diff --git a/Documentation/x86/entry_64.txt b/Documentation/x86/entry_64.txt index bc7226ef5055..4a1c5c2dc5a9 100644 --- a/Documentation/x86/entry_64.txt +++ b/Documentation/x86/entry_64.txt @@ -7,9 +7,12 @@ http://lkml.kernel.org/r/<20110529191055.GC9835%40elte.hu> The x86 architecture has quite a few different ways to jump into kernel code. Most of these entry points are registered in arch/x86/kernel/traps.c and implemented in arch/x86/kernel/entry_64.S -and arch/x86/ia32/ia32entry.S. +for 64-bit, arch/x86/kernel/entry_32.S for 32-bit and finally +arch/x86/ia32/ia32entry.S which implements the 32-bit compatibility +syscall entry points and thus provides for 32-bit processes the +ability to execute syscalls when running on 64-bit kernels. -The IDT vector assignments are listed in arch/x86/include/irq_vectors.h. +The IDT vector assignments are listed in arch/x86/include/asm/irq_vectors.h. Some of these entries are: diff --git a/MAINTAINERS b/MAINTAINERS index f273cb58d2e8..9ef141a913cf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10485,6 +10485,13 @@ L: linux-edac@vger.kernel.org S: Maintained F: arch/x86/kernel/cpu/mcheck/* +X86 VDSO +M: Andy Lutomirski +L: linux-kernel@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/vdso +S: Maintained +F: arch/x86/vdso/ + XC2028/3028 TUNER DRIVER M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h index 0bdb0c54d9a1..fe884e18fa6e 100644 --- a/arch/x86/include/asm/dma.h +++ b/arch/x86/include/asm/dma.h @@ -70,7 +70,7 @@ #define MAX_DMA_CHANNELS 8 /* 16MB ISA DMA zone */ -#define MAX_DMA_PFN ((16 * 1024 * 1024) >> PAGE_SHIFT) +#define MAX_DMA_PFN ((16UL * 1024 * 1024) >> PAGE_SHIFT) /* 4GB broken PCI/AGP hardware bus master zone */ #define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT) diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 6f1c3a8a33ab..db257a58571f 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -23,6 +23,15 @@ #define GDT_ENTRY_BOOT_TSS (GDT_ENTRY_BOOT_CS + 2) #define __BOOT_TSS (GDT_ENTRY_BOOT_TSS * 8) +#define SEGMENT_RPL_MASK 0x3 /* + * Bottom two bits of selector give the ring + * privilege level + */ +#define SEGMENT_TI_MASK 0x4 /* Bit 2 is table indicator (LDT/GDT) */ +#define USER_RPL 0x3 /* User mode is privilege level 3 */ +#define SEGMENT_LDT 0x4 /* LDT segment has TI set... */ +#define SEGMENT_GDT 0x0 /* ... GDT has it cleared */ + #ifdef CONFIG_X86_32 /* * The layout of the per-CPU GDT under Linux: @@ -125,16 +134,6 @@ #define PNP_TS1 (GDT_ENTRY_PNPBIOS_TS1 * 8) /* transfer data segment */ #define PNP_TS2 (GDT_ENTRY_PNPBIOS_TS2 * 8) /* another data segment */ -/* Bottom two bits of selector give the ring privilege level */ -#define SEGMENT_RPL_MASK 0x3 -/* Bit 2 is table indicator (LDT/GDT) */ -#define SEGMENT_TI_MASK 0x4 - -/* User mode is privilege level 3 */ -#define USER_RPL 0x3 -/* LDT segment has TI set, GDT has it cleared */ -#define SEGMENT_LDT 0x4 -#define SEGMENT_GDT 0x0 /* * Matching rules for certain types of segments. @@ -192,17 +191,6 @@ #define get_kernel_rpl() 0 #endif -/* User mode is privilege level 3 */ -#define USER_RPL 0x3 -/* LDT segment has TI set, GDT has it cleared */ -#define SEGMENT_LDT 0x4 -#define SEGMENT_GDT 0x0 - -/* Bottom two bits of selector give the ring privilege level */ -#define SEGMENT_RPL_MASK 0x3 -/* Bit 2 is table indicator (LDT/GDT) */ -#define SEGMENT_TI_MASK 0x4 - #define IDT_ENTRIES 256 #define NUM_EXCEPTION_VECTORS 32 /* Bitmask of exception vectors which push an error code on the stack */ diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index d67c4be3e8b1..3b3b9d33ac1d 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -1,3 +1,7 @@ +#ifndef __LINUX_KBUILD_H +# error "Please do not build this file directly, build asm-offsets.c instead" +#endif + #include #include diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 4f9359f36bb7..fdcbb4d27c9f 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -1,3 +1,7 @@ +#ifndef __LINUX_KBUILD_H +# error "Please do not build this file directly, build asm-offsets.c instead" +#endif + #include #define __SYSCALL_64(nr, sym, compat) [nr] = 1, diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 49f886481615..dd2f07ae9d0c 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1114,8 +1114,8 @@ void __init memblock_find_dma_reserve(void) * at first, and assume boot_mem will not take below MAX_DMA_PFN */ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { - start_pfn = min_t(unsigned long, start_pfn, MAX_DMA_PFN); - end_pfn = min_t(unsigned long, end_pfn, MAX_DMA_PFN); + start_pfn = min(start_pfn, MAX_DMA_PFN); + end_pfn = min(end_pfn, MAX_DMA_PFN); nr_pages += end_pfn - start_pfn; } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 3ed4a68d4013..5a2c02913af3 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -283,24 +283,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) fpu = switch_fpu_prepare(prev_p, next_p, cpu); - /* - * Reload esp0, LDT and the page table pointer: - */ + /* Reload esp0 and ss1. */ load_sp0(tss, next); - /* - * Switch DS and ES. - * This won't pick up thread selector changes, but I guess that is ok. - */ - savesegment(es, prev->es); - if (unlikely(next->es | prev->es)) - loadsegment(es, next->es); - - savesegment(ds, prev->ds); - if (unlikely(next->ds | prev->ds)) - loadsegment(ds, next->ds); - - /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). * @@ -309,41 +294,101 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) savesegment(fs, fsindex); savesegment(gs, gsindex); + /* + * Load TLS before restoring any segments so that segment loads + * reference the correct GDT entries. + */ load_TLS(next, cpu); /* - * Leave lazy mode, flushing any hypercalls made here. - * This must be done before restoring TLS segments so - * the GDT and LDT are properly updated, and must be - * done before math_state_restore, so the TS bit is up - * to date. + * Leave lazy mode, flushing any hypercalls made here. This + * must be done after loading TLS entries in the GDT but before + * loading segments that might reference them, and and it must + * be done before math_state_restore, so the TS bit is up to + * date. */ arch_end_context_switch(next_p); + /* Switch DS and ES. + * + * Reading them only returns the selectors, but writing them (if + * nonzero) loads the full descriptor from the GDT or LDT. The + * LDT for next is loaded in switch_mm, and the GDT is loaded + * above. + * + * We therefore need to write new values to the segment + * registers on every context switch unless both the new and old + * values are zero. + * + * Note that we don't need to do anything for CS and SS, as + * those are saved and restored as part of pt_regs. + */ + savesegment(es, prev->es); + if (unlikely(next->es | prev->es)) + loadsegment(es, next->es); + + savesegment(ds, prev->ds); + if (unlikely(next->ds | prev->ds)) + loadsegment(ds, next->ds); + /* * Switch FS and GS. * - * Segment register != 0 always requires a reload. Also - * reload when it has changed. When prev process used 64bit - * base always reload to avoid an information leak. + * These are even more complicated than FS and GS: they have + * 64-bit bases are that controlled by arch_prctl. Those bases + * only differ from the values in the GDT or LDT if the selector + * is 0. + * + * Loading the segment register resets the hidden base part of + * the register to 0 or the value from the GDT / LDT. If the + * next base address zero, writing 0 to the segment register is + * much faster than using wrmsr to explicitly zero the base. + * + * The thread_struct.fs and thread_struct.gs values are 0 + * if the fs and gs bases respectively are not overridden + * from the values implied by fsindex and gsindex. They + * are nonzero, and store the nonzero base addresses, if + * the bases are overridden. + * + * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should + * be impossible. + * + * Therefore we need to reload the segment registers