From 73159fdcdb9be3eda61b846864352c29371baeb6 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 5 May 2014 12:19:31 -0700 Subject: x86, mm: Ensure correct alignment of the fixmap The early_ioremap code requires that its buffers not span a PMD boundary. The logic for ensuring that only works if the fixmap is aligned, so assert that it's aligned correctly. To make this work reliably, reserve_top_address needs to be adjusted. Signed-off-by: Andy Lutomirski Link: http://lkml.kernel.org/r/e59a5f4362661f75dd4841fa74e1f2448045e245.1399317206.git.luto@amacapital.net Signed-off-by: H. Peter Anvin --- arch/x86/mm/ioremap.c | 6 ++++++ arch/x86/mm/pgtable.c | 6 +++--- 2 files changed, 9 insertions(+), 3 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 597ac155c91c..6ef98c55a899 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -355,6 +355,12 @@ void __init early_ioremap_init(void) { pmd_t *pmd; +#ifdef CONFIG_X86_64 + BUILD_BUG_ON((fix_to_virt(0) + PAGE_SIZE) & ((1 << PMD_SHIFT) - 1)); +#else + WARN_ON((fix_to_virt(0) + PAGE_SIZE) & ((1 << PMD_SHIFT) - 1)); +#endif + early_ioremap_setup(); pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index c96314abd144..5f8bdda1d1ba 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -449,9 +449,9 @@ void __init reserve_top_address(unsigned long reserve) { #ifdef CONFIG_X86_32 BUG_ON(fixmaps_set > 0); - printk(KERN_INFO "Reserving virtual address space above 0x%08x\n", - (int)-reserve); - __FIXADDR_TOP = -reserve - PAGE_SIZE; + __FIXADDR_TOP = round_down(-reserve, 1 << PMD_SHIFT) - PAGE_SIZE; + printk(KERN_INFO "Reserving virtual address space above 0x%08lx (rounded to 0x%08lx)\n", + -reserve, __FIXADDR_TOP + PAGE_SIZE); #endif } -- cgit v1.2.3 From 6f121e548f83674ab4920a4e60afb58d4f61b829 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 5 May 2014 12:19:34 -0700 Subject: x86, vdso: Reimplement vdso.so preparation in build-time C Currently, vdso.so files are prepared and analyzed by a combination of objcopy, nm, some linker script tricks, and some simple ELF parsers in the kernel. Replace all of that with plain C code that runs at build time. All five vdso images now generate .c files that are compiled and linked in to the kernel image. This should cause only one userspace-visible change: the loaded vDSO images are stripped more heavily than they used to be. Everything outside the loadable segment is dropped. In particular, this causes the section table and section name strings to be missing. This should be fine: real dynamic loaders don't load or inspect these tables anyway. The result is roughly equivalent to eu-strip's --strip-sections option. The purpose of this change is to enable the vvar and hpet mappings to be moved to the page following the vDSO load segment. Currently, it is possible for the section table to extend into the page after the load segment, so, if we map it, it risks overlapping the vvar or hpet page. This happens whenever the load segment is just under a multiple of PAGE_SIZE. The only real subtlety here is that the old code had a C file with inline assembler that did 'call VDSO32_vsyscall' and a linker script that defined 'VDSO32_vsyscall = __kernel_vsyscall'. This most likely worked by accident: the linker script entry defines a symbol associated with an address as opposed to an alias for the real dynamic symbol __kernel_vsyscall. That caused ld to relocate the reference at link time instead of leaving an interposable dynamic relocation. Since the VDSO32_vsyscall hack is no longer needed, I now use 'call __kernel_vsyscall', and I added -Bsymbolic to make it work. vdso2c will generate an error and abort the build if the resulting image contains any dynamic relocations, so we won't silently generate bad vdso images. (Dynamic relocations are a problem because nothing will even attempt to relocate the vdso.) Signed-off-by: Andy Lutomirski Link: http://lkml.kernel.org/r/2c4fcf45524162a34d87fdda1eb046b2a5cecee7.1399317206.git.luto@amacapital.net Signed-off-by: H. Peter Anvin --- arch/x86/mm/init_64.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index f35c66c5959a..563849600d3e 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1223,7 +1223,8 @@ int in_gate_area_no_mm(unsigned long addr) const char *arch_vma_name(struct vm_area_struct *vma) { - if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso) + if (vma->vm_mm && vma->vm_start == + (long __force)vma->vm_mm->context.vdso) return "[vdso]"; if (vma == &gate_vma) return "[vsyscall]"; -- cgit v1.2.3 From f40c330091c7aa9956ab66f97a3abc8a68b67240 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 5 May 2014 12:19:36 -0700 Subject: x86, vdso: Move the vvar and hpet mappings next to the 64-bit vDSO This makes the 64-bit and x32 vdsos use the same mechanism as the 32-bit vdso. Most of the churn is deleting all the old fixmap code. Signed-off-by: Andy Lutomirski Link: http://lkml.kernel.org/r/8af87023f57f6bb96ec8d17fce3f88018195b49b.1399317206.git.luto@amacapital.net