSYNC)); } #define pud_page(pud) phys_to_page(pud_val(pud) & PAGE_MASK) #define pud_pgtable(pud) ((pmd_t *) __va(pud_val(pud) & PAGE_MASK)) +#define p4d_page(p4d) phys_to_page(p4d_val(p4d) & PAGE_MASK) +#define p4d_pgtable(p4d) ((pud_t *) __va(p4d_val(p4d) & PAGE_MASK)) + static inline unsigned long pte_pfn(pte_t pte) { return phys_to_pfn(pte_val(pte)); } -static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) -{ - pte_t pte; - phys_t phys = pfn_to_phys(page_nr); - - pte_set_val(pte, phys, pgprot); - return pte; -} - static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { return __pmd((page_nr << PAGE_SHIFT) | pgprot_val(pgprot)); } #endif - diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index 4e3052f2671a..3b42b0f45bf6 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -8,11 +8,11 @@ #ifndef __UM_PGTABLE_H #define __UM_PGTABLE_H -#include <asm/fixmap.h> +#include <asm/page.h> +#include <linux/mm_types.h> #define _PAGE_PRESENT 0x001 -#define _PAGE_NEWPAGE 0x002 -#define _PAGE_NEWPROT 0x004 +#define _PAGE_NEEDSYNC 0x002 #define _PAGE_RW 0x020 #define _PAGE_USER 0x040 #define _PAGE_ACCESSED 0x080 @@ -21,10 +21,15 @@ #define _PAGE_PROTNONE 0x010 /* if the user mapped it with PROT_NONE; pte_present gives true */ -#ifdef CONFIG_3_LEVEL_PGTABLES -#include <asm/pgtable-3level.h> -#else +/* We borrow bit 10 to store the exclusive marker in swap PTEs. */ +#define _PAGE_SWP_EXCLUSIVE 0x400 + +#if CONFIG_PGTABLE_LEVELS == 4 +#include <asm/pgtable-4level.h> +#elif CONFIG_PGTABLE_LEVELS == 2 #include <asm/pgtable-2level.h> +#else +#error "Unsupported number of page table levels" #endif extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; @@ -40,15 +45,15 @@ extern unsigned long *empty_zero_page; * area for the same reason. ;) */ -extern unsigned long end_iomem; +#ifndef COMPILE_OFFSETS +#include <as-layout.h> /* for high_physmem */ +#endif #define VMALLOC_OFFSET (__va_space) -#define VMALLOC_START ((end_iomem + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)) -#define PKMAP_BASE ((FIXADDR_START - LAST_PKMAP * PAGE_SIZE) & PMD_MASK) -#define VMALLOC_END (FIXADDR_START-2*PAGE_SIZE) +#define VMALLOC_START ((high_physmem + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)) +#define VMALLOC_END (TASK_SIZE-2*PAGE_SIZE) #define MODULES_VADDR VMALLOC_START #define MODULES_END VMALLOC_END -#define MODULES_LEN (MODULES_VADDR - MODULES_END) #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY) #define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) @@ -75,22 +80,22 @@ extern unsigned long end_iomem; */ #define ZERO_PAGE(vaddr) virt_to_page(empty_zero_page) -#define pte_clear(mm,addr,xp) pte_set_val(*(xp), (phys_t) 0, __pgprot(_PAGE_NEWPAGE)) +#define pte_clear(mm, addr, xp) pte_set_val(*(xp), (phys_t) 0, __pgprot(_PAGE_NEEDSYNC)) -#define pmd_none(x) (!((unsigned long)pmd_val(x) & ~_PAGE_NEWPAGE)) +#define pmd_none(x) (!((unsigned long)pmd_val(x) & ~_PAGE_NEEDSYNC)) #define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE) #define pmd_present(x) (pmd_val(x) & _PAGE_PRESENT) -#define pmd_clear(xp) do { pmd_val(*(xp)) = _PAGE_NEWPAGE; } while (0) +#define pmd_clear(xp) do { pmd_val(*(xp)) = _PAGE_NEEDSYNC; } while (0) -#define pmd_newpage(x) (pmd_val(x) & _PAGE_NEWPAGE) -#define pmd_mkuptodate(x) (pmd_val(x) &= ~_PAGE_NEWPAGE) +#define pmd_needsync(x) (pmd_val(x) & _PAGE_NEEDSYNC) +#define pmd_mkuptodate(x) (pmd_val(x) &= ~_PAGE_NEEDSYNC) -#define pud_newpage(x) (pud_val(x) & _PAGE_NEWPAGE) -#define pud_mkuptodate(x) (pud_val(x) &= ~_PAGE_NEWPAGE) +#define pud_needsync(x) (pud_val(x) & _PAGE_NEEDSYNC) +#define pud_mkuptodate(x) (pud_val(x) &= ~_PAGE_NEEDSYNC) -#define p4d_newpage(x) (p4d_val(x) & _PAGE_NEWPAGE) -#define p4d_mkuptodate(x) (p4d_val(x) &= ~_PAGE_NEWPAGE) +#define p4d_needsync(x) (p4d_val(x) & _PAGE_NEEDSYNC) +#define p4d_mkuptodate(x) (p4d_val(x) &= ~_PAGE_NEEDSYNC) #define pmd_pfn(pmd) (pmd_val(pmd) >> PAGE_SHIFT) #define pmd_page(pmd) phys_to_page(pmd_val(pmd) & PAGE_MASK) @@ -141,14 +146,9 @@ static inline int pte_young(pte_t pte) return pte_get_bits(pte, _PAGE_ACCESSED); } -static inline int pte_newpage(pte_t pte) +static inline int pte_needsync(pte_t pte) { - return pte_get_bits(pte, _PAGE_NEWPAGE); -} - -static inline int pte_newprot(pte_t pte) -{ - return(pte_present(pte) && (pte_get_bits(pte, _PAGE_NEWPROT))); + return pte_get_bits(pte, _PAGE_NEEDSYNC); } /* @@ -157,12 +157,6 @@ static inline int pte_newprot(pte_t pte) * ================================= */ -static inline pte_t pte_mknewprot(pte_t pte) -{ - pte_set_bits(pte, _PAGE_NEWPROT); - return(pte); -} - static inline pte_t pte_mkclean(pte_t pte) { pte_clear_bits(pte, _PAGE_DIRTY); @@ -177,19 +171,14 @@ static inline pte_t pte_mkold(pte_t pte) static inline pte_t pte_wrprotect(pte_t pte) { - if (likely(pte_get_bits(pte, _PAGE_RW))) - pte_clear_bits(pte, _PAGE_RW); - else - return pte; - return(pte_mknewprot(pte)); + pte_clear_bits(pte, _PAGE_RW); + return pte; } static inline pte_t pte_mkread(pte_t pte) { - if (unlikely(pte_get_bits(pte, _PAGE_USER))) - return pte; pte_set_bits(pte, _PAGE_USER); - return(pte_mknewprot(pte)); + return pte; } static inline pte_t pte_mkdirty(pte_t pte) @@ -204,25 +193,21 @@ static inline pte_t pte_mkyoung(pte_t pte) return(pte); } -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t pte_mkwrite_novma(pte_t pte) { - if (unlikely(pte_get_bits(pte, _PAGE_RW))) - return pte; pte_set_bits(pte, _PAGE_RW); - return(pte_mknewprot(pte)); + return pte; } static inline pte_t pte_mkuptodate(pte_t pte) { - pte_clear_bits(pte, _PAGE_NEWPAGE); - if(pte_present(pte)) - pte_clear_bits(pte, _PAGE_NEWPROT); - return(pte); + pte_clear_bits(pte, _PAGE_NEEDSYNC); + return pte; } -static inline pte_t pte_mknewpage(pte_t pte) +static inline pte_t pte_mkneedsync(pte_t pte) { - pte_set_bits(pte, _PAGE_NEWPAGE); + pte_set_bits(pte, _PAGE_NEEDSYNC); return(pte); } @@ -230,44 +215,66 @@ static inline void set_pte(pte_t *pteptr, pte_t pteval) { pte_copy(*pteptr, pteval); - /* If it's a swap entry, it needs to be marked _PAGE_NEWPAGE so - * fix_range knows to unmap it. _PAGE_NEWPROT is specific to - * mapped pages. + /* If it's a swap entry, it needs to be marked _PAGE_NEEDSYNC so + * update_pte_range knows to unmap it. */ - *pteptr = pte_mknewpage(*pteptr); - if(pte_present(*pteptr)) *pteptr = pte_mknewprot(*pteptr); + *pteptr = pte_mkneedsync(*pteptr); } -static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *pteptr, pte_t pteval) +#define PFN_PTE_SHIFT PAGE_SHIFT + +static inline void um_tlb_mark_sync(struct mm_struct *mm, unsigned long start, + unsigned long end) { - set_pte(pteptr, pteval); + guard(spinlock_irqsave)(&mm->context.sync_tlb_lock); + + if (!mm->context.sync_tlb_range_to) { + mm->context.sync_tlb_range_from = start; + mm->context.sync_tlb_range_to = end; + } else { + if (start < mm->context.sync_tlb_range_from) + mm->context.sync_tlb_range_from = start; + if (end > mm->context.sync_tlb_range_to) + mm->context.sync_tlb_range_to = end; + } +} + +#define set_ptes set_ptes +static inline void set_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, int nr) +{ + /* Basically the default implementation */ + size_t length = nr * PAGE_SIZE; + + for (;;) { + set_pte(ptep, pte); + if (--nr == 0) + break; + ptep++; + pte = __pte(pte_val(pte) + (nr << PFN_PTE_SHIFT)); + } + + um_tlb_mark_sync(mm, addr, addr + length); } #define __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t pte_a, pte_t pte_b) { - return !((pte_val(pte_a) ^ pte_val(pte_b)) & ~_PAGE_NEWPAGE); + return !((pte_val(pte_a) ^ pte_val(pte_b)) & ~_PAGE_NEEDSYNC); } -/* - * Conversion functions: convert a page and protection to a page entry, - * and a page entry and page directory to the page they refer to. - */ - -#define phys_to_page(phys) pfn_to_page(phys_to_pfn(phys)) #define __virt_to_page(virt) phys_to_page(__pa(virt)) -#define page_to_phys(page) pfn_to_phys(page_to_pfn(page)) #define virt_to_page(addr) __virt_to_page((const unsigned long) addr) -#define mk_pte(page, pgprot) \ - ({ pte_t pte; \ - \ - pte_set_val(pte, page_to_phys(page), (pgprot)); \ - if (pte_present(pte)) \ - pte_mknewprot(pte_mknewpage(pte)); \ - pte;}) +static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) +{ + pte_t pte; + + pte_set_val(pte, pfn_to_phys(pfn), pgprot); + + return pte; +} static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { @@ -287,22 +294,45 @@ struct mm_struct; extern pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr); #define update_mmu_cache(vma,address,ptep) do {} while (0) +#define update_mmu_cache_range(vmf, vma, address, ptep, nr) do {} while (0) -/* Encode and de-code a swap entry */ +/* + * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that + * are !pte_none() && !pte_present(). + * + * Format of swap PTEs: + * + * 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 + * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 + * <--------------- offset ----------------> E < type -> 0 0 0 1 0 + * + * E is the exclusive marker that is not stored in swap entries. + * _PAGE_NEEDSYNC (bit 1) is always set to 1 in set_pte(). + */ #define __swp_type(x) (((x).val >> 5) & 0x1f) #define __swp_offset(x) ((x).val >> 11) #define __swp_entry(type, offset) \ - ((swp_entry_t) { ((type) << 5) | ((offset) << 11) }) + ((swp_entry_t) { (((type) & 0x1f) << 5) | ((offset) << 11) }) #define __pte_to_swp_entry(pte) \ ((swp_entry_t) { pte_val(pte_mkuptodate(pte)) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -/* Clear a kernel PTE and flush it from the TLB */ -#define kpte_clear_flush(ptep, vaddr) \ -do { \ - pte_clear(&init_mm, (vaddr), (ptep)); \ - __flush_tlb_one((vaddr)); \ -} while (0) +static inline bool pte_swp_exclusive(pte_t pte) +{ + return pte_get_bits(pte, _PAGE_SWP_EXCLUSIVE); +} + +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + pte_set_bits(pte, _PAGE_SWP_EXCLUSIVE); + return pte; +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + pte_clear_bits(pte, _PAGE_SWP_EXCLUSIVE); + return pte; +} #endif diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index bb5f06480da9..7854d51b6639 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -20,39 +20,29 @@ struct task_struct; struct mm_struct; struct thread_struct { - struct pt_regs regs; struct pt_regs *segv_regs; - int singlestep_syscall; - void *fault_addr; - jmp_buf *fault_catcher; struct task_struct *prev_sched; struct arch_thread arch; jmp_buf switch_buf; struct { - int op; - union { - struct { - int pid; - } fork, exec; - struct { - int (*proc)(void *); - void *arg; - } thread; - struct { - void (*proc)(void *); - void *arg; - } cb; - } u; + struct { + int (*proc)(void *); + void *arg; + } thread; } request; + + void *segv_continue; + + /* Contains variable sized FP registers */ + struct pt_regs regs; }; #define INIT_THREAD \ { \ .regs = EMPTY_REGS, \ - .fault_addr = NULL, \ .prev_sched = NULL, \ .arch = INIT_ARCH_THREAD, \ - .request = { 0 } \ + .request = { } \ } /* @@ -81,7 +71,6 @@ extern void start_thread(struct pt_regs *regs, unsigned long entry, struct cpuinfo_um { unsigned long loops_per_jiffy; - int ipi_pipe[2]; int cache_alignment; union { __u32 x86_capability[NCAPINTS + NBUGINTS]; @@ -91,11 +80,8 @@ struct cpuinfo_um { extern struct cpuinfo_um boot_cpu_data; -#define cpu_data (&boot_cpu_data) -#define current_cpu_data boot_cpu_data #define cache_line_size() (boot_cpu_data.cache_alignment) -extern unsigned long get_thread_reg(int reg, jmp_buf *buf); #define KSTK_REG(tsk, reg) get_thread_reg(reg, &tsk->thread.switch_buf) extern unsigned long __get_wchan(struct task_struct *p); diff --git a/arch/um/include/asm/ptrace-generic.h b/arch/um/include/asm/ptrace-generic.h index adf91ef553ae..86d74f9d33cf 100644 --- a/arch/um/include/asm/ptrace-generic.h +++ b/arch/um/include/asm/ptrace-generic.h @@ -6,7 +6,7 @@ #ifndef __UM_PTRACE_GENERIC_H #define __UM_PTRACE_GENERIC_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <sysdep/ptrace.h> @@ -36,6 +36,9 @@ extern long subarch_ptrace(struct task_struct *child, long request, extern unsigned long getreg(struct task_struct *child, int regno); extern int putreg(struct task_struct *child, int regno, unsigned long value); +extern int poke_user(struct task_struct *child, long addr, long data); +extern int peek_user(struct task_struct *child, long addr, long data); + extern int arch_set_tls(struct task_struct *new, unsigned long tls); extern void clear_flushed_tls(struct task_struct *task); extern int syscall_trace_enter(struct pt_regs *regs); diff --git a/arch/um/include/asm/smp.h b/arch/um/include/asm/smp.h index a8cc1d46ddcb..be1743a6ff3c 100644 --- a/arch/um/include/asm/smp.h +++ b/arch/um/include/asm/smp.h @@ -2,6 +2,19 @@ #ifndef __UM_SMP_H #define __UM_SMP_H -#define hard_smp_processor_id() 0 +#if IS_ENABLED(CONFIG_SMP) + +#include <linux/cpumask.h> +#include <shared/smp.h> + +#define raw_smp_processor_id() uml_curr_cpu() + +void arch_smp_send_reschedule(int cpu); + +void arch_send_call_function_single_ipi(int cpu); + +void arch_send_call_function_ipi_mask(const struct cpumask *mask); + +#endif /* CONFIG_SMP */ #endif diff --git a/arch/um/include/asm/syscall-generic.h b/arch/um/include/asm/syscall-generic.h index 172b74143c4b..bcd73bcfe577 100644 --- a/arch/um/include/asm/syscall-generic.h +++ b/arch/um/include/asm/syscall-generic.h @@ -21,6 +21,11 @@ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) return PT_REGS_SYSCALL_NR(regs); } +static inline void syscall_set_nr(struct task_struct *task, struct pt_regs *regs, int nr) +{ + PT_REGS_SYSCALL_NR(regs) = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { @@ -62,6 +67,20 @@ static inline void syscall_get_arguments(struct task_struct *task, *args = UPT_SYSCALL_ARG6(r); } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + struct uml_pt_regs *r = ®s->regs; + + UPT_SYSCALL_ARG1(r) = *args++; + UPT_SYSCALL_ARG2(r) = *args++; + UPT_SYSCALL_ARG3(r) = *args++; + UPT_SYSCALL_ARG4(r) = *args++; + UPT_SYSCALL_ARG5(r) = *args++; + UPT_SYSCALL_ARG6(r) = *args; +} + /* See arch/x86/um/asm/syscall.h for syscall_get_arch() definition. */ #endif /* __UM_SYSCALL_GENERIC_H */ diff --git a/arch/um/include/asm/sysrq.h b/arch/um/include/asm/sysrq.h deleted file mode 100644 index 8fc8c65cd357..000000000000 --- a/arch/um/include/asm/sysrq.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __UM_SYSRQ_H -#define __UM_SYSRQ_H - -struct task_struct; -extern void show_trace(struct task_struct* task, unsigned long *stack); - -#endif diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h index c7b4b49826a2..7a6f4dc99fa1 100644 --- a/arch/um/include/asm/thread_info.h +++ b/arch/um/include/asm/thread_info.h @@ -9,7 +9,7 @@ #define THREAD_SIZE_ORDER CONFIG_KERNEL_STACK_ORDER #define THREAD_SIZE ((1 << CONFIG_KERNEL_STACK_ORDER) * PAGE_SIZE) -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <asm/types.h> #include <asm/page.h> @@ -17,35 +17,17 @@ #include <sysdep/ptrace_user.h> struct thread_info { - struct task_struct *task; /* main task structure */ unsigned long flags; /* low level flags */ __u32 cpu; /* current CPU */ int preempt_count; /* 0 => preemptable, <0 => BUG */ - struct thread_info *real_thread; /* Points to non-IRQ stack */ - unsigned long aux_fp_regs[FP_SIZE]; /* auxiliary fp_regs to save/restore - them out-of-band */ }; #define INIT_THREAD_INFO(tsk) \ { \ - .task = &tsk, \ .flags = 0, \ .cpu = 0, \ .preempt_count = INIT_PREEMPT_COUNT, \ - .real_thread = NULL, \ -} - -/* how to get the thread information struct from C */ -static inline struct thread_info *current_thread_info(void) -{ - struct thread_info *ti; - unsigned long mask = THREAD_SIZE - 1; - void *p; - - asm volatile ("" : "=r" (p) : "0" (&ti)); - ti = (struct thread_info *) (((unsigned long)p) & ~mask); - return ti; } #endif @@ -61,6 +43,8 @@ static inline struct thread_info *current_thread_info(void) #define TIF_NOTIFY_RESUME 8 #define TIF_SECCOMP 9 /* secure computing */ #define TIF_SINGLESTEP 10 /* single stepping userspace */ +#define TIF_SYSCALL_TRACEPOINT 11 /* syscall tracepoint instrumentation */ + #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) @@ -68,7 +52,11 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_MEMDIE (1 << TIF_MEMDIE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) +#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL | \ + _TIF_NOTIFY_RESUME) + #endif diff --git a/arch/um/include/asm/tlbflush.h b/arch/um/include/asm/tlbflush.h index a5bda890390d..13a3009942be 100644 --- a/arch/um/include/asm/tlbflush.h +++ b/arch/um/include/asm/tlbflush.h @@ -9,23 +9,51 @@ #include <linux/mm.h> /* - * TLB flushing: + * In UML, we need to sync the TLB over by using mmap/munmap syscalls from + * the process handling the MM (which can be the kernel itself). + * + * To track updates, we can hook into set_ptes and flush_tlb_*. With set_ptes + * we catch all PTE transitions where memory that was unusable becomes usable. + * While with flush_tlb_* we can track any memory that becomes unusable and + * even if a higher layer of the page table was modified. + * + * So, we simply track updates using both methods and mark the memory area to + * be synced later on. The only special case is that flush_tlb_kern_* needs to + * be executed immediately as there is no good synchronization point in that + * case. In contrast, in the set_ptes case we can wait for the next kernel + * segfault before we do the synchornization. * - * - flush_tlb() flushes the current mm struct TLBs * - flush_tlb_all() flushes all processes TLBs * - flush_tlb_mm(mm) flushes the specified mm context TLB's * - flush_tlb_page(vma, vmaddr) flushes one page - * - flush_tlb_kernel_vm() flushes the kernel vm area * - flush_tlb_range(vma, start, end) flushes a range of pages + * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages */ +extern int um_tlb_sync(struct mm_struct *mm); + extern void flush_tlb_all(void); extern void flush_tlb_mm(struct mm_struct *mm); -extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end); -extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long address); -extern void flush_tlb_kernel_vm(void); -extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); -extern void __flush_tlb_one(unsigned long addr); + +static inline void flush_tlb_page(struct vm_area_struct *vma, + unsigned long address) +{ + um_tlb_mark_sync(vma->vm_mm, address, address + PAGE_SIZE); +} + +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + um_tlb_mark_sync(vma->vm_mm, start, end); +} + +static inline void flush_tlb_kernel_range(unsigned long start, + unsigned long end) +{ + um_tlb_mark_sync(&init_mm, start, end); + + /* Kernel needs to be synced immediately */ + um_tlb_sync(&init_mm); +} #endif diff --git a/arch/um/include/asm/uaccess.h b/arch/um/include/asm/uaccess.h index 7d9d60e41e4e..0df9ea4abda8 100644 --- a/arch/um/include/asm/uaccess.h +++ b/arch/um/include/asm/uaccess.h @@ -8,17 +8,13 @@ #define __UM_UACCESS_H #include <asm/elf.