With segmentation, the base address of the segment descriptor is needed to compute a linear address. The segment descriptor used in the address computation depends on either any segment override prefixes in the instruction or the default segment determined by the registers involved in the address computation. Thus, both the instruction as well as the register (specified as the offset from the base of pt_regs) are given as inputs, along with a boolean variable to select between override and default.
The segment selector is determined by get_seg_selector() with the inputs described above. Once the selector is known, the base address is determined. In protected mode, the selector is used to obtain the segment descriptor and then its base address. If in 64-bit user mode, the segment base address is zero except when FS or GS are used. In virtual-8086 mode, the base address is computed as the value of the segment selector shifted 4 positions to the left.
In protected mode, segment limits are enforced. Thus, a function to determine the limit of the segment is added. Segment limits are not enforced in long or virtual-8086. For the latter, addresses are limited to 20 bits; address size will be handled when computing the linear address.
Cc: Dave Hansen dave.hansen@linux.intel.com Cc: Adam Buchbinder adam.buchbinder@gmail.com Cc: Colin Ian King colin.king@canonical.com Cc: Lorenzo Stoakes lstoakes@gmail.com Cc: Qiaowei Ren qiaowei.ren@intel.com Cc: Arnaldo Carvalho de Melo acme@redhat.com Cc: Masami Hiramatsu mhiramat@kernel.org Cc: Adrian Hunter adrian.hunter@intel.com Cc: Kees Cook keescook@chromium.org Cc: Thomas Garnier thgarnie@google.com Cc: Peter Zijlstra peterz@infradead.org Cc: Borislav Petkov bp@suse.de Cc: Dmitry Vyukov dvyukov@google.com Cc: Ravi V. Shankar ravi.v.shankar@intel.com Cc: x86@kernel.org Signed-off-by: Ricardo Neri ricardo.neri-calderon@linux.intel.com --- arch/x86/include/asm/insn-eval.h | 2 + arch/x86/lib/insn-eval.c | 127 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 129 insertions(+)
diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h index 7e8c963..7f3c7fe 100644 --- a/arch/x86/include/asm/insn-eval.h +++ b/arch/x86/include/asm/insn-eval.h @@ -13,5 +13,7 @@
void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs); int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs); +unsigned long insn_get_seg_base(struct pt_regs *regs, struct insn *insn, + int regoff);
#endif /* _ASM_X86_INSN_EVAL_H */ diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index f46cb31..c77ed80 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -476,6 +476,133 @@ static struct desc_struct *get_desc(unsigned short sel) }
/** + * insn_get_seg_base() - Obtain base address of segment descriptor. + * @regs: Structure with register values as seen when entering kernel mode + * @insn: Instruction structure with selector override prefixes + * @regoff: Operand offset, in pt_regs, of which the selector is needed + * + * Obtain the base address of the segment descriptor as indicated by either + * any segment override prefixes contained in insn or the default segment + * applicable to the register indicated by regoff. regoff is specified as the + * offset in bytes from the base of pt_regs. + * + * Return: In protected mode, base address of the segment. Zero in for long + * mode, except when FS or GS are used. In virtual-8086 mode, the segment + * selector shifted 4 positions to the right. -1L in case of + * error. + */ +unsigned long insn_get_seg_base(struct pt_regs *regs, struct insn *insn, + int regoff) +{ + struct desc_struct *desc; + unsigned short sel; + enum segment_register seg_reg; + + seg_reg = resolve_seg_register(insn, regs, regoff); + if (seg_reg == SEG_REG_INVAL) + return -1L; + + sel = get_segment_selector(regs, seg_reg); + if ((short)sel < 0) + return -1L; + + if (v8086_mode(regs)) + /* + * Base is simply the segment selector shifted 4 + * positions to the right. + */ + return (unsigned long)(sel << 4); + + if (user_64bit_mode(regs)) { + /* + * Only FS or GS will have a base address, the rest of + * the segments' bases are forced to 0. + */ + unsigned long base; + + if (seg_reg == SEG_REG_FS) + rdmsrl(MSR_FS_BASE, base); + else if (seg_reg == SEG_REG_GS) + /* + * swapgs was called at the kernel entry point. Thus, + * MSR_KERNEL_GS_BASE will have the user-space GS base. + */ + rdmsrl(MSR_KERNEL_GS_BASE, base); + else if (seg_reg != SEG_REG_IGNORE) + /* We should ignore the rest of segment registers */ + base = -1L; + else + base = 0; + return base; + } + + /* In protected mode the segment selector cannot be null */ + if (!sel) + return -1L; + + desc = get_desc(sel); + if (!desc) + return -1L; + + return get_desc_base(desc); +} + +/** + * get_seg_limit() - Obtain the limit of a segment descriptor + * @regs: Structure with register values as seen when entering kernel mode + * @insn: Instruction structure with selector override prefixes + * @regoff: Operand offset, in pt_regs, of which the selector is needed + * + * Obtain the limit of the segment descriptor. The segment selector is obtained + * by inspecting any segment override prefixes or the default selector + * inferred by regoff. regoff is specified as the offset in bytes from the base + * of pt_regs. + * + * Return: In protected mode, the limit of the segment descriptor in bytes. + * In long mode and virtual-8086 mode, segment limits are not enforced. Thus, + * limit is returned as -1L to imply a limit-less segment. Zero is returned on + * error. + */ +static unsigned long get_seg_limit(struct pt_regs *regs, struct insn *insn, + int regoff) +{ + struct desc_struct *desc; + unsigned short sel; + unsigned long limit; + enum segment_register seg_reg; + + seg_reg = resolve_seg_register(insn, regs, regoff); + if (seg_reg == SEG_REG_INVAL) + return 0; + + sel = get_segment_selector(regs, seg_reg); + if ((short)sel < 0) + return 0; + + if (user_64bit_mode(regs) || v8086_mode(regs)) + return -1L; + + if (!sel) + return 0; + + desc = get_desc(sel); + if (!desc) + return 0; + + /* + * If the granularity bit is set, the limit is given in multiples + * of 4096. When the granularity bit is set, the least 12 significant + * bits are not tested when checking the segment limits. In practice, + * this means that the segment ends in (limit << 12) + 0xfff. + */ + limit = get_desc_limit(desc); + if (desc->g) + limit <<= 12 | 0x7; + + return limit; +} + +/** * insn_get_reg_offset_modrm_rm() - Obtain register in r/m part of ModRM byte * @insn: Instruction structure containing the ModRM byte * @regs: Structure with register values as seen when entering kernel mode