diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-22 09:59:21 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-22 09:59:21 -0700 |
commit | f56e65dff6ad52395ef45738799b4fb70ff43376 (patch) | |
tree | 230e0ac39888f219a6859fb15ef548fb2bd6511c /arch/x86/include/asm/page_64_types.h | |
parent | 24717cfbbbbfa415d1e3dca0f21c417e5faf8208 (diff) | |
parent | 7b84b665c874f60d84547635341e418f20cbbab2 (diff) |
Merge branch 'work.set_fs' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull initial set_fs() removal from Al Viro:
"Christoph's set_fs base series + fixups"
* 'work.set_fs' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
fs: Allow a NULL pos pointer to __kernel_read
fs: Allow a NULL pos pointer to __kernel_write
powerpc: remove address space overrides using set_fs()
powerpc: use non-set_fs based maccess routines
x86: remove address space overrides using set_fs()
x86: make TASK_SIZE_MAX usable from assembly code
x86: move PAGE_OFFSET, TASK_SIZE & friends to page_{32,64}_types.h
lkdtm: remove set_fs-based tests
test_bitmap: remove user bitmap tests
uaccess: add infrastructure for kernel builds with set_fs()
fs: don't allow splice read/write without explicit ops
fs: don't allow kernel reads and writes without iter ops
sysctl: Convert to iter interfaces
proc: add a read_iter method to proc proc_ops
proc: cleanup the compat vs no compat file ops
proc: remove a level of indentation in proc_get_inode
Diffstat (limited to 'arch/x86/include/asm/page_64_types.h')
-rw-r--r-- | arch/x86/include/asm/page_64_types.h | 38 |
1 files changed, 38 insertions, 0 deletions
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index d0c6c10c18a0..3f49dac03617 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -60,6 +60,44 @@ #endif /* + * User space process size. This is the first address outside the user range. + * There are a few constraints that determine this: + * + * On Intel CPUs, if a SYSCALL instruction is at the highest canonical + * address, then that syscall will enter the kernel with a + * non-canonical return address, and SYSRET will explode dangerously. + * We avoid this particular problem by preventing anything executable + * from being mapped at the maximum canonical address. + * + * On AMD CPUs in the Ryzen family, there's a nasty bug in which the + * CPUs malfunction if they execute code from the highest canonical page. + * They'll speculate right off the end of the canonical space, and + * bad things happen. This is worked around in the same way as the + * Intel problem. + * + * With page table isolation enabled, we map the LDT in ... [stay tuned] + */ +#define TASK_SIZE_MAX ((_AC(1,UL) << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE) + +#define DEFAULT_MAP_WINDOW ((1UL << 47) - PAGE_SIZE) + +/* This decides where the kernel will search for a free chunk of vm + * space during mmap's. + */ +#define IA32_PAGE_OFFSET ((current->personality & ADDR_LIMIT_3GB) ? \ + 0xc0000000 : 0xFFFFe000) + +#define TASK_SIZE_LOW (test_thread_flag(TIF_ADDR32) ? \ + IA32_PAGE_OFFSET : DEFAULT_MAP_WINDOW) +#define TASK_SIZE (test_thread_flag(TIF_ADDR32) ? \ + IA32_PAGE_OFFSET : TASK_SIZE_MAX) +#define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_ADDR32)) ? \ + IA32_PAGE_OFFSET : TASK_SIZE_MAX) + +#define STACK_TOP TASK_SIZE_LOW +#define STACK_TOP_MAX TASK_SIZE_MAX + +/* * Maximum kernel image size is limited to 1 GiB, due to the fixmap living * in the next 1 GiB (see level2_kernel_pgt in arch/x86/kernel/head_64.S). * |