if either + * the old or new selector is nonzero, and we need to override + * the base address if next thread expects it to be overridden. + * + * This code is unnecessarily slow in the case where the old and + * new indexes are zero and the new base is nonzero -- it will + * unnecessarily write 0 to the selector before writing the new + * base address. + * + * Note: This all depends on arch_prctl being the only way that + * user code can override the segment base. Once wrfsbase and + * wrgsbase are enabled, most of this code will need to change. */ if (unlikely(fsindex | next->fsindex | prev->fs)) { loadsegment(fs, next->fsindex); + /* - * Check if the user used a selector != 0; if yes - * clear 64bit base, since overloaded base is always - * mapped to the Null selector + * If user code wrote a nonzero value to FS, then it also + * cleared the overridden base address. + * + * XXX: if user code wrote 0 to FS and cleared the base + * address itself, we won't notice and we'll incorrectly + * restore the prior base address next time we reschdule + * the process. */ if (fsindex) prev->fs = 0; } - /* when next process has a 64bit base use it */ if (next->fs) wrmsrl(MSR_FS_BASE, next->fs); prev->fsindex = fsindex; if (unlikely(gsindex | next->gsindex | prev->gs)) { load_gs_index(next->gsindex); + + /* This works (and fails) the same way as fsindex above. */ if (gsindex) prev->gs = 0; } diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index f7fec09e3e3a..3e551eee87b9 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -27,6 +27,43 @@ static int get_free_idx(void) return -ESRCH; } +static bool tls_desc_okay(const struct user_desc *info) +{ + if (LDT_empty(info)) + return true; + + /* + * espfix is required for 16-bit data segments, but espfix + * only works for LDT segments. + */ + if (!info->seg_32bit) + return false; + + /* Only allow data segments in the TLS array. */ + if (info->contents > 1) + return false; + + /* + * Non-present segments with DPL 3 present an interesting attack + * surface. The kernel should handle such segments correctly, + * but TLS is very difficult to protect in a sandbox, so prevent + * such segments from being created. + * + * If userspace needs to remove a TLS entry, it can still delete + * it outright. + */ + if (info->seg_not_present) + return false; + +#ifdef CONFIG_X86_64 + /* The L bit makes no sense for data. */ + if (info->lm) + return false; +#endif + + return true; +} + static void set_tls_desc(struct task_struct *p, int idx, const struct user_desc *info, int n) { @@ -66,6 +103,9 @@ int do_set_thread_area(struct task_struct *p, int idx, if (copy_from_user(&info, u_info, sizeof(info))) return -EFAULT; + if (!tls_desc_okay(&info)) + return -EINVAL; + if (idx == -1) idx = info.entry_number; @@ -192,6 +232,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, { struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES]; const struct user_desc *info; + int i; if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || (pos % sizeof(struct user_desc)) != 0 || @@ -205,6 +246,10 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, else info = infobuf; + for (i = 0; i < count / sizeof(struct user_desc); i++) + if (!tls_desc_okay(info + i)) + return -EINVAL; + set_tls_desc(target, GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)), info, count / sizeof(struct user_desc)); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 82b41d56bb98..a97ee0801475 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -703,10 +703,10 @@ void __init zone_sizes_init(void) memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); #ifdef CONFIG_ZONE_DMA - max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN; + max_zone_pfns[ZONE_DMA] = min(MAX_DMA_PFN, max_low_pfn); #endif #ifdef CONFIG_ZONE_DMA32 - max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN; + max_zone_pfns[ZONE_DMA32] = min(MAX_DMA32_PFN, max_low_pfn); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM