diff options
Diffstat (limited to 'arch/x86/um')
49 files changed, 1003 insertions, 1369 deletions
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index 186f13268401..986045d5e638 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -10,6 +10,7 @@ config UML_X86 def_bool y select ARCH_BINFMT_ELF_EXTRA_PHDRS if X86_32 select DCACHE_WORD_ACCESS + select HAVE_EFFICIENT_UNALIGNED_ACCESS config 64BIT bool "64-bit kernel" if "$(SUBARCH)" = "x86" @@ -28,17 +29,6 @@ config X86_64 def_bool 64BIT select MODULES_USE_ELF_RELA -config 3_LEVEL_PGTABLES - bool "Three-level pagetables" if !64BIT - default 64BIT - help - Three-level pagetables will let UML have more than 4G of physical - memory. All the memory that can't be mapped directly will be treated - as high memory. - - However, this it experimental on 32-bit architectures, so if unsure say - N (on x86-64 it's automatically enabled, instead, as it's safe there). - config ARCH_HAS_SC_SIGNALS def_bool !64BIT diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index 8bc72a51b257..b42c31cd2390 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -9,9 +9,9 @@ else BITS := 64 endif -obj-y = bugs_$(BITS).o delay.o fault.o ldt.o \ - ptrace_$(BITS).o ptrace_user.o setjmp_$(BITS).o signal.o \ - stub_$(BITS).o stub_segv.o \ +obj-y = bugs_$(BITS).o delay.o fault.o \ + ptrace.o ptrace_$(BITS).o ptrace_user.o setjmp_$(BITS).o signal.o \ + stub_segv.o \ sys_call_table_$(BITS).o sysrq_$(BITS).o tls_$(BITS).o \ mem_$(BITS).o subarch.o os-Linux/ @@ -31,7 +31,6 @@ obj-y += syscalls_64.o vdso/ subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o \ ../lib/memmove_64.o ../lib/memset_64.o -subarch-$(CONFIG_PREEMPTION) += ../entry/thunk_64.o endif diff --git a/arch/x86/um/asm/archparam.h b/arch/x86/um/asm/archparam.h deleted file mode 100644 index c17cf68dda0f..000000000000 --- a/arch/x86/um/asm/archparam.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * Copyright (C) 2000 - 2003 Jeff Dike (jdike@addtoit.com) - * Copyright 2003 PathScale, Inc. - * Licensed under the GPL - */ - -#ifndef __UM_ARCHPARAM_H -#define __UM_ARCHPARAM_H - -#ifdef CONFIG_X86_32 - -#ifdef CONFIG_X86_PAE -#define LAST_PKMAP 512 -#else -#define LAST_PKMAP 1024 -#endif - -#endif - -#endif diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h index 4da336965698..b51aefd6ec2b 100644 --- a/arch/x86/um/asm/barrier.h +++ b/arch/x86/um/asm/barrier.h @@ -12,9 +12,9 @@ */ #ifdef CONFIG_X86_32 -#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) -#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) -#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) +#define mb() alternative("lock addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) +#define rmb() alternative("lock addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) +#define wmb() alternative("lock addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) #else /* CONFIG_X86_32 */ diff --git a/arch/x86/um/asm/checksum.h b/arch/x86/um/asm/checksum.h index b07824500363..ddc144657efa 100644 --- a/arch/x86/um/asm/checksum.h +++ b/arch/x86/um/asm/checksum.h @@ -20,6 +20,9 @@ */ extern __wsum csum_partial(const void *buff, int len, __wsum sum); +/* Do not call this directly. Declared for export type visibility. */ +extern __visible __wsum csum_partial_copy_generic(const void *src, void *dst, int len); + /** * csum_fold - Fold and invert a 32bit checksum. * sum: 32bit unfolded sum diff --git a/arch/x86/um/asm/elf.h b/arch/x86/um/asm/elf.h index 6052200fe925..62ed5d68a978 100644 --- a/arch/x86/um/asm/elf.h +++ b/arch/x86/um/asm/elf.h @@ -8,6 +8,8 @@ #include <asm/user.h> #include <skas.h> +#define CORE_DUMP_USE_REGSET + #ifdef CONFIG_X86_32 #define R_386_NONE 0 diff --git a/arch/x86/um/asm/mm_context.h b/arch/x86/um/asm/mm_context.h deleted file mode 100644 index dc32dc023c2f..000000000000 --- a/arch/x86/um/asm/mm_context.h +++ /dev/null @@ -1,70 +0,0 @@ -/* - * Copyright (C) 2004 Fujitsu Siemens Computers GmbH - * Licensed under the GPL - * - * Author: Bodo Stroesser <bstroesser@fujitsu-siemens.com> - */ - -#ifndef __ASM_LDT_H -#define __ASM_LDT_H - -#include <linux/mutex.h> -#include <asm/ldt.h> - -#define LDT_PAGES_MAX \ - ((LDT_ENTRIES * LDT_ENTRY_SIZE)/PAGE_SIZE) -#define LDT_ENTRIES_PER_PAGE \ - (PAGE_SIZE/LDT_ENTRY_SIZE) -#define LDT_DIRECT_ENTRIES \ - ((LDT_PAGES_MAX*sizeof(void *))/LDT_ENTRY_SIZE) - -struct ldt_entry { - __u32 a; - __u32 b; -}; - -typedef struct uml_ldt { - int entry_count; - struct mutex lock; - union { - struct ldt_entry * pages[LDT_PAGES_MAX]; - struct ldt_entry entries[LDT_DIRECT_ENTRIES]; - } u; -} uml_ldt_t; - -#define LDT_entry_a(info) \ - ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff)) - -#define LDT_entry_b(info) \ - (((info)->base_addr & 0xff000000) | \ - (((info)->base_addr & 0x00ff0000) >> 16) | \ - ((info)->limit & 0xf0000) | \ - (((info)->read_exec_only ^ 1) << 9) | \ - ((info)->contents << 10) | \ - (((info)->seg_not_present ^ 1) << 15) | \ - ((info)->seg_32bit << 22) | \ - ((info)->limit_in_pages << 23) | \ - ((info)->useable << 20) | \ - 0x7000) - -#define _LDT_empty(info) (\ - (info)->base_addr == 0 && \ - (info)->limit == 0 && \ - (info)->contents == 0 && \ - (info)->read_exec_only == 1 && \ - (info)->seg_32bit == 0 && \ - (info)->limit_in_pages == 0 && \ - (info)->seg_not_present == 1 && \ - (info)->useable == 0 ) - -#ifdef CONFIG_X86_64 -#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0)) -#else -#define LDT_empty(info) (_LDT_empty(info)) -#endif - -struct uml_arch_mm_context { - uml_ldt_t ldt; -}; - -#endif diff --git a/arch/x86/um/asm/module.h b/arch/x86/um/asm/module.h deleted file mode 100644 index a3b061d66082..000000000000 --- a/arch/x86/um/asm/module.h +++ /dev/null @@ -1,24 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __UM_MODULE_H -#define __UM_MODULE_H - -/* UML is simple */ -struct mod_arch_specific -{ -}; - -#ifdef CONFIG_X86_32 - -#define Elf_Shdr Elf32_Shdr -#define Elf_Sym Elf32_Sym -#define Elf_Ehdr Elf32_Ehdr - -#else - -#define Elf_Shdr Elf64_Shdr -#define Elf_Sym Elf64_Sym -#define Elf_Ehdr Elf64_Ehdr - -#endif - -#endif diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h index 478710384b34..e222d2ae28fd 100644 --- a/arch/x86/um/asm/processor.h +++ b/arch/x86/um/asm/processor.h @@ -21,10 +21,10 @@ #include <asm/user.h> -/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ -static __always_inline void rep_nop(void) +/* PAUSE is a good thing to insert into busy-wait loops. */ +static __always_inline void native_pause(void) { - __asm__ __volatile__("rep;nop": : :"memory"); + __asm__ __volatile__("pause": : :"memory"); } static __always_inline void cpu_relax(void) @@ -33,7 +33,7 @@ static __always_inline void cpu_relax(void) time_travel_mode == TT_MODE_EXTERNAL) time_travel_ndelay(1); else - rep_nop(); + native_pause(); } #define task_pt_regs(t) (&(t)->thread.regs) diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h index 83822fd42204..2641d28d115c 100644 --- a/arch/x86/um/asm/ptrace.h +++ b/arch/x86/um/asm/ptrace.h @@ -2,6 +2,16 @@ #ifndef __UM_X86_PTRACE_H #define __UM_X86_PTRACE_H +/* This is here because signal.c needs the REGSET_FP_LEGACY definition */ +enum { + REGSET_GENERAL, +#ifdef CONFIG_X86_32 + REGSET_FP_LEGACY, +#endif + REGSET_FP, + REGSET_XSTATE, +}; + #include <linux/compiler.h> #ifndef CONFIG_X86_32 #define __FRAME_OFFSETS /* Needed to get the R* macros */ @@ -54,6 +64,8 @@ extern int ptrace_get_thread_area(struct task_struct *child, int idx, extern int ptrace_set_thread_area(struct task_struct *child, int idx, struct user_desc __user *user_desc); +extern int arch_switch_tls(struct task_struct *to); + #else #define PT_REGS_R8(r) UPT_R8(&(r)->regs) @@ -83,5 +95,9 @@ extern long arch_prctl(struct task_struct *task, int option, unsigned long __user *addr); #endif + #define user_stack_pointer(regs) PT_REGS_SP(regs) + +extern void arch_switch_to(struct task_struct *to); + #endif /* __UM_X86_PTRACE_H */ diff --git a/arch/x86/um/bugs_32.c b/arch/x86/um/bugs_32.c index 33daff4dade4..d29929efcc07 100644 --- a/arch/x86/um/bugs_32.c +++ b/arch/x86/um/bugs_32.c @@ -3,6 +3,7 @@ * Licensed under the GPL */ +#include <arch.h> #include <signal.h> #include <kern_util.h> #include <longjmp.h> diff --git a/arch/x86/um/bugs_64.c b/arch/x86/um/bugs_64.c index 8cc8256c698d..b01295e8a676 100644 --- a/arch/x86/um/bugs_64.c +++ b/arch/x86/um/bugs_64.c @@ -4,6 +4,7 @@ * Licensed under the GPL */ +#include <arch.h> #include <sysdep/ptrace.h> void arch_check_bugs(void) diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c index 650cdbbdaf45..ef50662fc40d 100644 --- a/arch/x86/um/elfcore.c +++ b/arch/x86/um/elfcore.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/elf.h> +#include <linux/elfcore.h> #include <linux/coredump.h> #include <linux/fs.h> #include <linux/mm.h> diff --git a/arch/x86/um/fault.c b/arch/x86/um/fault.c index 84ac7f7b0257..0dde4d613a87 100644 --- a/arch/x86/um/fault.c +++ b/arch/x86/um/fault.c @@ -3,6 +3,7 @@ * Licensed under the GPL */ +#include <arch.h> #include <sysdep/ptrace.h> /* These two are from asm-um/uaccess.h and linux/module.h, check them. */ diff --git a/arch/x86/um/ldt.c b/arch/x86/um/ldt.c deleted file mode 100644 index 255a44dd415a..000000000000 --- a/arch/x86/um/ldt.c +++ /dev/null @@ -1,380 +0,0 @@ -/* - * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) - * Licensed under the GPL - */ - -#include <linux/mm.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/syscalls.h> -#include <linux/uaccess.h> -#include <asm/unistd.h> -#include <os.h> -#include <skas.h> -#include <sysdep/tls.h> - -static inline int modify_ldt (int func, void *ptr, unsigned long bytecount) -{ - return syscall(__NR_modify_ldt, func, ptr, bytecount); -} - -static long write_ldt_entry(struct mm_id *mm_idp, int func, - struct user_desc *desc, void **addr, int done) -{ - long res; - void *stub_addr; - - BUILD_BUG_ON(sizeof(*desc) % sizeof(long)); - - res = syscall_stub_data(mm_idp, (unsigned long *)desc, - sizeof(*desc) / sizeof(long), - addr, &stub_addr); - if (!res) { - unsigned long args[] = { func, - (unsigned long)stub_addr, - sizeof(*desc), - 0, 0, 0 }; - res = run_syscall_stub(mm_idp, __NR_modify_ldt, args, - 0, addr, done); - } - - return res; -} - -/* - * In skas mode, we hold our own ldt data in UML. - * Thus, the code implementing sys_modify_ldt_skas - * is very similar to (and mostly stolen from) sys_modify_ldt - * for arch/i386/kernel/ldt.c - * The routines copied and modified in part are: - * - read_ldt - * - read_default_ldt - * - write_ldt - * - sys_modify_ldt_skas - */ - -static int read_ldt(void __user * ptr, unsigned long bytecount) -{ - int i, err = 0; - unsigned long size; - uml_ldt_t *ldt = ¤t->mm->context.arch.ldt; - - if (!ldt->entry_count) - goto out; - if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES) - bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES; - err = bytecount; - - mutex_lock(&ldt->lock); - if (ldt->entry_count <= LDT_DIRECT_ENTRIES) { - size = LDT_ENTRY_SIZE*LDT_DIRECT_ENTRIES; - if (size > bytecount) - size = bytecount; - if (copy_to_user(ptr, ldt->u.entries, size)) - err = -EFAULT; - bytecount -= size; - ptr += size; - } - else { - for (i=0; i<ldt->entry_count/LDT_ENTRIES_PER_PAGE && bytecount; - i++) { - size = PAGE_SIZE; - if (size > bytecount) - size = bytecount; - if (copy_to_user(ptr, ldt->u.pages[i], size)) { - err = -EFAULT; - break; - } - bytecount -= size; - ptr += size; - } - } - mutex_unlock(&ldt->lock); - - if (bytecount == 0 || err == -EFAULT) - goto out; - - if (clear_user(ptr, bytecount)) - err = -EFAULT; - -out: - return err; -} - -static int read_default_ldt(void __user * ptr, unsigned long bytecount) -{ - int err; - - if (bytecount > 5*LDT_ENTRY_SIZE) - bytecount = 5*LDT_ENTRY_SIZE; - - err = bytecount; - /* - * UML doesn't support lcall7 and lcall27. - * So, we don't really have a default ldt, but emulate - * an empty ldt of common host default ldt size. - */ - if (clear_user(ptr, bytecount)) - err = -EFAULT; - - return err; -} - -static int write_ldt(void __user * ptr, unsigned long bytecount, int func) -{ - uml_ldt_t *ldt = ¤t->mm->context.arch.ldt; - struct mm_id * mm_idp = ¤t->mm->context.id; - int i, err; - struct user_desc ldt_info; - struct ldt_entry entry0, *ldt_p; - void *addr = NULL; - - err = -EINVAL; - if (bytecount != sizeof(ldt_info)) - goto out; - err = -EFAULT; - if (copy_from_user(&ldt_info, ptr, sizeof(ldt_info))) - goto out; - - err = -EINVAL; - if (ldt_info.entry_number >= LDT_ENTRIES) - goto out; - if (ldt_info.contents == 3) { - if (func == 1) - goto out; - if (ldt_info.seg_not_present == 0) - goto out; - } - - mutex_lock(&ldt->lock); - - err = write_ldt_entry(mm_idp, func, &ldt_info, &addr, 1); - if (err) - goto out_unlock; - - if (ldt_info.entry_number >= ldt->entry_count && - ldt_info.entry_number >= LDT_DIRECT_ENTRIES) { - for (i=ldt->entry_count/LDT_ENTRIES_PER_PAGE; - i*LDT_ENTRIES_PER_PAGE <= ldt_info.entry_number; - i++) { - if (i == 0) - memcpy(&entry0, ldt->u.entries, - sizeof(entry0)); - ldt->u.pages[i] = (struct ldt_entry *) - __get_free_page(GFP_KERNEL|__GFP_ZERO); - if (!ldt->u.pages[i]) { - err = -ENOMEM; - /* Undo the change in host */ - memset(&ldt_info, 0, sizeof(ldt_info)); - write_ldt_entry(mm_idp, 1, &ldt_info, &addr, 1); - goto out_unlock; - } - if (i == 0) { - memcpy(ldt->u.pages[0], &entry0, - sizeof(entry0)); - memcpy(ldt->u.pages[0]+1, ldt->u.entries+1, - sizeof(entry0)*(LDT_DIRECT_ENTRIES-1)); - } - ldt->entry_count = (i + 1) * LDT_ENTRIES_PER_PAGE; - } - } - if (ldt->entry_count <= ldt_info.entry_number) - ldt->entry_count = ldt_info.entry_number + 1; - - if (ldt->entry_count <= LDT_DIRECT_ENTRIES) - ldt_p = ldt->u.entries + ldt_info.entry_number; - else - ldt_p = ldt->u.pages[ldt_info.entry_number/LDT_ENTRIES_PER_PAGE] + - ldt_info.entry_number%LDT_ENTRIES_PER_PAGE; - - if (ldt_info.base_addr == 0 && ldt_info.limit == 0 && - (func == 1 || LDT_empty(&ldt_info))) { - ldt_p->a = 0; - ldt_p->b = 0; - } - else{ - if (func == 1) - ldt_info.useable = 0; - ldt_p->a = LDT_entry_a(&ldt_info); - ldt_p->b = LDT_entry_b(&ldt_info); - } - err = 0; - -out_unlock: - mutex_unlock(&ldt->lock); -out: - return err; -} - -static long do_modify_ldt_skas(int func, void __user *ptr, - unsigned long bytecount) -{ - int ret = -ENOSYS; - - switch (func) { - case 0: - ret = read_ldt(ptr, bytecount); - break; - case 1: - case 0x11: - ret = write_ldt(ptr, bytecount, func); - break; - case 2: - ret = read_default_ldt(ptr, bytecount); - break; - } - return ret; -} - -static DEFINE_SPINLOCK(host_ldt_lock); -static short dummy_list[9] = {0, -1}; -static short * host_ldt_entries = NULL; - -static void ldt_get_host_info(void) -{ - long ret; - struct ldt_entry * ldt; - short *tmp; - int i, size, k, order; - - spin_lock(&host_ldt_lock); - - if (host_ldt_entries != NULL) { - spin_unlock(&host_ldt_lock); - return; - } - host_ldt_entries = dummy_list+1; - - spin_unlock(&host_ldt_lock); - - for (i = LDT_PAGES_MAX-1, order=0; i; i>>=1, order++) - ; - - ldt = (struct ldt_entry *) - __get_free_pages(GFP_KERNEL|__GFP_ZERO, order); - if (ldt == NULL) { - printk(KERN_ERR "ldt_get_host_info: couldn't allocate buffer " - "for host ldt\n"); - return; - } - - ret = modify_ldt(0, ldt, (1<<order)*PAGE_SIZE); - if (ret < 0) { - printk(KERN_ERR "ldt_get_host_info: couldn't read host ldt\n"); - goto out_free; - } - if (ret == 0) { - /* default_ldt is active, simply write an empty entry 0 */ - host_ldt_entries = dummy_list; - goto out_free; - } - - for (i=0, size=0; i<ret/LDT_ENTRY_SIZE; i++) { - if (ldt[i].a != 0 || ldt[i].b != 0) - size++; - } - - if (size < ARRAY_SIZE(dummy_list)) - host_ldt_entries = dummy_list; - else { - size = (size + 1) * sizeof(dummy_list[0]); - tmp = kmalloc(size, GFP_KERNEL); - if (tmp == NULL) { - printk(KERN_ERR "ldt_get_host_info: couldn't allocate " - "host ldt list\n"); - goto out_free; - } - host_ldt_entries = tmp; - } - - for (i=0, k=0; i<ret/LDT_ENTRY_SIZE; i++) { - if (ldt[i].a != 0 || ldt[i].b != 0) - host_ldt_entries[k++] = i; - } - host_ldt_entries[k] = -1; - -out_free: - free_pages((unsigned long)ldt, order); -} - -long init_new_ldt(struct mm_context *new_mm, struct mm_context *from_mm) -{ - struct user_desc desc; - short * num_p; - int i; - long page, err=0; - void *addr = NULL; - - - mutex_init(&new_mm->arch.ldt.lock); - - if (!from_mm) { - memset(&desc, 0, sizeof(desc)); - /* - * Now we try to retrieve info about the ldt, we - * inherited from the host. All ldt-entries found - * will be reset in the following loop - */ - ldt_get_host_info(); - for (num_p=host_ldt_entries; *num_p != -1; num_p++) { - desc.entry_number = *num_p; - err = write_ldt_entry(&new_mm->id, 1, &desc, - &addr, *(num_p + 1) == -1); - if (err) - break; - } - new_mm->arch.ldt.entry_count = 0; - - goto out; - } - - /* - * Our local LDT is used to supply the data for - * modify_ldt(READLDT), if PTRACE_LDT isn't available, - * i.e., we have to use the stub for modify_ldt, which - * can't handle the big read buffer of up to 64kB. - */ - mutex_lock(&from_mm->arch.ldt.lock); - if (from_mm->arch.ldt.entry_count <= LDT_DIRECT_ENTRIES) - memcpy(new_mm->arch.ldt.u.entries, from_mm->arch.ldt.u.entries, - sizeof(new_mm->arch.ldt.u.entries)); - else { - i = from_mm->arch.ldt.entry_count / LDT_ENTRIES_PER_PAGE; - while (i-->0) { - page = __get_free_page(GFP_KERNEL|__GFP_ZERO); - if (!page) { - err = -ENOMEM; - break; - } - new_mm->arch.ldt.u.pages[i] = - (struct ldt_entry *) page; - memcpy(new_mm->arch.ldt.u.pages[i], - from_mm->arch.ldt.u.pages[i], PAGE_SIZE); - } - } - new_mm->arch.ldt.entry_count = from_mm->arch.ldt.entry_count; - mutex_unlock(&from_mm->arch.ldt.lock); - - out: - return err; -} - - -void free_ldt(struct mm_context *mm) -{ - int i; - - if (mm->arch.ldt.entry_count > LDT_DIRECT_ENTRIES) { - i = mm->arch.ldt.entry_count / LDT_ENTRIES_PER_PAGE; - while (i-- > 0) - free_page((long) mm->arch.ldt.u.pages[i]); - } - mm->arch.ldt.entry_count = 0; -} - -SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr , - unsigned long , bytecount) -{ - /* See non-um modify_ldt() for why we do this cast */ - return (unsigned int)do_modify_ldt_skas(func, ptr, bytecount); -} diff --git a/arch/x86/um/os-Linux/Makefile b/arch/x86/um/os-Linux/Makefile index 5249bbc30dcd..77a308aaa5ec 100644 --- a/arch/x86/um/os-Linux/Makefile +++ b/arch/x86/um/os-Linux/Makefile @@ -3,7 +3,7 @@ # Licensed under the GPL # -obj-y = registers.o task_size.o mcontext.o +obj-y = registers.o mcontext.o obj-$(CONFIG_X86_32) += tls.o diff --git a/arch/x86/um/os-Linux/mcontext.c b/arch/x86/um/os-Linux/mcontext.c index 49c3744cac37..a21403df6663 100644 --- a/arch/x86/um/os-Linux/mcontext.c +++ b/arch/x86/um/os-Linux/mcontext.c @@ -1,8 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 -#include <sys/ucontext.h> #define __FRAME_OFFSETS +#include <linux/errno.h> +#include <linux/string.h> +#include <sys/ucontext.h> #include <asm/ptrace.h> +#include <asm/sigcontext.h> #include <sysdep/ptrace.h> +#include <sysdep/mcontext.h> +#include <arch.h> void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc) { @@ -16,6 +21,10 @@ void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc) COPY2(UESP, ESP); /* sic */ COPY(EBX); COPY(EDX); COPY(ECX); COPY(EAX); COPY(EIP); COPY_SEG_CPL3(CS); COPY(EFL); COPY_SEG_CPL3(SS); +#undef COPY2 +#undef COPY +#undef COPY_SEG +#undef COPY_SEG_CPL3 #else #define COPY2(X,Y) regs->gp[X/sizeof(unsigned long)] = mc->gregs[REG_##Y] #define COPY(X) regs->gp[X/sizeof(unsigned long)] = mc->gregs[REG_##X] @@ -26,7 +35,226 @@ void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc) COPY(RIP); COPY2(EFLAGS, EFL); COPY2(CS, CSGSFS); - regs->gp[CS / sizeof(unsigned long)] &= 0xffff; - regs->gp[CS / sizeof(unsigned long)] |= 3; + regs->gp[SS / sizeof(unsigned long)] = mc->gregs[REG_CSGSFS] >> 48; +#undef COPY2 +#undef COPY +#endif +} + +void mc_set_rip(void *_mc, void *target) +{ + mcontext_t *mc = _mc; + +#ifdef __i386__ + mc->gregs[REG_EIP] = (unsigned long)target; +#else + mc->gregs[REG_RIP] = (unsigned long)target; #endif } + +/* Same thing, but the copy macros are turned around. */ +void get_mc_from_regs(struct uml_pt_regs *regs, mcontext_t *mc, int single_stepping) +{ +#ifdef __i386__ +#define COPY2(X,Y) mc->gregs[REG_##Y] = regs->gp[X] +#define COPY(X) mc->gregs[REG_##X] = regs->gp[X] +#define COPY_SEG(X) mc->gregs[REG_##X] = regs->gp[X] & 0xffff; +#define COPY_SEG_CPL3(X) mc->gregs[REG_##X] = (regs->gp[X] & 0xffff) | 3; + COPY_SEG(GS); COPY_SEG(FS); COPY_SEG(ES); COPY_SEG(DS); + COPY(EDI); COPY(ESI); COPY(EBP); + COPY2(UESP, ESP); /* sic */ + COPY(EBX); COPY(EDX); COPY(ECX); COPY(EAX); + COPY(EIP); COPY_SEG_CPL3(CS); COPY(EFL); COPY_SEG_CPL3(SS); +#else +#define COPY2(X,Y) mc->gregs[REG_##Y] = regs->gp[X/sizeof(unsigned long)] +#define COPY(X) mc->gregs[REG_##X] = regs->gp[X/sizeof(unsigned long)] + COPY(R8); COPY(R9); COPY(R10); COPY(R11); + COPY(R12); COPY(R13); COPY(R14); COPY(R15); + COPY(RDI); COPY(RSI); COPY(RBP); COPY(RBX); + COPY(RDX); COPY(RAX); COPY(RCX); COPY(RSP); + COPY(RIP); + COPY2(EFLAGS, EFL); + mc->gregs[REG_CSGSFS] = mc->gregs[REG_CSGSFS] & 0xffffffffffffl; + mc->gregs[REG_CSGSFS] |= (regs->gp[SS / sizeof(unsigned long)] & 0xffff) << 48; +#endif + + if (single_stepping) + mc->gregs[REG_EFL] |= X86_EFLAGS_TF; + else + mc->gregs[REG_EFL] &= ~X86_EFLAGS_TF; +} + +#ifdef CONFIG_X86_32 +struct _xstate_64 { + struct _fpstate_64 fpstate; + struct _header xstate_hdr; + struct _ymmh_state ymmh; + /* New processor state extensions go here: */ +}; + +/* Not quite the right structures as these contain more information */ +int um_i387_from_fxsr(struct _fpstate_32 *i387, + const struct _fpstate_64 *fxsave); +int um_fxsr_from_i387(struct _fpstate_64 *fxsave, + const struct _fpstate_32 *from); +#else +#define _xstate_64 _xstate +#endif + +static struct _fpstate *get_fpstate(struct stub_data *data, + mcontext_t *mcontext, + int *fp_size) +{ + struct _fpstate *res; + + /* Assume floating point registers are on the same page */ + res = (void *)(((unsigned long)mcontext->fpregs & + (UM_KERN_PAGE_SIZE - 1)) + + (unsigned long)&data->sigstack[0]); + + if ((void *)res + sizeof(struct _fpstate) > + (void *)data->sigstack + sizeof(data->sigstack)) + return NULL; + + if (res->sw_reserved.magic1 != FP_XSTATE_MAGIC1) { + *fp_size = sizeof(struct _fpstate); + } else { + char *magic2_addr; + + magic2_addr = (void *)res; + magic2_addr += res->sw_reserved.extended_size; + magic2_addr -= FP_XSTATE_MAGIC2_SIZE; + + /* We still need to be within our stack */ + if ((void *)magic2_addr > + (void *)data->sigstack + sizeof(data->sigstack)) + return NULL; + + /* If we do not read MAGIC2, then we did something wrong */ + if (*(__u32 *)magic2_addr != FP_XSTATE_MAGIC2) + return NULL; + + /* Remove MAGIC2 from the size, we do not save/restore it */ + *fp_size = res->sw_reserved.extended_size - + FP_XSTATE_MAGIC2_SIZE; + } + + return res; +} + +int get_stub_state(struct uml_pt_regs *regs, struct stub_data *data, + unsigned long *fp_size_out) +{ + mcontext_t *mcontext; + struct _fpstate *fpstate_stub; + struct _xstate_64 *xstate_stub; + int fp_size, xstate_size; + + /* mctx_offset is verified by wait_stub_done_seccomp */ + mcontext = (void *)&data->sigstack[data->mctx_offset]; + + get_regs_from_mc(regs, mcontext); + + fpstate_stub = get_fpstate(data, mcontext, &fp_size); + if (!fpstate_stub) + return -EINVAL; + +#ifdef CONFIG_X86_32 + xstate_stub = (void *)&fpstate_stub->_fxsr_env; + xstate_size = fp_size - offsetof(struct _fpstate_32, _fxsr_env); +#else + xstate_stub = (void *)fpstate_stub; + xstate_size = fp_size; +#endif + + if (fp_size_out) + *fp_size_out = xstate_size; + + if (xstate_size > host_fp_size) + return -ENOSPC; + + memcpy(®s->fp, xstate_stub, xstate_size); + + /* We do not need to read the x86_64 FS_BASE/GS_BASE registers as + * we do not permit userspace to set them directly. + */ + +#ifdef CONFIG_X86_32 + /* Read the i387 legacy FP registers */ + if (um_fxsr_from_i387((void *)®s->fp, fpstate_stub)) + return -EINVAL; +#endif + + return 0; +} + +/* Copied because we cannot include regset.h here. */ +struct task_struct; +struct user_regset; +struct membuf { + void *p; + size_t left; +}; + +int fpregs_legacy_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to); + +int set_stub_state(struct uml_pt_regs *regs, struct stub_data *data, + int single_stepping) +{ + mcontext_t *mcontext; + struct _fpstate *fpstate_stub; + struct _xstate_64 *xstate_stub; + int fp_size, xstate_size; + + /* mctx_offset is verified by wait_stub_done_seccomp */ + mcontext = (void *)&data->sigstack[data->mctx_offset]; + + if ((unsigned long)mcontext < (unsigned long)data->sigstack || + (unsigned long)mcontext > + (unsigned long) data->sigstack + + sizeof(data->sigstack) - sizeof(*mcontext)) + return -EINVAL; + + get_mc_from_regs(regs, mcontext, single_stepping); + + fpstate_stub = get_fpstate(data, mcontext, &fp_size); + if (!fpstate_stub) + return -EINVAL; + +#ifdef CONFIG_X86_32 + xstate_stub = (void *)&fpstate_stub->_fxsr_env; + xstate_size = fp_size - offsetof(struct _fpstate_32, _fxsr_env); +#else + xstate_stub = (void *)fpstate_stub; + xstate_size = fp_size; +#endif + + memcpy(xstate_stub, ®s->fp, xstate_size); + +#ifdef __i386__ + /* + * On x86, the GDT entries are updated by arch_set_tls. + */ + + /* Store the i387 legacy FP registers which the host will use */ + if (um_i387_from_fxsr(fpstate_stub, (void *)®s->fp)) + return -EINVAL; +#else + /* + * On x86_64, we need to sync the FS_BASE/GS_BASE registers using the + * arch specific data. + */ + if (data->arch_data.fs_base != regs->gp[FS_BASE / sizeof(unsigned long)]) { + data->arch_data.fs_base = regs->gp[FS_BASE / sizeof(unsigned long)]; + data->arch_data.sync |= STUB_SYNC_FS_BASE; + } + if (data->arch_data.gs_base != regs->gp[GS_BASE / sizeof(unsigned long)]) { + data->arch_data.gs_base = regs->gp[GS_BASE / sizeof(unsigned long)]; + data->arch_data.sync |= STUB_SYNC_GS_BASE; + } +#endif + + return 0; +} diff --git a/arch/x86/um/os-Linux/registers.c b/arch/x86/um/os-Linux/registers.c index df8f4b4bf98b..eb1cdadc8a61 100644 --- a/arch/x86/um/os-Linux/registers.c +++ b/arch/x86/um/os-Linux/registers.c @@ -16,132 +16,72 @@ #include <asm/sigcontext.h> #include <linux/elf.h> #include <registers.h> +#include <sys/mman.h> -int have_xstate_support; +static unsigned long ptrace_regset; +unsigned long host_fp_size; -int save_i387_registers(int pid, unsigned long *fp_regs) -{ - if (ptrace(PTRACE_GETFPREGS, pid, 0, fp_regs) < 0) - return -errno; - return 0; -} - -int save_fp_registers(int pid, unsigned long *fp_regs) +int get_fp_registers(int pid, unsigned long *regs) { -#ifdef PTRACE_GETREGSET - struct iovec iov; + struct iovec iov = { + .iov_base = regs, + .iov_len = host_fp_size, + }; - if (have_xstate_support) { - iov.iov_base = fp_regs; - iov.iov_len = FP_SIZE * sizeof(unsigned long); - if (ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov) < 0) - return -errno; - return 0; - } else -#endif - return save_i387_registers(pid, fp_regs); -} - -int restore_i387_registers(int pid, unsigned long *fp_regs) -{ - if (ptrace(PTRACE_SETFPREGS, pid, 0, fp_regs) < 0) + if (ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov) < 0) return -errno; return 0; } -int restore_fp_registers(int pid, unsigned long *fp_regs) -{ -#ifdef PTRACE_SETREGSET - struct iovec iov; - if (have_xstate_support) { - iov.iov_base = fp_regs; - iov.iov_len = FP_SIZE * sizeof(unsigned long); - if (ptrace(PTRACE_SETREGSET, pid, NT_X86_XSTATE, &iov) < 0) - return -errno; - return 0; - } else -#endif - return restore_i387_registers(pid, fp_regs); -} - -#ifdef __i386__ -int have_fpx_regs = 1; -int save_fpx_registers(int pid, unsigned long *fp_regs) +int put_fp_registers(int pid, unsigned long *regs) { - if (ptrace(PTRACE_GETFPXREGS, pid, 0, fp_regs) < 0) - return -errno; - return 0; -} + struct iovec iov = { + .iov_base = regs, + .iov_len = host_fp_size, + }; -int restore_fpx_registers(int pid, unsigned long *fp_regs) -{ - if (ptrace(PTRACE_SETFPXREGS, pid, 0, fp_regs) < 0) + if (ptrace(PTRACE_SETREGSET, pid, ptrace_regset, &iov) < 0) return -errno; return 0; } -int get_fp_registers(int pid, unsigned long *regs) -{ - if (have_fpx_regs) - return save_fpx_registers(pid, regs); - else - return save_fp_registers(pid, regs); -} - -int put_fp_registers(int pid, unsigned long *regs) -{ - if (have_fpx_regs) - return restore_fpx_registers(pid, regs); - else - return restore_fp_registers(pid, regs); -} - -void arch_init_registers(int pid) +int arch_init_registers(int pid) { - struct user_fpxregs_struct fpx_regs; - int err; - - err = ptrace(PTRACE_GETFPXREGS, pid, 0, &fpx_regs); - if (!err) - return; - - if (errno != EIO) - panic("check_ptrace : PTRACE_GETFPXREGS failed, errno = %d", - errno); - - have_fpx_regs = 0; -} + struct iovec iov = { + /* Just use plenty of space, it does not cost us anything */ + .iov_len = 2 * 1024 * 1024, + }; + int ret; + + iov.iov_base = mmap(NULL, iov.iov_len, PROT_WRITE | PROT_READ, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (iov.iov_base == MAP_FAILED) + return -ENOMEM; + + /* GDB has x86_xsave_length, which uses x86_cpuid_count */ + ptrace_regset = NT_X86_XSTATE; + ret = ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov); + if (ret) + ret = -errno; + + if (ret == -ENODEV) { +#ifdef CONFIG_X86_32 + ptrace_regset = NT_PRXFPREG; #else + ptrace_regset = NT_PRFPREG; +#endif + iov.iov_len = 2 * 1024 * 1024; + ret = ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov); + if (ret) + ret = -errno; + } -int get_fp_registers(int pid, unsigned long *regs) -{ - return save_fp_registers(pid, regs); -} - -int put_fp_registers(int pid, unsigned long *regs) -{ - return restore_fp_registers(pid, regs); -} - -void arch_init_registers(int pid) -{ -#ifdef PTRACE_GETREGSET - void * fp_regs; - struct iovec iov; - - fp_regs = malloc(FP_SIZE * sizeof(unsigned long)); - if(fp_regs == NULL) - return; + munmap(iov.iov_base, 2 * 1024 * 1024); - iov.iov_base = fp_regs; - iov.iov_len = FP_SIZE * sizeof(unsigned long); - if (ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov) == 0) - have_xstate_support = 1; + host_fp_size = iov.iov_len; - free(fp_regs); -#endif + return ret; } -#endif unsigned long get_thread_reg(int reg, jmp_buf *buf) { diff --git a/arch/x86/um/os-Linux/task_size.c b/arch/x86/um/os-Linux/task_size.c deleted file mode 100644 index 1dc9adc20b1c..000000000000 --- a/arch/x86/um/os-Linux/task_size.c +++ /dev/null @@ -1,151 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <stdio.h> -#include <stdlib.h> -#include <signal.h> -#include <sys/mman.h> -#include <longjmp.h> - -#ifdef __i386__ - -static jmp_buf buf; - -static void segfault(int sig) -{ - longjmp(buf, 1); -} - -static int page_ok(unsigned long page) -{ - unsigned long *address = (unsigned long *) (page << UM_KERN_PAGE_SHIFT); - unsigned long n = ~0UL; - void *mapped = NULL; - int ok = 0; - - /* - * First see if the page is readable. If it is, it may still - * be a VDSO, so we go on to see if it's writable. If not - * then try mapping memory there. If that fails, then we're - * still in the kernel area. As a sanity check, we'll fail if - * the mmap succeeds, but gives us an address different from - * what we wanted. - */ - if (setjmp(buf) == 0) - n = *address; - else { - mapped = mmap(address, UM_KERN_PAGE_SIZE, - PROT_READ | PROT_WRITE, - MAP_FIXED | MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); - if (mapped == MAP_FAILED) - return 0; - if (mapped != address) - goto out; - } - - /* - * Now, is it writeable? If so, then we're in user address - * space. If not, then try mprotecting it and try the write - * again. - */ - if (setjmp(buf) == 0) { - *address = n; - ok = 1; - goto out; - } else if (mprotect(address, UM_KERN_PAGE_SIZE, - PROT_READ | PROT_WRITE) != 0) - goto out; - - if (setjmp(buf) == 0) { - *address = n; - ok = 1; - } - - out: - if (mapped != NULL) - munmap(mapped, UM_KERN_PAGE_SIZE); - return ok; -} - -unsigned long os_get_top_address(void) -{ - struct sigaction sa, old; - unsigned long bottom = 0; - /* - * A 32-bit UML on a 64-bit host gets confused about the VDSO at - * 0xffffe000. It is mapped, is readable, can be reprotected writeable - * and written. However, exec discovers later that it can't be - * unmapped. So, just set the highest address to be checked to just - * below it. This might waste some address space on 4G/4G 32-bit - * hosts, but shouldn't hurt otherwise. - */ - unsigned long top = 0xffffd000 >> UM_KERN_PAGE_SHIFT; - unsigned long test, original; - - printf("Locating the bottom of the address space ... "); - fflush(stdout); - - /* - * We're going to be longjmping out of the signal handler, so - * SA_DEFER needs to be set. - */ - sa.sa_handler = segfault; - sigemptyset(&sa.sa_mask); - sa.sa_flags = SA_NODEFER; - if (sigaction(SIGSEGV, &sa, &old)) { - perror("os_get_top_address"); - exit(1); - } - - /* Manually scan the address space, bottom-up, until we find - * the first valid page (or run out of them). - */ - for (bottom = 0; bottom < top; bottom++) { - if (page_ok(bottom)) - break; - } - - /* If we've got this far, we ran out of pages. */ - if (bottom == top) { - fprintf(stderr, "Unable to determine bottom of address " - "space.