Signed-off-by: H. Peter Anvin --- arch/x86/mm/fault.c | 5 +++-- arch/x86/mm/init_64.c | 10 +++++----- 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 8e5722992677..858b47b5221b 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -18,7 +18,8 @@ #include /* dotraplinkage, ... */ #include /* pgd_*(), ... */ #include /* kmemcheck_*(), ... */ -#include /* VSYSCALL_START */ +#include /* VSYSCALL_ADDR */ +#include /* emulate_vsyscall */ #define CREATE_TRACE_POINTS #include @@ -771,7 +772,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, * emulation. */ if (unlikely((error_code & PF_INSTR) && - ((address & ~0xfff) == VSYSCALL_START))) { + ((address & ~0xfff) == VSYSCALL_ADDR))) { if (emulate_vsyscall(regs, address)) return; } diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 563849600d3e..6f881842116c 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1055,8 +1055,8 @@ void __init mem_init(void) after_bootmem = 1; /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START, - VSYSCALL_END - VSYSCALL_START, KCORE_OTHER); + kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, + PAGE_SIZE, KCORE_OTHER); mem_init_print_info(NULL); } @@ -1186,8 +1186,8 @@ int kern_addr_valid(unsigned long addr) * not need special handling anymore: */ static struct vm_area_struct gate_vma = { - .vm_start = VSYSCALL_START, - .vm_end = VSYSCALL_START + (VSYSCALL_MAPPED_PAGES * PAGE_SIZE), + .vm_start = VSYSCALL_ADDR, + .vm_end = VSYSCALL_ADDR + PAGE_SIZE, .vm_page_prot = PAGE_READONLY_EXEC, .vm_flags = VM_READ | VM_EXEC }; @@ -1218,7 +1218,7 @@ int in_gate_area(struct mm_struct *mm, unsigned long addr) */ int in_gate_area_no_mm(unsigned long addr) { - return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END); + return (addr & PAGE_MASK) == VSYSCALL_ADDR; } const char *arch_vma_name(struct vm_area_struct *vma) -- cgit v1.2.3 From a62c34bd2a8a3f159945becd57401e478818d51c Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 19 May 2014 15:58:33 -0700 Subject: x86, mm: Improve _install_special_mapping and fix x86 vdso naming Using arch_vma_name to give special mappings a name is awkward. x86 currently implements it by comparing the start address of the vma to the expected address of the vdso. This requires tracking the start address of special mappings and is probably buggy if a special vma is split or moved. Improve _install_special_mapping to just name the vma directly. Use it to give the x86 vvar area a name, which should make CRIU's life easier. As a side effect, the vvar area will show up in core dumps. This could be considered weird and is fixable. [hpa: I say we accept this as-is but be prepared to deal with knocking out the vvars from core dumps if this becomes a problem.] Cc: Cyrill Gorcunov Cc: Pavel Emelyanov Signed-off-by: Andy Lutomirski Link: http://lkml.kernel.org/r/276b39b6b645fb11e345457b503f17b83c2c6fd0.1400538962.git.luto@amacapital.net Signed-off-by: H. Peter Anvin --- arch/x86/mm/init_64.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 6f881842116c..9deb59b0baea 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1223,9 +1223,6 @@ int in_gate_area_no_mm(unsigned long addr) const char *arch_vma_name(struct vm_area_struct *vma) { - if (vma->vm_mm && vma->vm_start == - (long __force)vma->vm_mm->context.vdso) - return "[vdso]"; if (vma == &gate_vma) return "[vsyscall]"; return NULL; -- cgit v1.2.3 From ac49b9a9f26b6c42585f87857722085ef4b19c13 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 19 May 2014 15:58:34 -0700 Subject: x86, mm: Replace arch_vma_name with vm_ops->name for vsyscalls This removes the last vestiges of arch_vma_name from x86, replacing it with vm_ops->name. Good riddance. Signed-off-by: Andy Lutomirski Link: http://lkml.kernel.org/r/e681cb56096eee5b8b8767093a4f6fb82839f0a4.1400538962.git.luto@amacapital.net Signed-off-by: H. Peter Anvin --- arch/x86/mm/init_64.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 9deb59b0baea..bdcde58ca9ed 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1185,11 +1185,19 @@ int kern_addr_valid(unsigned long addr) * covers the 64bit vsyscall page now. 32bit has a real VMA now and does * not need special handling anymore: */ +static const char *gate_vma_name(struct vm_area_struct *vma) +{ + return "[vsyscall]"; +} +static struct vm_operations_struct gate_vma_ops = { + .name = gate_vma_name, +}; static struct vm_area_struct gate_vma = { .vm_start = VSYSCALL_ADDR, .vm_end = VSYSCALL_ADDR + PAGE_SIZE, .vm_page_prot = PAGE_READONLY_EXEC, - .vm_flags = VM_READ | VM_EXEC + .vm_flags = VM_READ | VM_EXEC, + .vm_ops = &gate_vma_ops, }; struct vm_area_struct *get_gate_vma(struct mm_struct *mm) @@ -1221,13 +1229,6 @@ int in_gate_area_no_mm(unsigned long addr) return (addr & PAGE_MASK) == VSYSCALL_ADDR; } -const char *arch_vma_name(struct vm_area_struct *vma) -{ - if (vma == &gate_vma) - return "[vsyscall]"; - return NULL; -} - #ifdef CONFIG_X86_UV unsigned long memory_block_size_bytes(void) { -- cgit v1.2.3