Perpcu uses a clever design where the .percu ELF section has a virtual
address of zero and the relocation code avoid relocating specific
symbols. It makes the code simple and easily adaptable with or without
SMP support.
This design is incompatible with PIE because generated code always try to
access the zero virtual address relative to the default mapping address.
It becomes impossible when KASLR is configured to go below -2G. This
patch solves this problem by removing the zero mapping and adapting the GS
base to be relative to the expected address. These changes are done only
when PIE is enabled. The original implementation is kept as-is
by default.
The assembly and PER_CPU macros are changed to use relative references
when PIE is enabled.
The KALLSYMS_ABSOLUTE_PERCPU configuration is disabled with PIE given
percpu symbols are not absolute in this case.
Position Independent Executable (PIE) support will allow to extend the
KASLR randomization range 0xffffffff80000000.
Signed-off-by: Thomas Garnier <[email protected]>
---
arch/x86/entry/calling.h | 2 +-
arch/x86/entry/entry_64.S | 4 ++--
arch/x86/include/asm/percpu.h | 25 +++++++++++++++++++------
arch/x86/include/asm/processor.h | 4 +++-
arch/x86/kernel/head_64.S | 4 ++++
arch/x86/kernel/setup_percpu.c | 5 ++++-
arch/x86/kernel/vmlinux.lds.S | 13 +++++++++++--
arch/x86/lib/cmpxchg16b_emu.S | 8 ++++----
arch/x86/xen/xen-asm.S | 12 ++++++------
init/Kconfig | 2 +-
10 files changed, 55 insertions(+), 24 deletions(-)
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 352e70cd33e8..d6c60e6b598f 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -218,7 +218,7 @@ For 32-bit we have the following conventions - kernel is built with
.endm
#define THIS_CPU_user_pcid_flush_mask \
- PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask
+ PER_CPU_VAR(cpu_tlbstate + TLB_STATE_user_pcid_flush_mask)
.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 1cbf4c3616a8..f9b42ca4bf60 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -359,7 +359,7 @@ ENTRY(__switch_to_asm)
#ifdef CONFIG_CC_STACKPROTECTOR
movq TASK_stack_canary(%rsi), %rbx
- movq %rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset
+ movq %rbx, PER_CPU_VAR(irq_stack_union + stack_canary_offset)
#endif
#ifdef CONFIG_RETPOLINE
@@ -897,7 +897,7 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt
/*
* Exception entry points.
*/
-#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
+#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw + (TSS_ist + ((x) - 1) * 8))
.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
ENTRY(\sym)
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index a06b07399d17..7d1271b536ea 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -5,9 +5,11 @@
#ifdef CONFIG_X86_64
#define __percpu_seg gs
#define __percpu_mov_op movq
+#define __percpu_rel (%rip)
#else
#define __percpu_seg fs
#define __percpu_mov_op movl
+#define __percpu_rel
#endif
#ifdef __ASSEMBLY__
@@ -28,10 +30,14 @@
#define PER_CPU(var, reg) \
__percpu_mov_op %__percpu_seg:this_cpu_off, reg; \
lea var(reg), reg
-#define PER_CPU_VAR(var) %__percpu_seg:var
+/* Compatible with Position Independent Code */
+#define PER_CPU_VAR(var) %__percpu_seg:(var)##__percpu_rel
+/* Rare absolute reference */
+#define PER_CPU_VAR_ABS(var) %__percpu_seg:var
#else /* ! SMP */
#define PER_CPU(var, reg) __percpu_mov_op $var, reg
-#define PER_CPU_VAR(var) var
+#define PER_CPU_VAR(var) (var)##__percpu_rel
+#define PER_CPU_VAR_ABS(var) var
#endif /* SMP */
#ifdef CONFIG_X86_64_SMP
@@ -209,27 +215,34 @@ do { \
pfo_ret__; \
})
+/* Position Independent code uses relative addresses only */
+#ifdef CONFIG_X86_PIE
+#define __percpu_stable_arg __percpu_arg(a1)
+#else
+#define __percpu_stable_arg __percpu_arg(P1)
+#endif
+
#define percpu_stable_op(op, var) \
({ \
typeof(var) pfo_ret__; \
switch (sizeof(var)) { \
case 1: \
- asm(op "b "__percpu_arg(P1)",%0" \
+ asm(op "b "__percpu_stable_arg ",%0" \
: "=q" (pfo_ret__) \
: "p" (&(var))); \
break; \
case 2: \
- asm(op "w "__percpu_arg(P1)",%0" \
+ asm(op "w "__percpu_stable_arg ",%0" \
: "=r" (pfo_ret__) \
: "p" (&(var))); \
break; \
case 4: \
- asm(op "l "__percpu_arg(P1)",%0" \
+ asm(op "l "__percpu_stable_arg ",%0" \
: "=r" (pfo_ret__) \
: "p" (&(var))); \
break; \
case 8: \
- asm(op "q "__percpu_arg(P1)",%0" \
+ asm(op "q "__percpu_stable_arg ",%0" \
: "=r" (pfo_ret__) \
: "p" (&(var))); \
break; \