\n"); - exit(1); - } - - printf("0x%lx\n", bottom << UM_KERN_PAGE_SHIFT); - printf("Locating the top of the address space ... "); - fflush(stdout); - - original = bottom; - - /* This could happen with a 4G/4G split */ - if (page_ok(top)) - goto out; - - do { - test = bottom + (top - bottom) / 2; - if (page_ok(test)) - bottom = test; - else - top = test; - } while (top - bottom > 1); - -out: - /* Restore the old SIGSEGV handling */ - if (sigaction(SIGSEGV, &old, NULL)) { - perror("os_get_top_address"); - exit(1); - } - top <<= UM_KERN_PAGE_SHIFT; - printf("0x%lx\n", top); - - return top; -} - -#else - -unsigned long os_get_top_address(void) -{ - /* The old value of CONFIG_TOP_ADDR */ - return 0x7fc0002000; -} - -#endif diff --git a/arch/x86/um/os-Linux/tls.c b/arch/x86/um/os-Linux/tls.c index 3e1b1bf6acbc..eed9efe29ade 100644 --- a/arch/x86/um/os-Linux/tls.c +++ b/arch/x86/um/os-Linux/tls.c @@ -6,6 +6,7 @@ #include <sys/syscall.h> #include <unistd.h> +#include <os.h> #include <sysdep/tls.h> #ifndef PTRACE_GET_THREAD_AREA diff --git a/arch/x86/um/ptrace.c b/arch/x86/um/ptrace.c new file mode 100644 index 000000000000..fae8aabad10f --- /dev/null +++ b/arch/x86/um/ptrace.c @@ -0,0 +1,305 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/sched.h> +#include <linux/elf.h> +#include <linux/regset.h> +#include <asm/user32.h> +#include <asm/sigcontext.h> + +#ifdef CONFIG_X86_32 +/* + * FPU tag word conversions. + */ + +static inline unsigned short twd_i387_to_fxsr(unsigned short twd) +{ + unsigned int tmp; /* to avoid 16 bit prefixes in the code */ + + /* Transform each pair of bits into 01 (valid) or 00 (empty) */ + tmp = ~twd; + tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */ + /* and move the valid bits to the lower byte. */ + tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */ + tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */ + tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */ + return tmp; +} + +static inline unsigned long +twd_fxsr_to_i387(const struct user_fxsr_struct *fxsave) +{ + struct _fpxreg *st = NULL; + unsigned long twd = (unsigned long) fxsave->twd; + unsigned long tag; + unsigned long ret = 0xffff0000; + int i; + +#define FPREG_ADDR(f, n) ((char *)&(f)->st_space + (n) * 16) + + for (i = 0; i < 8; i++) { + if (twd & 0x1) { + st = (struct _fpxreg *) FPREG_ADDR(fxsave, i); + + switch (st->exponent & 0x7fff) { + case 0x7fff: + tag = 2; /* Special */ + break; + case 0x0000: + if (!st->significand[0] && + !st->significand[1] && + !st->significand[2] && + !st->significand[3]) { + tag = 1; /* Zero */ + } else { + tag = 2; /* Special */ + } + break; + default: + if (st->significand[3] & 0x8000) + tag = 0; /* Valid */ + else + tag = 2; /* Special */ + break; + } + } else { + tag = 3; /* Empty */ + } + ret |= (tag << (2 * i)); + twd = twd >> 1; + } + return ret; +} + +/* + * Get/set the old 32bit i387 registers (pre-FPX) + * + * We provide simple wrappers for mcontext.c, they are only defined locally + * because mcontext.c is userspace facing and needs to a different definition + * of the structures. + */ +static int _um_i387_from_fxsr(struct membuf to, + const struct user_fxsr_struct *fxsave) +{ + int i; + + membuf_store(&to, (unsigned long)fxsave->cwd | 0xffff0000ul); + membuf_store(&to, (unsigned long)fxsave->swd | 0xffff0000ul); + membuf_store(&to, twd_fxsr_to_i387(fxsave)); + membuf_store(&to, fxsave->fip); + membuf_store(&to, fxsave->fcs | ((unsigned long)fxsave->fop << 16)); + membuf_store(&to, fxsave->foo); + membuf_store(&to, fxsave->fos); + + for (i = 0; i < 8; i++) + membuf_write(&to, (void *)fxsave->st_space + i * 16, 10); + + return 0; +} + +int um_i387_from_fxsr(struct user_i387_struct *i387, + const struct user_fxsr_struct *fxsave); + +int um_i387_from_fxsr(struct user_i387_struct *i387, + const struct user_fxsr_struct *fxsave) +{ + struct membuf to = { + .p = i387, + .left = sizeof(*i387), + }; + + return _um_i387_from_fxsr(to, fxsave); +} + +static int fpregs_legacy_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct user_fxsr_struct *fxsave = (void *)target->thread.regs.regs.fp; + + return _um_i387_from_fxsr(to, fxsave); +} + +int um_fxsr_from_i387(struct user_fxsr_struct *fxsave, + const struct user_i387_struct *from); + +int um_fxsr_from_i387(struct user_fxsr_struct *fxsave, + const struct user_i387_struct *from) +{ + int i; + + fxsave->cwd = (unsigned short)(from->cwd & 0xffff); + fxsave->swd = (unsigned short)(from->swd & 0xffff); + fxsave->twd = twd_i387_to_fxsr((unsigned short)(from->twd & 0xffff)); + fxsave->fip = from->fip; + fxsave->fop = (unsigned short)((from->fcs & 0xffff0000ul) >> 16); + fxsave->fcs = (from->fcs & 0xffff); + fxsave->foo = from->foo; + fxsave->fos = from->fos; + + for (i = 0; i < 8; i++) { + memcpy((void *)fxsave->st_space + i * 16, + (void *)from->st_space + i * 10, 10); + } + + return 0; +} + +static int fpregs_legacy_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct user_fxsr_struct *fxsave = (void *)target->thread.regs.regs.fp; + const struct user_i387_struct *from; + struct user_i387_struct buf; + + if (ubuf) { + if (copy_from_user(&buf, ubuf, sizeof(buf))) + return -EFAULT; + from = &buf; + } else { + from = kbuf; + } + + return um_fxsr_from_i387(fxsave, from); +} +#endif + +static int genregs_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + int reg; + + for (reg = 0; to.left; reg++) + membuf_store(&to, getreg(target, reg * sizeof(unsigned long))); + return 0; +} + +static int genregs_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret = 0; + + if (kbuf) { + const unsigned long *k = kbuf; + + while (count >= sizeof(*k) && !ret) { + ret = putreg(target, pos, *k++); + count -= sizeof(*k); + pos += sizeof(*k); + } + } else { + const unsigned long __user *u = ubuf; + + while (count >= sizeof(*u) && !ret) { + unsigned long word; + + ret = __get_user(word, u++); + if (ret) + break; + ret = putreg(target, pos, word); + count -= sizeof(*u); + pos += sizeof(*u); + } + } + return ret; +} + +static int generic_fpregs_active(struct task_struct *target, const struct user_regset *regset) +{ + return regset->n; +} + +static int generic_fpregs_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + void *fpregs = task_pt_regs(target)->regs.fp; + + membuf_write(&to, fpregs, regset->size * regset->n); + return 0; +} + +static int generic_fpregs_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + void *fpregs = task_pt_regs(target)->regs.fp; + + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, + fpregs, 0, regset->size * regset->n); +} + +static struct user_regset uml_regsets[] __ro_after_init = { + [REGSET_GENERAL] = { + .core_note_type = NT_PRSTATUS, + .n = sizeof(struct user_regs_struct) / sizeof(long), + .size = sizeof(long), + .align = sizeof(long), + .regset_get = genregs_get, + .set = genregs_set + }, +#ifdef CONFIG_X86_32 + /* Old FP registers, they are needed in signal frames */ + [REGSET_FP_LEGACY] = { + .core_note_type = NT_PRFPREG, + .n = sizeof(struct user_i387_ia32_struct) / sizeof(long), + .size = sizeof(long), + .align = sizeof(long), + .active = generic_fpregs_active, + .regset_get = fpregs_legacy_get, + .set = fpregs_legacy_set, + }, +#endif + [REGSET_FP] = { +#ifdef CONFIG_X86_32 + .core_note_type = NT_PRXFPREG, + .n = sizeof(struct user32_fxsr_struct) / sizeof(long), +#else + .core_note_type = NT_PRFPREG, + .n = sizeof(struct user_i387_struct) / sizeof(long), +#endif + .size = sizeof(long), + .align = sizeof(long), + .active = generic_fpregs_active, + .regset_get = generic_fpregs_get, + .set = generic_fpregs_set, + }, + [REGSET_XSTATE] = { + .core_note_type = NT_X86_XSTATE, + .size = sizeof(long), + .align = sizeof(long), + .active = generic_fpregs_active, + .regset_get = generic_fpregs_get, + .set = generic_fpregs_set, + }, + /* TODO: Add TLS regset for 32bit */ +}; + +static const struct user_regset_view user_uml_view = { +#ifdef CONFIG_X86_32 + .name = "i386", .e_machine = EM_386, +#else + .name = "x86_64", .e_machine = EM_X86_64, +#endif + .regsets = uml_regsets, .n = ARRAY_SIZE(uml_regsets) +}; + +const struct user_regset_view * +task_user_regset_view(struct task_struct *tsk) +{ + return &user_uml_view; +} + +static int __init init_regset_xstate_info(void) +{ + uml_regsets[REGSET_XSTATE].n = + host_fp_size / uml_regsets[REGSET_XSTATE].size; + + return 0; +} +arch_initcall(init_regset_xstate_info); diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c index 7f1abde2c84b..3af3cb821524 100644 --- a/arch/x86/um/ptrace_32.c +++ b/arch/x86/um/ptrace_32.c @@ -6,12 +6,11 @@ #include <linux/mm.h> #include <linux/sched.h> #include <linux/uaccess.h> +#include <linux/regset.h> #include <asm/ptrace-abi.h> #include <registers.h> #include <skas.h> -extern int arch_switch_tls(struct task_struct *to); - void arch_switch_to(struct task_struct *to) { int err = arch_switch_tls(to); @@ -170,65 +169,6 @@ int peek_user(struct task_struct *child, long addr, long data) return put_user(tmp, (unsigned long __user *) data); } -static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) -{ - int err, n, cpu = task_cpu(child); - struct user_i387_struct fpregs; - - err = save_i387_registers(userspace_pid[cpu], - (unsigned long *) &fpregs); - if (err) - return err; - - n = copy_to_user(buf, &fpregs, sizeof(fpregs)); - if(n > 0) - return -EFAULT; - - return n; -} - -static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) -{ - int n, cpu = task_cpu(child); - struct user_i387_struct fpregs; - - n = copy_from_user(&fpregs, buf, sizeof(fpregs)); - if (n > 0) - return -EFAULT; - - return restore_i387_registers(userspace_pid[cpu], - (unsigned long *) &fpregs); -} - -static int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) -{ - int err, n, cpu = task_cpu(child); - struct user_fxsr_struct fpregs; - - err = save_fpx_registers(userspace_pid[cpu], (unsigned long *) &fpregs); - if (err) - return err; - - n = copy_to_user(buf, &fpregs, sizeof(fpregs)); - if(n > 0) - return -EFAULT; - - return n; -} - -static int set_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) -{ - int n, cpu = task_cpu(child); - struct user_fxsr_struct fpregs; - - n = copy_from_user(&fpregs, buf, sizeof(fpregs)); - if (n > 0) - return -EFAULT; - - return restore_fpx_registers(userspace_pid[cpu], - (unsigned long *) &fpregs); -} - long subarch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data) { @@ -236,17 +176,25 @@ long subarch_ptrace(struct task_struct *child, long request, void __user *datap = (void __user *) data; switch (request) { case PTRACE_GETFPREGS: /* Get the child FPU state. */ - ret = get_fpregs(datap, child); - break; + return copy_regset_to_user(child, task_user_regset_view(child), + REGSET_FP_LEGACY, + 0, sizeof(struct user_i387_struct), + datap); case PTRACE_SETFPREGS: /* Set the child FPU state. */ - ret = set_fpregs(datap, child); - break; + return copy_regset_from_user(child, task_user_regset_view(child), + REGSET_FP_LEGACY, + 0, sizeof(struct user_i387_struct), + datap); case PTRACE_GETFPXREGS: /* Get the child FPU state. */ - ret = get_fpxregs(datap, child); - break; + return copy_regset_to_user(child, task_user_regset_view(child), + REGSET_FP, + 0, sizeof(struct user_fxsr_struct), + datap); case PTRACE_SETFPXREGS: /* Set the child FPU state. */ - ret = set_fpxregs(datap, child); - break; + return copy_regset_from_user(child, task_user_regset_view(child), + REGSET_FP, + 0, sizeof(struct user_fxsr_struct), + datap); default: ret = -EIO; } diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c index aa68d83d3f44..e0d4120a45c8 100644 --- a/arch/x86/um/ptrace_64.c +++ b/arch/x86/um/ptrace_64.c @@ -8,6 +8,7 @@ #include <linux/mm.h> #include <linux/sched.h> #include <linux/errno.h> +#include <linux/regset.h> #define __FRAME_OFFSETS #include <asm/ptrace.h> #include <linux/uaccess.h> @@ -188,36 +189,6 @@ int peek_user(struct task_struct *child, long addr, long data) return put_user(tmp, (unsigned long *) data); } -static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) -{ - int err, n, cpu = ((struct thread_info *) child->stack)->cpu; - struct user_i387_struct fpregs; - - err = save_i387_registers(userspace_pid[cpu], - (unsigned long *) &fpregs); - if (err) - return err; - - n = copy_to_user(buf, &fpregs, sizeof(fpregs)); - if (n > 0) - return -EFAULT; - - return n; -} - -static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) -{ - int n, cpu = ((struct thread_info *) child->stack)->cpu; - struct user_i387_struct fpregs; - - n = copy_from_user(&fpregs, buf, sizeof(fpregs)); - if (n > 0) - return -EFAULT; - - return restore_i387_registers(userspace_pid[cpu], - (unsigned long *) &fpregs); -} - long subarch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data) { @@ -226,11 +197,15 @@ long subarch_ptrace(struct task_struct *child, long request, switch (request) { case PTRACE_GETFPREGS: /* Get the child FPU state. */ - ret = get_fpregs(datap, child); - break; + return copy_regset_to_user(child, task_user_regset_view(child), + REGSET_FP, + 0, sizeof(struct user_i387_struct), + datap); case PTRACE_SETFPREGS: /* Set the child FPU state. */ - ret = set_fpregs(datap, child); - break; + return copy_regset_from_user(child, task_user_regset_view(child), + REGSET_FP, + 0, sizeof(struct user_i387_struct), + datap); case PTRACE_ARCH_PRCTL: /* XXX Calls ptrace on the host - needs some SMP thinking */ ret = arch_prctl(child, data, (void __user *) addr); diff --git a/arch/x86/um/shared/sysdep/archsetjmp.h b/arch/x86/um/shared/sysdep/archsetjmp.h index 166cedbab926..8c81d1a604a9 100644 --- a/arch/x86/um/shared/sysdep/archsetjmp.h +++ b/arch/x86/um/shared/sysdep/archsetjmp.h @@ -1,6 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __X86_UM_SYSDEP_ARCHSETJMP_H +#define __X86_UM_SYSDEP_ARCHSETJMP_H + #ifdef __i386__ #include "archsetjmp_32.h" #else #include "archsetjmp_64.h" #endif + +unsigned long get_thread_reg(int reg, jmp_buf *buf); + +#endif /* __X86_UM_SYSDEP_ARCHSETJMP_H */ diff --git a/arch/x86/um/shared/sysdep/faultinfo_32.h b/arch/x86/um/shared/sysdep/faultinfo_32.h index b6f2437ec29c..9193a7790a71 100644 --- a/arch/x86/um/shared/sysdep/faultinfo_32.h +++ b/arch/x86/um/shared/sysdep/faultinfo_32.h @@ -29,4 +29,16 @@ struct faultinfo { #define PTRACE_FULL_FAULTINFO 0 +#define ___backtrack_faulted(_faulted) \ + asm volatile ( \ + "movl $__get_kernel_nofault_faulted_%=,%1\n" \ + "mov $0, %0\n" \ + "jmp _end_%=\n" \ + "__get_kernel_nofault_faulted_%=:\n" \ + "mov $1, %0;" \ + "_end_%=:" \ + : "=r" (_faulted), \ + "=m" (current->thread.segv_continue) :: \ + ) + #endif diff --git a/arch/x86/um/shared/sysdep/faultinfo_64.h b/arch/x86/um/shared/sysdep/faultinfo_64.h index ee88f88974ea..61e4ca1e0ab5 100644 --- a/arch/x86/um/shared/sysdep/faultinfo_64.h +++ b/arch/x86/um/shared/sysdep/faultinfo_64.h @@ -29,4 +29,16 @@ struct faultinfo { #define PTRACE_FULL_FAULTINFO 1 +#define ___backtrack_faulted(_faulted) \ + asm volatile ( \ + "movq $__get_kernel_nofault_faulted_%=,%1\n" \ + "mov $0, %0\n" \ + "jmp _end_%=\n" \ + "__get_kernel_nofault_faulted_%=:\n" \ + "mov $1, %0;" \ + "_end_%=:" \ + : "=r" (_faulted), \ + "=m" (current->thread.segv_continue) :: \ + ) + #endif diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h index a004bffb7b8d..6fd1ed400399 100644 --- a/arch/x86/um/shared/sysdep/kernel-offsets.h +++ b/arch/x86/um/shared/sysdep/kernel-offsets.h @@ -4,7 +4,12 @@ #include <linux/elf.h> #include <linux/crypto.h> #include <linux/kbuild.h> +#include <linux/audit.h> #include <asm/mman.h> +#include <asm/seccomp.h> + +/* workaround for a warning with -Wmissing-prototypes */ +void foo(void); void foo(void) { diff --git a/arch/x86/um/shared/sysdep/mcontext.h b/arch/x86/um/shared/sysdep/mcontext.h index b724c54da316..6fe490cc5b98 100644 --- a/arch/x86/um/shared/sysdep/mcontext.h +++ b/arch/x86/um/shared/sysdep/mcontext.h @@ -6,7 +6,16 @@ #ifndef __SYS_SIGCONTEXT_X86_H #define __SYS_SIGCONTEXT_X86_H +#include <stub-data.h> + extern void get_regs_from_mc(struct uml_pt_regs *, mcontext_t *); +extern void get_mc_from_regs(struct uml_pt_regs *regs, mcontext_t *mc, + int single_stepping); + +extern int get_stub_state(struct uml_pt_regs *regs, struct stub_data *data, + unsigned long *fp_size_out); +extern int set_stub_state(struct uml_pt_regs *regs, struct stub_data *data, + int single_stepping); #ifdef __i386__ diff --git a/arch/x86/um/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace.h index 6ca4ecabc55b..8f7476ff6e95 100644 --- a/arch/x86/um/shared/sysdep/ptrace.h +++ b/arch/x86/um/shared/sysdep/ptrace.h @@ -56,12 +56,16 @@ struct syscall_args { UPT_SYSCALL_ARG5(r), \ UPT_SYSCALL_ARG6(r) } } ) +extern unsigned long host_fp_size; + struct uml_pt_regs { unsigned long gp[MAX_REG_NR]; - unsigned long fp[MAX_FP_NR]; struct faultinfo faultinfo; long syscall; int is_user; + + /* Dynamically sized FP registers (holds an XSTATE) */ + unsigned long fp[]; }; #define EMPTY_UML_PT_REGS { } @@ -70,6 +74,6 @@ struct uml_pt_regs { #define UPT_FAULTINFO(r) (&(r)->faultinfo) #define UPT_IS_USER(r) ((r)->is_user) -extern int user_context(unsigned long sp); +extern int arch_init_registers(int pid); #endif /* __SYSDEP_X86_PTRACE_H */ diff --git a/arch/x86/um/shared/sysdep/ptrace_32.h b/arch/x86/um/shared/sysdep/ptrace_32.h index 0c4989842fbe..2392470cac4d 100644 --- a/arch/x86/um/shared/sysdep/ptrace_32.h +++ b/arch/x86/um/shared/sysdep/ptrace_32.h @@ -6,8 +6,6 @@ #ifndef __SYSDEP_I386_PTRACE_H #define __SYSDEP_I386_PTRACE_H -#define MAX_FP_NR HOST_FPX_SIZE - #define UPT_SYSCALL_ARG1(r) UPT_BX(r) #define UPT_SYSCALL_ARG2(r) UPT_CX(r) #define UPT_SYSCALL_ARG3(r) UPT_DX(r) @@ -15,6 +13,4 @@ #define UPT_SYSCALL_ARG5(r) UPT_DI(r) #define UPT_SYSCALL_ARG6(r) UPT_BP(r) -extern void arch_init_registers(int pid); - #endif diff --git a/arch/x86/um/shared/sysdep/ptrace_64.h b/arch/x86/um/shared/sysdep/ptrace_64.h index 0dc223aa1c2d..e73573ac871f 100644 --- a/arch/x86/um/shared/sysdep/ptrace_64.h +++ b/arch/x86/um/shared/sysdep/ptrace_64.h @@ -8,8 +8,6 @@ #ifndef __SYSDEP_X86_64_PTRACE_H #define __SYSDEP_X86_64_PTRACE_H -#define MAX_FP_NR HOST_FP_SIZE - #define REGS_R8(r) ((r)[HOST_R8]) #define REGS_R9(r) ((r)[HOST_R9]) #define REGS_R10(r) ((r)[HOST_R10]) @@ -57,6 +55,4 @@ #define UPT_SYSCALL_ARG5(r) UPT_R8(r) #define UPT_SYSCALL_ARG6(r) UPT_R9(r) -extern void arch_init_registers(int pid); - #endif diff --git a/arch/x86/um/shared/sysdep/ptrace_user.h b/arch/x86/um/shared/sysdep/ptrace_user.h index 1d1a824fa652..98da23120538 100644 --- a/arch/x86/um/shared/sysdep/ptrace_user.h +++ b/arch/x86/um/shared/sysdep/ptrace_user.h @@ -11,12 +11,6 @@ #define REGS_IP_INDEX HOST_IP #define REGS_SP_INDEX HOST_SP -#ifdef __i386__ -#define FP_SIZE ((HOST_FPX_SIZE > HOST_FP_SIZE) ? HOST_FPX_SIZE : HOST_FP_SIZE) -#else -#define FP_SIZE HOST_FP_SIZE -#endif - /* * glibc before 2.27 does not include PTRACE_SYSEMU_SINGLESTEP in its enum, * ensure we have a definition by (re-)defining it here. diff --git a/arch/x86/um/shared/sysdep/stub-data.h b/arch/x86/um/shared/sysdep/stub-data.h new file mode 100644 index 000000000000..82b1b7f8ac3d --- /dev/null +++ b/arch/x86/um/shared/sysdep/stub-data.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ARCH_STUB_DATA_H +#define __ARCH_STUB_DATA_H + +#ifdef __i386__ +#include <generated/asm-offsets.h> +#include <asm/ldt.h> + +struct stub_data_arch { + int sync; + struct user_desc tls[UM_KERN_GDT_ENTRY_TLS_ENTRIES]; +}; +#else +#define STUB_SYNC_FS_BASE (1 << 0) +#define STUB_SYNC_GS_BASE (1 << 1) +struct stub_data_arch { + int sync; + unsigned long fs_base; + unsigned long gs_base; +}; +#endif + +#endif /* __ARCH_STUB_DATA_H */ diff --git a/arch/x86/um/shared/sysdep/stub.h b/arch/x86/um/shared/sysdep/stub.h index ce0ca46ad383..4fa58f5b4fca 100644 --- a/arch/x86/um/shared/sysdep/stub.h +++ b/arch/x86/um/shared/sysdep/stub.h @@ -12,4 +12,6 @@ #endif extern void stub_segv_handler(int, siginfo_t *, void *); -extern void stub_clone_handler(void); +extern void stub_syscall_handler(void); +extern void stub_signal_interrupt(int, siginfo_t *, void *); +extern void stub_signal_restorer(void); diff --git a/arch/x86/um/shared/sysdep/stub_32.h b/arch/x86/um/shared/sysdep/stub_32.h index ea8b5a2d67af..df568fc3ceb4 100644 --- a/arch/x86/um/shared/sysdep/stub_32.h +++ b/arch/x86/um/shared/sysdep/stub_32.h @@ -6,6 +6,7 @@ #ifndef __SYSDEP_STUB_H #define __SYSDEP_STUB_H +#include <stddef.h> #include <asm/ptrace.h> #include <generated/asm-offsets.h> @@ -79,33 +80,31 @@ static __always_inline long stub_syscall5(long syscall, long arg1, long arg2, return ret; } -static __always_inline void trap_myself(void) +static __always_inline long stub_syscall6(long syscall, long arg1, long arg2, + long arg3, long arg4, long arg5, + long arg6) { - __asm("int3"); + struct syscall_args { + int ebx, ebp; + } args = { arg1, arg6 }; + long ret; + + __asm__ volatile ("pushl %%ebp;" + "movl 0x4(%%ebx),%%ebp;" + "movl (%%ebx),%%ebx;" + "int $0x80;" + "popl %%ebp" + : "=a" (ret) + : "0" (syscall), "b" (&args), + "c" (arg2), "d" (arg3), "S" (arg4), "D" (arg5) + : "memory"); + + return ret; } -static __always_inline void remap_stack_and_trap(void) +static __always_inline void trap_myself(void) { - __asm__ volatile ( - "movl %%esp,%%ebx ;" - "andl %0,%%ebx ;" - "movl %1,%%eax ;" - "movl %%ebx,%%edi ; addl %2,%%edi ; movl (%%edi),%%edi ;" - "movl %%ebx,%%ebp ; addl %3,%%ebp ; movl (%%ebp),%%ebp ;" - "int $0x80 ;" - "addl %4,%%ebx ; movl %%eax, (%%ebx) ;" - "int $3" - : : - "g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1)), - "g" (STUB_MMAP_NR), - "g" (UML_STUB_FIELD_FD), - "g" (UML_STUB_FIELD_OFFSET), - "g" (UML_STUB_FIELD_CHILD_ERR), - "c" (STUB_DATA_PAGES * UM_KERN_PAGE_SIZE), - "d" (PROT_READ | PROT_WRITE), - "S" (MAP_FIXED | MAP_SHARED) - : - "memory"); + __asm("int3"); } static __always_inline void *get_stub_data(void) @@ -113,11 +112,36 @@ static __always_inline void *get_stub_data(void) unsigned long ret; asm volatile ( - "movl %%esp,%0 ;" - "andl %1,%0" + "call _here_%=;" + "_here_%=:" + "popl %0;" + "andl %1, %0 ;" + "addl %2, %0 ;" : "=a" (ret) - : "g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1))); + : "g" (~(UM_KERN_PAGE_SIZE - 1)), + "g" (UM_KERN_PAGE_SIZE)); return (void *)ret; } + +#define stub_start(fn) \ + asm volatile ( \ + "subl %0,%%esp ;" \ + "movl %1, %%eax ; " \ + "call *%%eax ;" \ + :: "i" ((1 + STUB_DATA_PAGES) * UM_KERN_PAGE_SIZE), \ + "i" (&fn)) + +static __always_inline void +stub_seccomp_restore_state(struct stub_data_arch *arch) +{ + for (int i = 0; i < sizeof(arch->tls) / sizeof(arch->tls[0]); i++) { + if (arch->sync & (1 << i)) + stub_syscall1(__NR_set_thread_area, + (unsigned long) &arch->tls[i]); + } + + arch->sync = 0; +} + #endif diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h index b24168ef0ac4..9cfd31afa769 100644 --- a/arch/x86/um/shared/sysdep/stub_64.h +++ b/arch/x86/um/shared/sysdep/stub_64.h @@ -6,9 +6,11 @@ #ifndef __SYSDEP_STUB_H #define __SYSDEP_STUB_H +#include <stddef.h> #include <sysdep/ptrace_user.h> #include <generated/asm-offsets.h> #include <linux/stddef.h> +#include <asm/prctl.h> #define STUB_MMAP_NR __NR_mmap #define MMAP_OFFSET(o) (o) @@ -27,6 +29,17 @@ static __always_inline long stub_syscall0(long syscall) return ret; } +static __always_inline long stub_syscall1(long syscall, long arg1) +{ + long ret; + + __asm__ volatile (__syscall + : "=a" (ret) + : "0" (syscall), "D" (arg1) : __syscall_clobber ); + + return ret; +} + static __always_inline long stub_syscall2(long syscall, long arg1, long arg2) { long ret; @@ -79,35 +92,25 @@ static __always_inline long stub_syscall5(long syscall, long arg1, long arg2, return ret; } -static __always_inline void trap_myself(void) +static __always_inline long stub_syscall6(long syscall, long arg1, long arg2, + long arg3, long arg4, long arg5, + long arg6) { - __asm("int3"); + long ret; + + __asm__ volatile ("movq %5,%%r10 ; movq %6,%%r8 ; movq %7,%%r9 ; " + __syscall + : "=a" (ret) + : "0" (syscall), "D" (arg1), "S" (arg2), "d" (arg3), + "g" (arg4), "g" (arg5), "g" (arg6) + : __syscall_clobber, "r10", "r8", "r9"); + + return ret; } -static __always_inline void remap_stack_and_trap(void) +static __always_inline void trap_myself(void) { - __asm__ volatile ( - "movq %0,%%rax ;" - "movq %%rsp,%%rdi ;" - "andq %1,%%rdi ;" - "movq %2,%%r10 ;" - "movq %%rdi,%%r8 ; addq %3,%%r8 ; movq (%%r8),%%r8 ;" - "movq %%rdi,%%r9 ; addq %4,%%r9 ; movq (%%r9),%%r9 ;" - __syscall ";" - "movq %%rsp,%%rdi ; andq %1,%%rdi ;" - "addq %5,%%rdi ; movq %%rax, (%%rdi) ;" - "int3" - : : - "g" (STUB_MMAP_NR), - "g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1)), - "g" (MAP_FIXED | MAP_SHARED), - "g" (UML_STUB_FIELD_FD), - "g" (UML_STUB_FIELD_OFFSET), - "g" (UML_STUB_FIELD_CHILD_ERR), - "S" (STUB_DATA_PAGES * UM_KERN_PAGE_SIZE), - "d" (PROT_READ | PROT_WRITE) - : - __syscall_clobber, "r10", "r8", "r9"); + __asm("int3"); } static __always_inline void *get_stub_data(void) @@ -115,11 +118,37 @@ static __always_inline void *get_stub_data(void) unsigned long ret; asm volatile ( - "movq %%rsp,%0 ;" - "andq %1,%0" + "lea 0(%%rip), %0;" + "andq %1, %0 ;" + "addq %2, %0 ;" : "=a" (ret) - : "g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1))); + : "g" (~(UM_KERN_PAGE_SIZE - 1)), + "g" (UM_KERN_PAGE_SIZE)); return (void *)ret; } + +#define stub_start(fn) \ + asm volatile ( \ + "subq %0,%%rsp ;" \ + "movq %1,%%rax ;" \ + "call *%%rax ;" \ + :: "i" ((1 + STUB_DATA_PAGES) * UM_KERN_PAGE_SIZE), \ + "i" (&fn)) + +static __always_inline void +stub_seccomp_restore_state(struct stub_data_arch *arch) +{ + /* + * We could use _writefsbase_u64/_writegsbase_u64 if the host reports + * support in the hwcaps (HWCAP2_FSGSBASE). + */ + if (arch->sync & STUB_SYNC_FS_BASE) + stub_syscall2(__NR_arch_prctl, ARCH_SET_FS, arch->fs_base); + if (arch->sync & STUB_SYNC_GS_BASE) + stub_syscall2(__NR_arch_prctl, ARCH_SET_GS, arch->gs_base); + + arch->sync = 0; +} + #endif diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index 263e1d08f216..2934e170b0fe 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -8,6 +8,7 @@ #include <linux/personality.h> #include <linux/ptrace.h> #include <linux/kernel.h> +#include <linux/syscalls.h> #include <asm/unistd.h> #include <linux/uaccess.h> #include <asm/ucontext.h> @@ -15,147 +16,26 @@ #include <registers.h> #include <skas.h> -#ifdef CONFIG_X86_32 - -/* - * FPU tag word conversions. - */ - -static inline unsigned short twd_i387_to_fxsr(unsigned short twd) -{ - unsigned int tmp; /* to avoid 16 bit prefixes in the code */ - - /* Transform each pair of bits into 01 (valid) or 00 (empty) */ - tmp = ~twd; - tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */ - /* and move the valid bits to the lower byte. */ - tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */ - tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */ - tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */ - return tmp; -} - -static inline unsigned long twd_fxsr_to_i387(struct user_fxsr_struct *fxsave) -{ - struct _fpxreg *st = NULL; - unsigned long twd = (unsigned long) fxsave->twd; - unsigned long tag; - unsigned long ret = 0xffff0000; - int i; - -#define FPREG_ADDR(f, n) ((char *)&(f)->st_space + (n) * 16) - - for (i = 0; i < 8; i++) { - if (twd & 0x1) { - st = (struct _fpxreg *) FPREG_ADDR(fxsave, i); - - switch (st->exponent & 0x7fff) { - case 0x7fff: - tag = 2; /* Special */ - break; - case 0x0000: - if ( !st->significand[0] && - !st->significand[1] && - !st->significand[2] && - !st->significand[3] ) { - tag = 1; /* Zero */ - } else { - tag = 2; /* Special */ - } - break; - default: - if (st->significand[3] & 0x8000) { - tag = 0; /* Valid */ - } else { - tag = 2; /* Special */ - } - break; - } - } else { - tag = 3; /* Empty */ - } - ret |= (tag << (2 * i)); - twd = twd >> 1; - } - return ret; -} - -static int convert_fxsr_to_user(struct _fpstate __user *buf, - struct user_fxsr_struct *fxsave) -{ - unsigned long env[7]; - struct _fpreg __user *to; - struct _fpxreg *from; - int i; - - env[0] = (unsigned long)fxsave->cwd | 0xffff0000ul; - env[1] = (unsigned long)fxsave->swd | 0xffff0000ul; - env[2] = twd_fxsr_to_i387(fxsave); - env[3] = fxsave->fip; - env[4] = fxsave->fcs | ((unsigned long)fxsave->fop << 16); - env[5] = fxsave->foo; - env[6] = fxsave->fos; - - if (__copy_to_user(buf, env, 7 * sizeof(unsigned long))) - return 1; - - to = &buf->_st[0]; - from = (struct _fpxreg *) &fxsave->st_space[0]; - for (i = 0; i < 8; i++, to++, from++) { - unsigned long __user *t = (unsigned long __user *)to; - unsigned long *f = (unsigned long *)from; - - if (__put_user(*f, t) || - __put_user(*(f + 1), t + 1) || - __put_user(from->exponent, &to->exponent)) - return 1; - } - return 0; -} - -static int convert_fxsr_from_user(struct user_fxsr_struct *fxsave, - struct _fpstate __user *buf) -{ - unsigned long env[7]; - struct _fpxreg *to; - struct _fpreg __user *from; - int i; - - if (copy_from_user( env, buf, 7 * sizeof(long))) - return 1; - - fxsave->cwd = (unsigned short)(env[0] & 0xffff); - fxsave->swd = (unsigned short)(env[1] & 0xffff); - fxsave->twd = twd_i387_to_fxsr((unsigned short)(env[2] & 0xffff)); - fxsave->fip = env[3]; - fxsave->fop = (unsigned short)((env[4] & 0xffff0000ul) >> 16); - fxsave->fcs = (env[4] & 0xffff); - fxsave->foo = env[5]; - fxsave->fos = env[6]; - - to = (struct _fpxreg *) &fxsave->st_space[0]; - from = &buf->_st[0]; - for (i = 0; i < 8; i++, to++, from++) { - unsigned long *t = (unsigned long *)to; - unsigned long __user *f = (unsigned long __user *)from; - - if (__get_user(*t, f) || - __get_user(*(t + 1), f + 1) || - __get_user(to->exponent, &from->exponent)) - return 1; - } - return 0; -} - -extern int have_fpx_regs; +#include <linux/regset.h> +#include <asm/sigframe.h> +#ifdef CONFIG_X86_32 +struct _xstate_64 { + struct _fpstate_64 fpstate; + struct _header xstate_hdr; + struct _ymmh_state ymmh; + /* New processor state extensions go here: */ +}; +#else +#define _xstate_64 _xstate #endif static int copy_sc_from_user(struct pt_regs *regs, struct sigcontext __user *from) { + struct _xstate_64 __user *from_fp64; struct sigcontext sc; - int err, pid; + int err; /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; @@ -201,36 +81,28 @@ static int copy_sc_from_user(struct pt_regs *regs, #undef GETREG - pid = userspace_pid[current_thread_info()->cpu]; #ifdef CONFIG_X86_32 - if (have_fpx_regs) { - struct user_fxsr_struct fpx; + from_fp64 = ((void __user *)sc.fpstate) + + offsetof(struct _fpstate_32, _fxsr_env); +#else + from_fp64 = (void __user *)sc.fpstate; +#endif - err = copy_from_user(&fpx, - &((struct _fpstate __user *)sc.fpstate)->_fxsr_env[0], - sizeof(struct user_fxsr_struct)); - if (err) - return 1; + err = copy_from_user(regs->regs.fp, from_fp64, host_fp_size); + if (err) + return 1; - err = convert_fxsr_from_user(&fpx, (void *)sc.fpstate); - if (err) - return 1; - - err = restore_fpx_registers(pid, (unsigned long *) &fpx); - if (err < 0) { - printk(KERN_ERR "copy_sc_from_user - " - "restore_fpx_registers failed, errno = %d\n", - -err); - return 1; - } - } else +#ifdef CONFIG_X86_32 + /* Data is duplicated and this copy is the important one */ + err = copy_regset_from_user(current, + task_user_regset_view(current), + REGSET_FP_LEGACY, 0, + sizeof(struct user_i387_struct), + (void __user *)sc.fpstate); + if (err < 0) + return err; #endif - { - err = copy_from_user(regs->regs.fp, (void *)sc.fpstate, - sizeof(struct _xstate)); - if (err) - return 1; - } + return 0; } @@ -238,9 +110,10 @@ static int copy_sc_to_user(struct sigcontext __user *to, struct _xstate __user *to_fp, struct pt_regs *regs, unsigned long mask) { + struct _xstate_64 __user *to_fp64; struct sigcontext sc; struct faultinfo * fi = ¤t->thread.arch.faultinfo; - int err, pid; + int err; memset(&sc, 0, sizeof(struct sigcontext)); #define PUTREG(regno, regname) sc.regname = regs->regs.gp[HOST_##regno] @@ -288,37 +161,52 @@ static int copy_sc_to_user(struct sigcontext __user *to, if (err) return 1; - pid = userspace_pid[current_thread_info()->cpu]; - #ifdef CONFIG_X86_32 - if (have_fpx_regs) { - struct user_fxsr_struct fpx; + err = copy_regset_to_user(current, + task_user_regset_view(current), + REGSET_FP_LEGACY, 0, + sizeof(struct _fpstate_32), to_fp); + if (err < 0) + return err; - err = save_fpx_registers(pid, (unsigned long *) &fpx); - if (err < 0){ - printk(KERN_ERR "copy_sc_to_user - save_fpx_registers " - "failed, errno = %d\n", err); - return 1; - } + __put_user(X86_FXSR_MAGIC, &to_fp->fpstate.magic); - err = convert_fxsr_to_user(&to_fp->fpstate, &fpx); - if (err) - return 1; + BUILD_BUG_ON(offsetof(struct _xstate, xstate_hdr) != + offsetof(struct _xstate_64, xstate_hdr) + + offsetof(struct _fpstate_32, _fxsr_env)); + to_fp64 = (void __user *)to_fp + + offsetof(struct _fpstate_32, _fxsr_env); +#else + to_fp64 = to_fp; +#endif /* CONFIG_X86_32 */ - err |= __put_user(fpx.swd, &to_fp->fpstate.status); - err |= __put_user(X86_FXSR_MAGIC, &to_fp->fpstate.magic); - if (err) - return 1; + if (copy_to_user(to_fp64, regs->regs.fp, host_fp_size)) + return 1; + + /* + * Put magic/size values for userspace. We do not bother to verify them + * later on, however, userspace needs them should it try to read the + * XSTATE data. And ptrace does not fill in these parts. + * + * Skip this if we do not have an XSTATE frame. + */ + if (host_fp_size <= sizeof(to_fp64->fpstate)) + return 0; - if (copy_to_user(&to_fp->fpstate._fxsr_env[0], &fpx, - sizeof(struct user_fxsr_struct))) - return 1; - } else + BUILD_BUG_ON(sizeof(int) != FP_XSTATE_MAGIC2_SIZE); +#ifdef CONFIG_X86_32 + __put_user(offsetof(struct _fpstate_32, _fxsr_env) + + host_fp_size + FP_XSTATE_MAGIC2_SIZE, + &to_fp64->fpstate.sw_reserved.extended_size); +#else + __put_user(host_fp_size + FP_XSTATE_MAGIC2_SIZE, + &to_fp64->fpstate.sw_reserved.extended_size); #endif - { - if (copy_to_user(to_fp, regs->regs.fp, sizeof(struct _xstate))) - return 1; - } + __put_user(host_fp_size, &to_fp64->fpstate.sw_reserved.xstate_size); + + __put_user(FP_XSTATE_MAGIC1, &to_fp64->fpstate.sw_reserved.magic1); + __put_user(FP_XSTATE_MAGIC2, + (int __user *)((void __user *)to_fp64 + host_fp_size)); return 0; } @@ -336,34 +224,15 @@ static int copy_ucontext_to_user(struct ucontext __user *uc, return err; } -struct sigframe -{ - char __user *pretcode; - int sig; - struct sigcontext sc; - struct _xstate fpstate; - unsigned long extramask[_NSIG_WORDS-1]; - char retcode[8]; -}; - -struct rt_sigframe -{ - char __user *pretcode; - int sig; - struct siginfo __user *pinfo; - void __user *puc; - struct siginfo info; - struct ucontext uc; - struct _xstate fpstate; - char retcode[8]; -}; - int setup_signal_stack_sc(unsigned long stack_top, struct ksignal *ksig, struct pt_regs *regs, sigset_t *mask) { + size_t math_size = offsetof(struct _fpstate_32, _fxsr_env) + + host_fp_size + FP_XSTATE_MAGIC2_SIZE; struct sigframe __user *frame; void __user *restorer; int err = 0, sig = ksig->sig; + unsigned long fp_to; /* This is the same calculation as i386 - ((sp + 4) & 15) == 0 */ stack_top = ((stack_top + 4) & -16UL) - 4; @@ -371,13 +240,21 @@ int setup_signal_stack_sc(unsigned long stack_top, struct ksignal *ksig, if (!access_ok(frame, sizeof(*frame))) return 1; + /* Add required space for math frame */ + frame = (struct sigframe __user *)((unsigned long)frame - math_size); + restorer = frame->retcode; if (ksig->ka.sa.sa_flags & SA_RESTORER) restorer = ksig->ka.sa.sa_restorer; - err |= __put_user(restorer, &frame->pretcode); + err |= __put_user(restorer, (void __user * __user *)&frame->pretcode); err |= __put_user(sig, &frame->sig); - err |= copy_sc_to_user(&frame->sc, &frame->fpstate, regs, mask->sig[0]); + + fp_to = (unsigned long)frame + sizeof(*frame); + + err |= copy_sc_to_user(&frame->sc, + (struct _xstate __user *)fp_to, + regs, mask->sig[0]); if (_NSIG_WORDS > 1) err |= __copy_to_user(&frame->extramask, &mask->sig[1], sizeof(frame->extramask)); @@ -407,26 +284,35 @@ int setup_signal_stack_sc(unsigned long stack_top, struct ksignal *ksig, int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, struct pt_regs *regs, sigset_t *mask) { + size_t math_size = offsetof(struct _fpstate_32, _fxsr_env) + + host_fp_size + FP_XSTATE_MAGIC2_SIZE; struct rt_sigframe __user *frame; void __user *restorer; int err = 0, sig = ksig->sig; + unsigned long fp_to; stack_top &= -8UL; frame = (struct rt_sigframe __user *) stack_top - 1; if (!access_ok(frame, sizeof(*frame))) return 1; + /* Add required space for math frame */ + frame = (struct rt_sigframe __user *)((unsigned long)frame - math_size); + restorer = frame->retcode; if (ksig->ka.sa.sa_flags & SA_RESTORER) restorer = ksig->ka.sa.sa_restorer; - err |= __put_user(restorer, &frame->pretcode); + err |= __put_user(restorer, (void __user * __user *)&frame->pretcode); err |= __put_user(sig, &frame->sig); - err |= __put_user(&frame->info, &frame->pinfo); - err |= __put_user(&frame->uc, &frame->puc); + err |= __put_user(&frame->info, (void __user * __user *)&frame->pinfo); + err |= __put_user(&frame->uc, (void __user * __user *)&frame->puc); err |= copy_siginfo_to_user(&frame->info, &ksig->info); - err |= copy_ucontext_to_user(&frame->uc, &frame->fpstate, mask, - PT_REGS_SP(regs)); + + fp_to = (unsigned long)frame + sizeof(*frame); + + err |= copy_ucontext_to_user(&frame->uc, (struct _xstate __user *)fp_to, + mask, PT_REGS_SP(regs)); /* * This is movl $,%eax ; int $0x80 @@ -450,7 +336,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, return 0; } -long sys_sigreturn(void) +SYSCALL_DEFINE0(sigreturn) { unsigned long sp = PT_REGS_SP(¤t->thread.regs); struct sigframe __user *frame = (struct sigframe __user *)(sp - 8); @@ -478,27 +364,26 @@ long sys_sigreturn(void) #else -struct rt_sigframe -{ - char __user *pretcode; - struct ucontext uc; - struct siginfo info; - struct _xstate fpstate; -}; - int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, struct pt_regs *regs, sigset_t *set) { + unsigned long math_size = host_fp_size + FP_XSTATE_MAGIC2_SIZE; struct rt_sigframe __user *frame; int err = 0, sig = ksig->sig; unsigned long fp_to; - frame = (struct rt_sigframe __user *) - round_down(stack_top - sizeof(struct rt_sigframe), 16); + frame = (void __user *)stack_top - sizeof(struct rt_sigframe); + + /* Add required space for math frame */ + frame = (void __user *)((unsigned long)frame - math_size); + + /* ABI requires 16 byte boundary alignment */ + frame = (void __user *)round_down((unsigned long)frame, 16); + /* Subtract 128 for a red zone and 8 for proper alignment */ frame = (struct rt_sigframe __user *) ((unsigned long) frame - 128 - 8); - if (!access_ok(frame, sizeof(*frame))) + if (!access_ok(frame, sizeof(*frame) + math_size)) goto out; if (ksig->ka.sa.sa_flags & SA_SIGINFO) { @@ -509,12 +394,14 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, /* Create the ucontext. */ err |= __put_user(0, &frame->uc.uc_flags); - err |= __put_user(0, &frame->uc.uc_link); + err |= __put_user(NULL, &frame->uc.uc_link); err |= __save_altstack(&frame->uc.uc_stack, PT_REGS_SP(regs)); - err |= copy_sc_to_user(&frame->uc.uc_mcontext, &frame->fpstate, regs, - set->sig[0]); - fp_to = (unsigned long)&frame->fpstate; + fp_to = (unsigned long)frame + sizeof(*frame); + + err |= copy_sc_to_user(&frame->uc.uc_mcontext, + (struct _xstate __user *)fp_to, + regs, set->sig[0]); err |= __put_user(fp_to, &frame->uc.uc_mcontext.fpstate); if (sizeof(*set) == 16) { @@ -531,7 +418,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, */ /* x86-64 should always use SA_RESTORER. */ if (ksig->ka.sa.sa_flags & SA_RESTORER) - err |= __put_user((void *)ksig->ka.sa.sa_restorer, + err |= __put_user((void __user *)ksig->ka.sa.sa_restorer, &frame->pretcode); else /* could use a vstub here */ @@ -557,7 +444,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, } #endif -long sys_rt_sigreturn(void) +SYSCALL_DEFINE0(rt_sigreturn) { unsigned long sp = PT_REGS_SP(¤t->thread.regs); struct rt_sigframe __user *frame = diff --git a/arch/x86/um/stub_32.S b/arch/x86/um/stub_32.S deleted file mode 100644 index 8291899e6aaf..000000000000 --- a/arch/x86/um/stub_32.S +++ /dev/null @@ -1,56 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <as-layout.h> - -.section .__syscall_stub, "ax" - - .globl batch_syscall_stub -batch_syscall_stub: - /* %esp comes in as "top of page" */ - mov %esp, %ecx - /* %esp has pointer to first operation */ - add $8, %esp -again: - /* load length of additional data */ - mov 0x0(%esp), %eax - - /* if(length == 0) : end of list */ - /* write possible 0 to header */ - mov %eax, 0x4(%ecx) - cmpl $0, %eax - jz done - - /* save current pointer */ - mov %esp, 0x4(%ecx) - - /* skip additional data */ - add %eax, %esp - - /* load syscall-# */ - pop %eax - - /* load syscall params */ - pop %ebx - pop %ecx - pop %edx - pop %esi - pop %edi - pop %ebp - - /* execute syscall */ - int $0x80 - - /* restore top of page pointer in %ecx */ - mov %esp, %ecx - andl $(~UM_KERN_PAGE_SIZE) + 1, %ecx - - /* check return value */ - pop %ebx - cmp %ebx, %eax - je again - -done: - /* save return value */ - mov %eax, (%ecx) - - /* stop */ - int3 diff --git a/arch/x86/um/stub_64.S b/arch/x86/um/stub_64.S deleted file mode 100644 index f3404640197a..000000000000 --- a/arch/x86/um/stub_64.S +++ /dev/null @@ -1,50 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <as-layout.h> - -.section .__syscall_stub, "ax" - .globl batch_syscall_stub -batch_syscall_stub: - /* %rsp has the pointer to first operation */ - mov %rsp, %rbx - add $0x10, %rsp -again: - /* load length of additional data */ - mov 0x0(%rsp), %rax - - /* if(length == 0) : end of list */ - /* write possible 0 to header */ - mov %rax, 8(%rbx) - cmp $0, %rax - jz done - - /* save current pointer */ - mov %rsp, 8(%rbx) - - /* skip additional data */ - add %rax, %rsp - - /* load syscall-# */ - pop %rax - - /* load syscall params */ - pop %rdi - pop %rsi - pop %rdx - pop %r10 - pop %r8 - pop %r9 - - /* execute syscall */ - syscall - - /* check return value */ - pop %rcx - cmp %rcx, %rax - je again - -done: - /* save return value */ - mov %rax, (%rbx) - - /* stop */ - int3 diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 89df5d89d664..51655133eee3 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -9,6 +9,10 @@ #include <linux/cache.h> #include <asm/syscall.h> +extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, + unsigned long, unsigned long, + unsigned long, unsigned long); + /* * Below you can see, in terms of #define's, the differences between the x86-64 * and the UML syscall table. @@ -22,15 +26,13 @@ #define sys_vm86 sys_ni_syscall #define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) +#define __SYSCALL_NORETURN __SYSCALL #define __SYSCALL(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #include <asm/syscalls_32.h> +#undef __SYSCALL -#undef __SYSCALL #define __SYSCALL(nr, sym) sym, - -extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); - const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { #include <asm/syscalls_32.h> }; diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index b0b4cfd2308c..943d414f2109 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -9,6 +9,10 @@ #include <linux/cache.h> #include <asm/syscall.h> +extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, + unsigned long, unsigned long, + unsigned long, unsigned long); + /* * Below you can see, in terms of #define's, the differences between the x86-64 * and the UML syscall table. @@ -18,14 +22,13 @@ #define sys_iopl sys_ni_syscall #define sys_ioperm sys_ni_syscall +#define __SYSCALL_NORETURN __SYSCALL + #define __SYSCALL(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #include <asm/syscalls_64.h> +#undef __SYSCALL -#undef __SYSCALL #define __SYSCALL(nr, sym) sym, - -extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); - const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { #include <asm/syscalls_64.h> }; diff --git a/arch/x86/um/sysrq_32.c b/arch/x86/um/sysrq_32.c index f2383484840d..a1ee415c008d 100644 --- a/arch/x86/um/sysrq_32.c +++ b/arch/x86/um/sysrq_32.c @@ -9,7 +9,6 @@ #include <linux/sched/debug.h> #include <linux/kallsyms.h> #include <asm/ptrace.h> -#include <asm/sysrq.h> /* This is declared by <linux/sched.h> */ void show_regs(struct pt_regs *regs) diff --git a/arch/x86/um/sysrq_64.c b/arch/x86/um/sysrq_64.c index 0bf6de40abff..340d8a243c8a 100644 --- a/arch/x86/um/sysrq_64.c +++ b/arch/x86/um/sysrq_64.c @@ -12,7 +12,6 @@ #include <linux/utsname.h> #include <asm/current.h> #include <asm/ptrace.h> -#include <asm/sysrq.h> void show_regs(struct pt_regs *regs) { diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c index 66162eafd8e8..cb3f17627d16 100644 --- a/arch/x86/um/tls_32.c +++ b/arch/x86/um/tls_32.c @@ -11,6 +11,8 @@ #include <os.h> #include <skas.h> #include <sysdep/tls.h> +#include <asm/desc.h> +#include <stub-data.h> /* * If needed we can detect when it's uninitialized. @@ -20,33 +22,28 @@ static int host_supports_tls = -1; int host_gdt_entry_tls_min; -int do_set_thread_area(struct user_desc *info) +static int do_set_thread_area(struct task_struct* task, struct user_desc *info) { int ret; - u32 cpu; - cpu = get_cpu(); - ret = os_set_thread_area(info, userspace_pid[cpu]); - put_cpu(); + if (info->entry_number < host_gdt_entry_tls_min || + info->entry_number >= host_gdt_entry_tls_min + GDT_ENTRY_TLS_ENTRIES) + return -EINVAL; - if (ret) - printk(KERN_ERR "PTRACE_SET_THREAD_AREA failed, err = %d, " - "index = %d\n", ret, info->entry_number); + if (using_seccomp) { + int idx = info->entry_number - host_gdt_entry_tls_min; + struct stub_data *data = (void *)task->mm->context.id.stack; - return ret; -} + data->arch_data.tls[idx] = *info; + data->arch_data.sync |= BIT(idx); -int do_get_thread_area(struct user_desc *info) -{ - int ret; - u32 cpu; + return 0; + } - cpu = get_cpu(); - ret = os_get_thread_area(info, userspace_pid[cpu]); - put_cpu(); + ret = os_set_thread_area(info, task->mm->context.id.pid); if (ret) - printk(KERN_ERR "PTRACE_GET_THREAD_AREA failed, err = %d, " + printk(KERN_ERR "PTRACE_SET_THREAD_AREA failed, err = %d, " "index = %d\n", ret, info->entry_number); return ret; @@ -112,7 +109,7 @@ static int load_TLS(int flags, struct task_struct *to) if (!(flags & O_FORCE) && curr->flushed) continue; - ret = do_set_thread_area(&curr->tls); + ret = do_set_thread_area(current, &curr->tls); if (ret) goto out; @@ -231,7 +228,6 @@ out: return ret; } -/* XXX: use do_get_thread_area to read the host value? I'm not at all sure! */ static int get_tls_entry(struct task_struct *task, struct user_desc *info, int idx) { @@ -291,7 +287,7 @@ SYSCALL_DEFINE1(set_thread_area, struct user_desc __user *, user_desc) return -EFAULT; } - ret = do_set_thread_area(&info); + ret = do_set_thread_area(current, &info); if (ret) return ret; return set_tls_entry(current, &info, idx, 1); diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index e54a9814ccf1..d6e1cd9956bf 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -14,12 +14,12 @@ COMMENT(#val " / sizeof(unsigned long)"); \ DEFINE(sym, val / sizeof(unsigned long)) +/* workaround for a warning with -Wmissing-prototypes */ +void foo(void); + void foo(void) { #ifdef __i386__ - DEFINE_LONGS(HOST_FP_SIZE, sizeof(struct user_fpregs_struct)); - DEFINE_LONGS(HOST_FPX_SIZE, sizeof(struct user_fpxregs_struct)); - DEFINE(HOST_IP, EIP); DEFINE(HOST_SP, UESP); DEFINE(HOST_EFLAGS, EFL); @@ -38,11 +38,6 @@ void foo(void) DEFINE(HOST_GS, GS); DEFINE(HOST_ORIG_AX, ORIG_EAX); #else -#ifdef FP_XSTATE_MAGIC1 - DEFINE_LONGS(HOST_FP_SIZE, 2696); -#else - DEFINE(HOST_FP_SIZE, sizeof(struct _fpstate) / sizeof(unsigned long)); -#endif DEFINE_LONGS(HOST_BX, RBX); DEFINE_LONGS(HOST_CX, RCX); DEFINE_LONGS(HOST_DI, RDI); diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index b86d634730b2..7478d11dacb7 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -3,12 +3,6 @@ # Building vDSO images for x86. # -# do not instrument on vdso because KASAN is not compatible with user mode -KASAN_SANITIZE := n - -# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. -KCOV_INSTRUMENT := n - VDSO64-y := y vdso-install-$(VDSO64-y) += vdso.so @@ -62,8 +56,6 @@ CFLAGS_REMOVE_um_vdso.o = -pg -fprofile-arcs -ftest-coverage quiet_cmd_vdso = VDSO $@ cmd_vdso = $(CC) -nostdlib -o $@ \ $(CC_FLAGS_LTO) $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ - -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ - sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' + -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) -VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv -z noexecstack -GCOV_PROFILE := n +VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv -z noexecstack -Wl,--no-undefined diff --git a/arch/x86/um/vdso/checkundef.sh b/arch/x86/um/vdso/checkundef.sh deleted file mode 100644 index 8e3ea6bb956f..000000000000 --- a/arch/x86/um/vdso/checkundef.sh +++ /dev/null @@ -1,11 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -nm="$1" -file="$2" -$nm "$file" | grep '^ *U' > /dev/null 2>&1 -if [ $? -eq 1 ]; then - exit 0 -else - echo "$file: undefined symbols found" >&2 - exit 1 -fi diff --git a/arch/x86/um/vdso/um_vdso.c b/arch/x86/um/vdso/um_vdso.c index ff0f3b4b6c45..cbae2584124f 100644 --- a/arch/x86/um/vdso/um_vdso.c +++ b/arch/x86/um/vdso/um_vdso.c @@ -13,6 +13,12 @@ #include <linux/getcpu.h> #include <asm/unistd.h> +/* workaround for -Wmissing-prototypes warnings */ +int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts); +int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz); +__kernel_old_time_t __vdso_time(__kernel_old_time_t *t); +long __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused); + int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts) { long ret; @@ -54,7 +60,7 @@ __kernel_old_time_t __vdso_time(__kernel_old_time_t *t) __kernel_old_time_t time(__kernel_old_time_t *t) __attribute__((weak, alias("__vdso_time"))); long -__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) +__vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused) { /* * UML does not support SMP, we can cheat here. :) @@ -68,5 +74,5 @@ __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) return 0; } -long getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache) +long getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *tcache) __attribute__((weak, alias("__vdso_getcpu"))); diff --git a/arch/x86/um/vdso/vma.c b/arch/x86/um/vdso/vma.c index 76d9f6ce7a3d..dc8dfb2abd80 100644 --- a/arch/x86/um/vdso/vma.c +++ b/arch/x86/um/vdso/vma.c @@ -12,33 +12,22 @@ static unsigned int __read_mostly vdso_enabled = 1; unsigned long um_vdso_addr; +static struct page *um_vdso; extern unsigned long task_size; extern char vdso_start[], vdso_end[]; -static struct page **vdsop; - static int __init init_vdso(void) { - struct page *um_vdso; - BUG_ON(vdso_end - vdso_start > PAGE_SIZE); um_vdso_addr = task_size - PAGE_SIZE; - vdsop = kmalloc(sizeof(struct page *), GFP_KERNEL); - if (!vdsop) - goto oom; - um_vdso = alloc_page(GFP_KERNEL); - if (!um_vdso) { - kfree(vdsop); - + if (!um_vdso) goto oom; - } copy_page(page_address(um_vdso), vdso_start); - *vdsop = um_vdso; return 0; @@ -52,8 +41,12 @@ subsys_initcall(init_vdso); int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { - int err; + struct vm_area_struct *vma; struct mm_struct *mm = current->mm; + static struct vm_special_mapping vdso_mapping = { + .name = "[vdso]", + .pages = &um_vdso, + }; if (!vdso_enabled) return 0; @@ -61,12 +54,12 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (mmap_write_lock_killable(mm)) return -EINTR; - err = install_special_mapping(mm, um_vdso_addr, PAGE_SIZE, + vma = _install_special_mapping(mm, um_vdso_addr, PAGE_SIZE, VM_READ|VM_EXEC| VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, - vdsop); + &vdso_mapping); mmap_write_unlock(mm); - return err; + return IS_ERR(vma) ? PTR_ERR(vma) : 0; } |