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> +#include <sysdep/faultinfo.h> #define __under_task_size(addr, size) \ (((unsigned long) (addr) < TASK_SIZE) && \ (((unsigned long) (addr) + (size)) < TASK_SIZE)) -#define __access_ok_vsyscall(addr, size) \ - (((unsigned long) (addr) >= FIXADDR_USER_START) && \ - ((unsigned long) (addr) + (size) <= FIXADDR_USER_END) && \ - ((unsigned long) (addr) + (size) >= (unsigned long)(addr))) - #define __addr_range_nowrap(addr, size) \ ((unsigned long) (addr) <= ((unsigned long) (addr) + (size))) @@ -39,24 +35,33 @@ static inline int __access_ok(const void __user *ptr, unsigned long size); static inline int __access_ok(const void __user *ptr, unsigned long size) { unsigned long addr = (unsigned long)ptr; - return __addr_range_nowrap(addr, size) && - (__under_task_size(addr, size) || - __access_ok_vsyscall(addr, size)); + return __addr_range_nowrap(addr, size) && __under_task_size(addr, size); } -/* no pagefaults for kernel addresses in um */ #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ - *((type *)dst) = get_unaligned((type *)(src)); \ - if (0) /* make sure the label looks used to the compiler */ \ + int __faulted; \ + \ + ___backtrack_faulted(__faulted); \ + if (__faulted) { \ + *((type *)dst) = (type) 0; \ goto err_label; \ + } \ + *((type *)dst) = get_unaligned((type *)(src)); \ + barrier(); \ + current->thread.segv_continue = NULL; \ } while (0) #define __put_kernel_nofault(dst, src, type, err_label) \ do { \ - put_unaligned(*((type *)src), (type *)(dst)); \ - if (0) /* make sure the label looks used to the compiler */ \ + int __faulted; \ + \ + ___backtrack_faulted(__faulted); \ + if (__faulted) \ goto err_label; \ + put_unaligned(*((type *)src), (type *)(dst)); \ + barrier(); \ + current->thread.segv_continue = NULL; \ } while (0) #endif diff --git a/arch/um/include/linux/smp-internal.h b/arch/um/include/linux/smp-internal.h new file mode 100644 index 000000000000..1dbcbc23f9c9 --- /dev/null +++ b/arch/um/include/linux/smp-internal.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __UM_SMP_INTERNAL_H +#define __UM_SMP_INTERNAL_H + +#if IS_ENABLED(CONFIG_SMP) + +void prefill_possible_map(void); + +#else /* !CONFIG_SMP */ + +static inline void prefill_possible_map(void) { } + +#endif /* CONFIG_SMP */ + +extern char cpu_irqstacks[NR_CPUS][THREAD_SIZE] __aligned(THREAD_SIZE); + +#endif /* __UM_SMP_INTERNAL_H */ diff --git a/arch/um/include/linux/time-internal.h b/arch/um/include/linux/time-internal.h index b22226634ff6..c274eb5ad55e 100644 --- a/arch/um/include/linux/time-internal.h +++ b/arch/um/include/linux/time-internal.h @@ -83,9 +83,14 @@ extern void time_travel_not_configured(void); #define time_travel_del_event(...) time_travel_not_configured() #endif /* CONFIG_UML_TIME_TRAVEL_SUPPORT */ +extern unsigned long tt_extra_sched_jiffies; + /* * Without CONFIG_UML_TIME_TRAVEL_SUPPORT this is a linker error if used, * which is intentional since we really shouldn't link it in that case. */ void time_travel_ndelay(unsigned long nsec); + +int um_setup_timer(void); + #endif /* __TIMER_INTERNAL_H__ */ diff --git a/arch/um/include/shared/arch.h b/arch/um/include/shared/arch.h index 880ee42a3329..cc398a21ad96 100644 --- a/arch/um/include/shared/arch.h +++ b/arch/um/include/shared/arch.h @@ -12,4 +12,6 @@ extern void arch_check_bugs(void); extern int arch_fixup(unsigned long address, struct uml_pt_regs *regs); extern void arch_examine_signal(int sig, struct uml_pt_regs *regs); +void mc_set_rip(void *_mc, void *target); + #endif diff --git a/arch/um/include/shared/as-layout.h b/arch/um/include/shared/as-layout.h index 9a0bd648d872..02ef258e3395 100644 --- a/arch/um/include/shared/as-layout.h +++ b/arch/um/include/shared/as-layout.h @@ -23,36 +23,34 @@ #define STUB_START stub_start #define STUB_CODE STUB_START #define STUB_DATA (STUB_CODE + UM_KERN_PAGE_SIZE) -#define STUB_END (STUB_DATA + UM_KERN_PAGE_SIZE) +#define STUB_DATA_PAGES 2 +#define STUB_SIZE ((1 + STUB_DATA_PAGES) * UM_KERN_PAGE_SIZE) +#define STUB_END (STUB_START + STUB_SIZE) -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <sysdep/ptrace.h> -struct cpu_task { - int pid; - void *task; -}; +struct task_struct; +extern struct task_struct *cpu_tasks[]; -extern struct cpu_task cpu_tasks[]; +extern unsigned long long physmem_size; extern unsigned long high_physmem; extern unsigned long uml_physmem; extern unsigned long uml_reserved; extern unsigned long end_vm; extern unsigned long start_vm; -extern unsigned long long highmem; extern unsigned long brk_start; -extern unsigned long host_task_size; extern unsigned long stub_start; -extern int linux_main(int argc, char **argv); +extern int linux_main(int argc, char **argv, char **envp); extern void uml_finishsetup(void); struct siginfo; -extern void (*sig_info[])(int, struct siginfo *si, struct uml_pt_regs *); +extern void (*sig_info[])(int, struct siginfo *si, struct uml_pt_regs *, void *); #endif diff --git a/arch/um/include/shared/common-offsets.h b/arch/um/include/shared/common-offsets.h deleted file mode 100644 index 96195483fbd0..000000000000 --- a/arch/um/include/shared/common-offsets.h +++ /dev/null @@ -1,36 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* for use by sys-$SUBARCH/kernel-offsets.c */ -#include <stub-data.h> - -DEFINE(KERNEL_MADV_REMOVE, MADV_REMOVE); - -DEFINE(UM_KERN_PAGE_SIZE, PAGE_SIZE); -DEFINE(UM_KERN_PAGE_MASK, PAGE_MASK); -DEFINE(UM_KERN_PAGE_SHIFT, PAGE_SHIFT); -DEFINE(UM_NSEC_PER_SEC, NSEC_PER_SEC); - -DEFINE(UM_GFP_KERNEL, GFP_KERNEL); -DEFINE(UM_GFP_ATOMIC, GFP_ATOMIC); - -DEFINE(UM_THREAD_SIZE, THREAD_SIZE); - -DEFINE(UM_NSEC_PER_SEC, NSEC_PER_SEC); -DEFINE(UM_NSEC_PER_USEC, NSEC_PER_USEC); - -#ifdef CONFIG_PRINTK -DEFINE(UML_CONFIG_PRINTK, CONFIG_PRINTK); -#endif -#ifdef CONFIG_UML_X86 -DEFINE(UML_CONFIG_UML_X86, CONFIG_UML_X86); -#endif -#ifdef CONFIG_64BIT -DEFINE(UML_CONFIG_64BIT, CONFIG_64BIT); -#endif -#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT -DEFINE(UML_CONFIG_UML_TIME_TRAVEL_SUPPORT, CONFIG_UML_TIME_TRAVEL_SUPPORT); -#endif - -/* for stub */ -DEFINE(UML_STUB_FIELD_OFFSET, offsetof(struct stub_data, offset)); -DEFINE(UML_STUB_FIELD_CHILD_ERR, offsetof(struct stub_data, child_err)); -DEFINE(UML_STUB_FIELD_FD, offsetof(struct stub_data, fd)); diff --git a/arch/um/include/shared/irq_kern.h b/arch/um/include/shared/irq_kern.h index f2dc817abb7c..44357fa6ee29 100644 --- a/arch/um/include/shared/irq_kern.h +++ b/arch/um/include/shared/irq_kern.h @@ -76,4 +76,5 @@ static inline bool um_irq_timetravel_handler_used(void) } void um_free_irq(int irq, void *dev_id); +void free_irqs(void); #endif diff --git a/arch/um/include/shared/irq_user.h b/arch/um/include/shared/irq_user.h index da0f6eea30d0..746abc24a5d5 100644 --- a/arch/um/include/shared/irq_user.h +++ b/arch/um/include/shared/irq_user.h @@ -15,7 +15,10 @@ enum um_irq_type { }; struct siginfo; -extern void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs); +extern void sigio_handler(int sig, struct siginfo *unused_si, + struct uml_pt_regs *regs, void *mc); +extern void sigchld_handler(int sig, struct siginfo *unused_si, + struct uml_pt_regs *regs, void *mc); void sigio_run_timetravel_handlers(void); extern void free_irq_by_fd(int fd); extern void deactivate_fd(int fd, int irqnum); diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h index d8b8b4f07e42..38321188c04c 100644 --- a/arch/um/include/shared/kern_util.h +++ b/arch/um/include/shared/kern_util.h @@ -13,28 +13,25 @@ struct siginfo; extern int uml_exitcode; -extern int ncpus; extern int kmalloc_ok; -#define UML_ROUND_UP(addr) \ - ((((unsigned long) addr) + PAGE_SIZE - 1) & PAGE_MASK) - extern unsigned long alloc_stack(int order, int atomic); extern void free_stack(unsigned long stack, int order); struct pt_regs; extern void do_signal(struct pt_regs *regs); extern void interrupt_end(void); -extern void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs); +extern void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs, + void *mc); extern unsigned long segv(struct faultinfo fi, unsigned long ip, - int is_user, struct uml_pt_regs *regs); + int is_user, struct uml_pt_regs *regs, + void *mc); extern int handle_page_fault(unsigned long address, unsigned long ip, int is_write, int is_user, int *code_out); extern unsigned int do_IRQ(int irq, struct uml_pt_regs *regs); extern void initial_thread_cb(void (*proc)(void *), void *arg); -extern int is_syscall(unsigned long addr); extern void timer_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs); @@ -50,21 +47,25 @@ extern void do_uml_exitcalls(void); * Are we disallowed to sleep? Used to choose between GFP_KERNEL and * GFP_ATOMIC. */ -extern int __cant_sleep(void); +extern int __uml_cant_sleep(void); extern int get_current_pid(void); extern int copy_from_user_proc(void *to, void *from, int size); extern char *uml_strdup(const char *string); +int uml_need_resched(void); extern unsigned long to_irq_stack(unsigned long *mask_out); extern unsigned long from_irq_stack(int nested); -extern int singlestepping(void *t); +extern int singlestepping(void); -extern void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs); -extern void bus_handler(int sig, struct siginfo *si, struct uml_pt_regs *regs); -extern void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs); +extern void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs, + void *mc); +extern void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs, + void *mc); extern void fatal_sigsegv(void) __attribute__ ((noreturn)); void um_idle_sleep(void); +void kasan_map_memory(void *start, size_t len); + #endif diff --git a/arch/um/include/shared/longjmp.h b/arch/um/include/shared/longjmp.h index 8863319039f3..c53e43d980c8 100644 --- a/arch/um/include/shared/longjmp.h +++ b/arch/um/include/shared/longjmp.h @@ -5,7 +5,6 @@ #include <sysdep/archsetjmp.h> #include <os.h> -extern int signals_enabled; extern int setjmp(jmp_buf); extern void longjmp(jmp_buf, int); @@ -15,7 +14,7 @@ extern void longjmp(jmp_buf, int); #define UML_SETJMP(buf) ({ \ int n, enable; \ - enable = *(volatile int *)&signals_enabled; \ + enable = um_get_signals(); \ n = setjmp(*buf); \ if(n != 0) \ um_set_signals_trace(enable); \ diff --git a/arch/um/include/shared/mem_user.h b/arch/um/include/shared/mem_user.h index 11a723a58545..8a5b72872ff8 100644 --- a/arch/um/include/shared/mem_user.h +++ b/arch/um/include/shared/mem_user.h @@ -32,25 +32,10 @@ #ifndef _MEM_USER_H #define _MEM_USER_H -struct iomem_region { - struct iomem_region *next; - char *driver; - int fd; - int size; - unsigned long phys; - unsigned long virt; -}; - -extern struct iomem_region *iomem_regions; -extern int iomem_size; - #define ROUND_4M(n) ((((unsigned long) (n)) + (1 << 22)) & ~((1 << 22) - 1)) -extern unsigned long find_iomem(char *driver, unsigned long *len_out); -extern void mem_total_pages(unsigned long physmem, unsigned long iomem, - unsigned long highmem); extern void setup_physmem(unsigned long start, unsigned long usable, - unsigned long len, unsigned long long highmem); + unsigned long len); extern void map_memory(unsigned long virt, unsigned long phys, unsigned long len, int r, int w, int x); diff --git a/arch/um/include/shared/net_kern.h b/arch/um/include/shared/net_kern.h deleted file mode 100644 index 67b2e9a1f2e5..000000000000 --- a/arch/um/include/shared/net_kern.h +++ /dev/null @@ -1,69 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2002 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) - */ - -#ifndef __UM_NET_KERN_H -#define __UM_NET_KERN_H - -#include <linux/netdevice.h> -#include <linux/platform_device.h> -#include <linux/skbuff.h> -#include <linux/socket.h> -#include <linux/list.h> -#include <linux/workqueue.h> - -struct uml_net { - struct list_head list; - struct net_device *dev; - struct platform_device pdev; - int index; -}; - -struct uml_net_private { - struct list_head list; - spinlock_t lock; - struct net_device *dev; - struct timer_list tl; - - struct work_struct work; - int fd; - unsigned char mac[ETH_ALEN]; - int max_packet; - unsigned short (*protocol)(struct sk_buff *); - int (*open)(void *); - void (*close)(int, void *); - void (*remove)(void *); - int (*read)(int, struct sk_buff *skb, struct uml_net_private *); - int (*write)(int, struct sk_buff *skb, struct uml_net_private *); - - void (*add_address)(unsigned char *, unsigned char *, void *); - void (*delete_address)(unsigned char *, unsigned char *, void *); - char user[]; -}; - -struct net_kern_info { - void (*init)(struct net_device *, void *); - unsigned short (*protocol)(struct sk_buff *); - int (*read)(int, struct sk_buff *skb, struct uml_net_private *); - int (*write)(int, struct sk_buff *skb, struct uml_net_private *); -}; - -struct transport { - struct list_head list; - const char *name; - int (* const setup)(char *, char **, void *); - const struct net_user_info *user; - const struct net_kern_info *kern; - const int private_size; - const int setup_size; -}; - -extern int tap_setup_common(char *str, char *type, char **dev_name, - char **mac_out, char **gate_addr); -extern void register_transport(struct transport *new); -extern unsigned short eth_protocol(struct sk_buff *skb); -extern void uml_net_setup_etheraddr(struct net_device *dev, char *str); - - -#endif diff --git a/arch/um/include/shared/net_user.h b/arch/um/include/shared/net_user.h deleted file mode 100644 index ba92a4d93531..000000000000 --- a/arch/um/include/shared/net_user.h +++ /dev/null @@ -1,52 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) - */ - -#ifndef __UM_NET_USER_H__ -#define __UM_NET_USER_H__ - -#define ETH_ADDR_LEN (6) -#define ETH_HEADER_ETHERTAP (16) -#define ETH_HEADER_OTHER (26) /* 14 for ethernet + VLAN + MPLS for crazy people */ -#define ETH_MAX_PACKET (1500) - -#define UML_NET_VERSION (4) - -struct net_user_info { - int (*init)(void *, void *); - int (*open)(void *); - void (*close)(int, void *); - void (*remove)(void *); - void (*add_address)(unsigned char *, unsigned char *, void *); - void (*delete_address)(unsigned char *, unsigned char *, void *); - int max_packet; - int mtu; -}; - -extern void iter_addresses(void *d, void (*cb)(unsigned char *, - unsigned char *, void *), - void *arg); - -extern void *get_output_buffer(int *len_out); -extern void free_output_buffer(void *buffer); - -extern int tap_open_common(void *dev, char *gate_addr); -extern void tap_check_ips(char *gate_addr, unsigned char *eth_addr); - -extern void read_output(int fd, char *output_out, int len); - -extern int net_read(int fd, void *buf, int len); -extern int net_recvfrom(int fd, void *buf, int len); -extern int net_write(int fd, void *buf, int len); -extern int net_send(int fd, void *buf, int len); -extern int net_sendto(int fd, void *buf, int len, void *to, int sock_len); - -extern void open_addr(unsigned char *addr, unsigned char *netmask, void *arg); -extern void close_addr(unsigned char *addr, unsigned char *netmask, void *arg); - -extern char *split_if_spec(char *str, ...); - -extern int dev_netmask(void *d, void *m); - -#endif diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h index 0df646c6651e..b26e94292fc1 100644 --- a/arch/um/include/shared/os.h +++ b/arch/um/include/shared/os.h @@ -143,9 +143,7 @@ extern int os_access(const char *file, int mode); extern int os_set_exec_close(int fd); extern int os_ioctl_generic(int fd, unsigned int cmd, unsigned long arg); extern int os_get_ifname(int fd, char *namebuf); -extern int os_set_slip(int fd); extern int os_mode_fd(int fd, int mode); -extern int os_fsync_file(int fd); extern int os_seek_file(int fd, unsigned long long offset); extern int os_open_file(const char *file, struct openflags flags, int mode); @@ -163,8 +161,10 @@ extern int os_set_fd_block(int fd, int blocking); extern int os_accept_connection(int fd); extern int os_create_unix_socket(const char *file, int len, int close_on_exec); extern int os_shutdown_socket(int fd, int r, int w); +extern int os_dup_file(int fd); extern void os_close_file(int fd); -extern int os_rcv_fd(int fd, int *helper_pid_out); +ssize_t os_rcv_fd_msg(int fd, int *fds, unsigned int n_fds, + void *data, size_t data_len); extern int os_connect_socket(const char *name); extern int os_file_type(char *file); extern int os_file_mode(const char *file, struct openflags *mode_out); @@ -179,6 +179,8 @@ extern int os_eventfd(unsigned int initval, int flags); extern int os_sendmsg_fds(int fd, const void *buf, unsigned int len, const int *fds, unsigned int fds_num); int os_poll(unsigned int n, const int *fds); +void *os_mmap_rw_shared(int fd, size_t size); +void *os_mremap_rw_shared(void *old_addr, size_t old_size, size_t new_size); /* start_up.c */ extern void os_early_checks(void); @@ -191,16 +193,16 @@ extern void get_host_cpu_features( /* mem.c */ extern int create_mem_file(unsigned long long len); +/* tlb.c */ +extern void report_enomem(void); + /* process.c */ -extern unsigned long os_process_pc(int pid); -extern int os_process_parent(int pid); +pid_t os_reap_child(void); extern void os_alarm_process(int pid); -extern void os_stop_process(int pid); extern void os_kill_process(int pid, int reap_child); extern void os_kill_ptraced_process(int pid, int reap_child); extern int os_getpid(void); -extern int os_getpgrp(void); extern void init_new_thread_signals(void); @@ -211,7 +213,11 @@ extern int os_protect_memory(void *addr, unsigned long len, extern int os_unmap_memory(void *addr, int len); extern int os_drop_memory(void *addr, int length); extern int can_drop_memory(void); -extern int os_mincore(void *addr, unsigned long len); + +void os_set_pdeathsig(void); + +int os_futex_wait(void *uaddr, unsigned int val); +int os_futex_wake(void *uaddr); /* execvp.c */ extern int execvp_noalloc(char *buf, const char *file, char *const argv[]); @@ -221,6 +227,11 @@ extern int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags, unsigned long *stack_out); extern int helper_wait(int pid); +struct os_helper_thread; +int os_run_helper_thread(struct os_helper_thread **td_out, + void *(*routine)(void *), void *arg); +void os_kill_helper_thread(struct os_helper_thread *td); +void os_fix_helper_thread_signals(void); /* umid.c */ extern int umid_file_name(char *name, char *buf, int len); @@ -235,9 +246,9 @@ extern void send_sigio_to_self(void); extern int change_sig(int signal, int on); extern void block_signals(void); extern void unblock_signals(void); +extern int um_get_signals(void); extern int um_set_signals(int enable); extern int um_set_signals_trace(int enable); -extern int os_is_signal_stack(void); extern void deliver_alarm(void); extern void register_pm_wake_signal(void); extern void block_signals_hard(void); @@ -259,34 +270,29 @@ extern void os_warn(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); /* time.c */ +void os_idle_prepare(void); extern void os_idle_sleep(void); extern int os_timer_create(void); -extern int os_timer_set_interval(unsigned long long nsecs); -extern int os_timer_one_shot(unsigned long long nsecs); -extern void os_timer_disable(void); +extern int os_timer_set_interval(int cpu, unsigned long long nsecs); +extern int os_timer_one_shot(int cpu, unsigned long long nsecs); +extern void os_timer_disable(int cpu); extern long long os_persistent_clock_emulation(void); extern long long os_nsecs(void); /* skas/mem.c */ -extern long run_syscall_stub(struct mm_id * mm_idp, - int syscall, unsigned long *args, long expected, - void **addr, int done); -extern long syscall_stub_data(struct mm_id * mm_idp, - unsigned long *data, int data_count, - void **addr, void **stub_addr); -extern int map(struct mm_id * mm_idp, unsigned long virt, - unsigned long len, int prot, int phys_fd, - unsigned long long offset, int done, void **data); -extern int unmap(struct mm_id * mm_idp, unsigned long addr, unsigned long len, - int done, void **data); -extern int protect(struct mm_id * mm_idp, unsigned long addr, - unsigned long len, unsigned int prot, int done, void **data); +int syscall_stub_flush(struct mm_id *mm_idp); +struct stub_syscall *syscall_stub_alloc(struct mm_id *mm_idp); +void syscall_stub_dump_error(struct mm_id *mm_idp); + +int map(struct mm_id *mm_idp, unsigned long virt, + unsigned long len, int prot, int phys_fd, + unsigned long long offset); +int unmap(struct mm_id *mm_idp, unsigned long addr, unsigned long len); /* skas/process.c */ extern int is_skas_winch(int pid, int fd, void *data); -extern int start_userspace(unsigned long stub_stack); -extern int copy_context_skas0(unsigned long stack, int pid); -extern void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs); +extern int start_userspace(struct mm_id *mm_id); +extern void userspace(struct uml_pt_regs *regs); extern void new_thread(void *stack, jmp_buf *buf, void (*handler)(void)); extern void switch_threads(jmp_buf *me, jmp_buf *you); extern int start_idle_thread(void *stack, jmp_buf *switch_buf); @@ -313,7 +319,7 @@ extern void um_irqs_resume(void); extern int add_sigio_fd(int fd); extern int ignore_sigio_fd(int fd); extern void maybe_sigio_broken(int fd); -extern void sigio_broken(int fd); +extern void sigio_broken(void); /* * unlocked versions for IRQ controller code. * @@ -323,15 +329,9 @@ extern void sigio_broken(int fd); extern int __add_sigio_fd(int fd); extern int __ignore_sigio_fd(int fd); -/* prctl.c */ -extern int os_arch_prctl(int pid, int option, unsigned long *arg2); - /* tty.c */ extern int get_pty(void); -/* sys-$ARCH/task_size.c */ -extern unsigned long os_get_top_address(void); - long syscall(long number, ...); /* irqflags tracing */ @@ -343,4 +343,17 @@ extern void um_trace_signals_off(void); /* time-travel */ extern void deliver_time_travel_irqs(void); +/* smp.c */ +#if IS_ENABLED(CONFIG_SMP) +void os_init_smp(void); +int os_start_cpu_thread(int cpu); +void os_start_secondary(void *arg, jmp_buf *switch_buf); +int os_send_ipi(int cpu, int vector); +void os_local_ipi_enable(void); +void os_local_ipi_disable(void); +#else /* !CONFIG_SMP */ +static inline void os_local_ipi_enable(void) { } +static inline void os_local_ipi_disable(void) { } +#endif /* CONFIG_SMP */ + #endif diff --git a/arch/um/include/shared/ptrace_user.h b/arch/um/include/shared/ptrace_user.h index 95455e8996e7..8a705d8f96ce 100644 --- a/arch/um/include/shared/ptrace_user.h +++ b/arch/um/include/shared/ptrace_user.h @@ -12,45 +12,4 @@ extern int ptrace_getregs(long pid, unsigned long *regs_out); extern int ptrace_setregs(long pid, unsigned long *regs_in); -/* syscall emulation path in ptrace */ - -#ifndef PTRACE_SYSEMU -#define PTRACE_SYSEMU 31 -#endif -#ifndef PTRACE_SYSEMU_SINGLESTEP -#define PTRACE_SYSEMU_SINGLESTEP 32 -#endif - -/* On architectures, that started to support PTRACE_O_TRACESYSGOOD - * in linux 2.4, there are two different definitions of - * PTRACE_SETOPTIONS: linux 2.4 uses 21 while linux 2.6 uses 0x4200. - * For binary compatibility, 2.6 also supports the old "21", named - * PTRACE_OLDSETOPTION. On these architectures, UML always must use - * "21", to ensure the kernel runs on 2.4 and 2.6 host without - * recompilation. So, we use PTRACE_OLDSETOPTIONS in UML. - * We also want to be able to build the kernel on 2.4, which doesn't - * have PTRACE_OLDSETOPTIONS. So, if it is missing, we declare - * PTRACE_OLDSETOPTIONS to be the same as PTRACE_SETOPTIONS. - * - * On architectures, that start to support PTRACE_O_TRACESYSGOOD on - * linux 2.6, PTRACE_OLDSETOPTIONS never is defined, and also isn't - * supported by the host kernel. In that case, our trick lets us use - * the new 0x4200 with the name PTRACE_OLDSETOPTIONS. - */ -#ifndef PTRACE_OLDSETOPTIONS -#define PTRACE_OLDSETOPTIONS PTRACE_SETOPTIONS -#endif - -void set_using_sysemu(int value); -int get_using_sysemu(void); -extern int sysemu_supported; - -#define SELECT_PTRACE_OPERATION(sysemu_mode, singlestep_mode) \ - (((int[3][3] ) { \ - { PTRACE_SYSCALL, PTRACE_SYSCALL, PTRACE_SINGLESTEP }, \ - { PTRACE_SYSEMU, PTRACE_SYSEMU, PTRACE_SINGLESTEP }, \ - { PTRACE_SYSEMU, PTRACE_SYSEMU_SINGLESTEP, \ - PTRACE_SYSEMU_SINGLESTEP } }) \ - [sysemu_mode][singlestep_mode]) - #endif diff --git a/arch/um/include/shared/registers.h b/arch/um/include/shared/registers.h index 2f9c3ce5b45e..7d81b2339a48 100644 --- a/arch/um/include/shared/registers.h +++ b/arch/um/include/shared/registers.h @@ -8,14 +8,6 @@ #include <sysdep/ptrace.h> -extern int save_i387_registers(int pid, unsigned long *fp_regs); -extern int restore_i387_registers(int pid, unsigned long *fp_regs); -extern int save_fp_registers(int pid, unsigned long *fp_regs); -extern int restore_fp_registers(int pid, unsigned long *fp_regs); -extern int save_fpx_registers(int pid, unsigned long *fp_regs); -extern int restore_fpx_registers(int pid, unsigned long *fp_regs); -extern int save_registers(int pid, struct uml_pt_regs *regs); -extern int restore_pid_registers(int pid, struct uml_pt_regs *regs); extern int init_pid_registers(int pid); extern void get_safe_registers(unsigned long *regs, unsigned long *fp_regs); extern int get_fp_registers(int pid, unsigned long *regs); diff --git a/arch/um/include/shared/sigio.h b/arch/um/include/shared/sigio.h index e60c8b227844..c6c2edce1f6d 100644 --- a/arch/um/include/shared/sigio.h +++ b/arch/um/include/shared/sigio.h @@ -6,7 +6,6 @@ #ifndef __SIGIO_H__ #define __SIGIO_H__ -extern int write_sigio_irq(int fd); extern void sigio_lock(void); extern void sigio_unlock(void); diff --git a/arch/um/include/shared/skas/mm_id.h b/arch/um/include/shared/skas/mm_id.h index e82e203f5f41..fb96c0bd8222 100644 --- a/arch/um/include/shared/skas/mm_id.h +++ b/arch/um/include/shared/skas/mm_id.h @@ -6,13 +6,24 @@ #ifndef __MM_ID_H #define __MM_ID_H +#include <linux/compiler_types.h> + +#define STUB_MAX_FDS 4 + struct mm_id { - union { - int mm_fd; - int pid; - } u; + int pid; unsigned long stack; - int kill; + int syscall_data_len; + + /* Only used with SECCOMP mode */ + int sock; + int syscall_fd_num; + int syscall_fd_map[STUB_MAX_FDS]; }; +void enter_turnstile(struct mm_id *mm_id) __acquires(turnstile); +void exit_turnstile(struct mm_id *mm_id) __releases(turnstile); + +void notify_mm_kill(int pid); + #endif diff --git a/arch/um/include/shared/skas/skas.h b/arch/um/include/shared/skas/skas.h index c93d2cbc8f32..2237ffedec75 100644 --- a/arch/um/include/shared/skas/skas.h +++ b/arch/um/include/shared/skas/skas.h @@ -8,12 +8,14 @@ #include <sysdep/ptrace.h> -extern int userspace_pid[]; +extern int using_seccomp; -extern int user_thread(unsigned long stack, int flags); extern void new_thread_handler(void); extern void handle_syscall(struct uml_pt_regs *regs); -extern long execute_syscall_skas(void *r); extern unsigned long current_stub_stack(void); +extern struct mm_id *current_mm_id(void); +extern void current_mm_sync(void); +void initial_jmpbuf_lock(void); +void initial_jmpbuf_unlock(void); #endif diff --git a/arch/um/include/shared/skas/stub-data.h b/arch/um/include/shared/skas/stub-data.h index 5e3ade3fb38b..27db38e95df9 100644 --- a/arch/um/include/shared/skas/stub-data.h +++ b/arch/um/include/shared/skas/stub-data.h @@ -8,10 +8,69 @@ #ifndef __STUB_DATA_H #define __STUB_DATA_H +#include <linux/compiler_types.h> +#include <as-layout.h> +#include <sysdep/tls.h> +#include <sysdep/stub-data.h> +#include <mm_id.h> + +#define FUTEX_IN_CHILD 0 +#define FUTEX_IN_KERN 1 + +struct stub_init_data { + int seccomp; + + unsigned long stub_start; + + int stub_code_fd; + unsigned long stub_code_offset; + int stub_data_fd; + unsigned long stub_data_offset; + + unsigned long signal_handler; + unsigned long signal_restorer; +}; + +#define STUB_NEXT_SYSCALL(s) \ + ((struct stub_syscall *) (((unsigned long) s) + (s)->cmd_len)) + +enum stub_syscall_type { + STUB_SYSCALL_UNSET = 0, + STUB_SYSCALL_MMAP, + STUB_SYSCALL_MUNMAP, +}; + +struct stub_syscall { + struct { + unsigned long addr; + unsigned long length; + unsigned long offset; + int fd; + int prot; + } mem; + + enum stub_syscall_type syscall; +}; + struct stub_data { - unsigned long offset; - int fd; - long parent_err, child_err; + long err; + + int syscall_data_len; + /* 128 leaves enough room for additional fields in the struct */ + struct stub_syscall syscall_data[(UM_KERN_PAGE_SIZE - 128) / sizeof(struct stub_syscall)] __aligned(16); + + /* data shared with signal handler (only used in seccomp mode) */ + short restart_wait; + unsigned int futex; + int signal; + unsigned short si_offset; + unsigned short mctx_offset; + + /* seccomp architecture specific state restore */ + struct stub_data_arch arch_data; + + /* Stack for our signal handlers and for calling into . */ + unsigned char sigstack[UM_KERN_PAGE_SIZE] __aligned(UM_KERN_PAGE_SIZE); }; #endif diff --git a/arch/um/include/shared/smp.h b/arch/um/include/shared/smp.h new file mode 100644 index 000000000000..06e3faa95091 --- /dev/null +++ b/arch/um/include/shared/smp.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __UM_SHARED_SMP_H +#define __UM_SHARED_SMP_H + +#if IS_ENABLED(CONFIG_SMP) + +extern int uml_ncpus; + +int uml_curr_cpu(void); +void uml_start_secondary(void *opaque); +void uml_ipi_handler(int vector); + +#else /* !CONFIG_SMP */ + +#define uml_ncpus 1 +#define uml_curr_cpu() 0 + +#endif /* CONFIG_SMP */ + +#endif /* __UM_SHARED_SMP_H */ diff --git a/arch/um/include/shared/timetravel.h b/arch/um/include/shared/timetravel.h index e5c3d69f1b69..7c2b277b7eb0 100644 --- a/arch/um/include/shared/timetravel.h +++ b/arch/um/include/shared/timetravel.h @@ -12,11 +12,19 @@ enum time_travel_mode { TT_MODE_EXTERNAL, }; -#if defined(UML_CONFIG_UML_TIME_TRAVEL_SUPPORT) || \ - defined(CONFIG_UML_TIME_TRAVEL_SUPPORT) +#if IS_ENABLED(CONFIG_UML_TIME_TRAVEL_SUPPORT) extern enum time_travel_mode time_travel_mode; +extern int time_travel_should_print_bc_msg; #else #define time_travel_mode TT_MODE_OFF -#endif /* (UML_)CONFIG_UML_TIME_TRAVEL_SUPPORT */ +#define time_travel_should_print_bc_msg 0 +#endif /* CONFIG_UML_TIME_TRAVEL_SUPPORT */ + +void _time_travel_print_bc_msg(void); +static inline void time_travel_print_bc_msg(void) +{ + if (time_travel_should_print_bc_msg) + _time_travel_print_bc_msg(); +} #endif /* _UM_TIME_TRAVEL_H_ */ diff --git a/arch/um/include/shared/um_malloc.h b/arch/um/include/shared/um_malloc.h index 13da93284c2c..815dd03e8707 100644 --- a/arch/um/include/shared/um_malloc.h +++ b/arch/um/include/shared/um_malloc.h @@ -11,8 +11,9 @@ extern void *uml_kmalloc(int size, int flags); extern void kfree(const void *ptr); -extern void *vmalloc(unsigned long size); -extern void vfree(void *ptr); +extern void *vmalloc_noprof(unsigned long size); +#define vmalloc(...) vmalloc_noprof(__VA_ARGS__) +extern void vfree(const void *ptr); #endif /* __UM_MALLOC_H__ */ diff --git a/arch/um/include/shared/user.h b/arch/um/include/shared/user.h index bda66e5a9d4e..139eb78a4767 100644 --- a/arch/um/include/shared/user.h +++ b/arch/um/include/shared/user.h @@ -38,20 +38,29 @@ extern void panic(const char *fmt, ...) #define UM_KERN_DEBUG KERN_DEBUG #define UM_KERN_CONT KERN_CONT -#ifdef UML_CONFIG_PRINTK +#if IS_ENABLED(CONFIG_PRINTK) #define printk(...) _printk(__VA_ARGS__) extern int _printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); +extern void print_hex_dump(const char *level, const char *prefix_str, + int prefix_type, int rowsize, int groupsize, + const void *buf, size_t len, _Bool ascii); #else static inline int printk(const char *fmt, ...) { return 0; } +static inline void print_hex_dump(const char *level, const char *prefix_str, + int prefix_type, int rowsize, int groupsize, + const void *buf, size_t len, _Bool ascii) +{ +} #endif extern int in_aton(char *str); -extern size_t strlcpy(char *, const char *, size_t); extern size_t strlcat(char *, const char *, size_t); +extern size_t sized_strscpy(char *, const char *, size_t); +#define strscpy(dst, src) sized_strscpy(dst, src, sizeof(dst)) /* Copied from linux/compiler-gcc.h since we can't include it directly */ #define barrier() __asm__ __volatile__("": : :"memory") |