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 7ae9fb91f7b5..8162b5a24d8c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -24,6 +24,7 @@ struct vm86;
#include <asm/special_insns.h>
#include <asm/fpu/types.h>
#include <asm/unwind_hints.h>
+#include <asm/sections.h>
#include <linux/personality.h>
#include <linux/cache.h>
@@ -400,7 +401,8 @@ DECLARE_INIT_PER_CPU(irq_stack_union);
static inline unsigned long cpu_kernelmode_gs_base(int cpu)
{
- return (unsigned long)per_cpu(irq_stack_union.gs_base, cpu);
+ return (unsigned long)per_cpu(irq_stack_union.gs_base, cpu) -
+ (unsigned long)__per_cpu_start;
}
DECLARE_PER_CPU(char *, irq_stack_ptr);
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 7fca19e1f556..fddeb3d81aa6 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -268,7 +268,11 @@ ENDPROC(start_cpu0)
GLOBAL(initial_code)
.quad x86_64_start_kernel
GLOBAL(initial_gs)
+#ifdef CONFIG_X86_PIE
+ .quad 0
+#else
.quad INIT_PER_CPU_VAR(irq_stack_union)
+#endif
GLOBAL(initial_stack)
/*
* The SIZEOF_PTREGS gap is a convention which helps the in-kernel
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index ea554f812ee1..d61ecc3d2b6f 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -26,7 +26,7 @@
DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number);
EXPORT_PER_CPU_SYMBOL(cpu_number);
-#ifdef CONFIG_X86_64
+#if defined(CONFIG_X86_64) && !defined(CONFIG_X86_PIE)
#define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load)
#else
#define BOOT_PERCPU_OFFSET 0
@@ -40,6 +40,9 @@ unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init = {
};
EXPORT_SYMBOL(__per_cpu_offset);
+/* Used to calculate gs_base for each CPU */
+EXPORT_SYMBOL(__per_cpu_start);
+
/*
* On x86_64 symbols referenced from code should be reachable using
* 32bit relocations. Reserve space for static percpu variables in
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 5e1458f609a1..f582fc4776dd 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -211,9 +211,14 @@ SECTIONS
/*
* percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the
* output PHDR, so the next output section - .init.text - should
- * start another segment - init.
+ * start another segment - init. For Position Independent Code, the
+ * per-cpu section cannot be zero-based because everything is relative.
*/
+#ifdef CONFIG_X86_PIE
+ PERCPU_SECTION(INTERNODE_CACHE_BYTES)
+#else
PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu)
+#endif
ASSERT(SIZEOF(.data..percpu) < CONFIG_PHYSICAL_START,
"per-CPU data too large - increase CONFIG_PHYSICAL_START")
#endif
@@ -389,7 +394,11 @@ SECTIONS
* Per-cpu symbols which need to be offset from __per_cpu_load
* for the boot processor.
*/
+#ifdef CONFIG_X86_PIE
+#define INIT_PER_CPU(x) init_per_cpu__##x = x
+#else
#define INIT_PER_CPU(x) init_per_cpu__##x = x + __per_cpu_load
+#endif
INIT_PER_CPU(gdt_page);
INIT_PER_CPU(irq_stack_union);
@@ -399,7 +408,7 @@ INIT_PER_CPU(irq_stack_union);
. = ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
"kernel image bigger than KERNEL_IMAGE_SIZE");
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && !defined(CONFIG_X86_PIE)
. = ASSERT((irq_stack_union == 0),
"irq_stack_union is not at start of per-cpu area");
#endif
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index 9b330242e740..254950604ae4 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -33,13 +33,13 @@ ENTRY(this_cpu_cmpxchg16b_emu)
pushfq
cli
- cmpq PER_CPU_VAR((%rsi)), %rax
+ cmpq PER_CPU_VAR_ABS((%rsi)), %rax
jne .Lnot_same
- cmpq PER_CPU_VAR(8(%rsi)), %rdx
+ cmpq PER_CPU_VAR_ABS(8(%rsi)), %rdx
jne .Lnot_same
- movq %rbx, PER_CPU_VAR((%rsi))
- movq %rcx, PER_CPU_VAR(8(%rsi))
+ movq %rbx, PER_CPU_VAR_ABS((%rsi))
+ movq %rcx, PER_CPU_VAR_ABS(8(%rsi))
popfq
mov $1, %al
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 8019edd0125c..a5d73d3218be 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -21,7 +21,7 @@
ENTRY(xen_irq_enable_direct)
FRAME_BEGIN
/* Unmask events */
- movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+ movb $0, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
/*
* Preempt here doesn't matter because that will deal with any
@@ -30,7 +30,7 @@ ENTRY(xen_irq_enable_direct)
*/
/* Test for pending */
- testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
+ testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_pending)
jz 1f
call check_events
@@ -45,7 +45,7 @@ ENTRY(xen_irq_enable_direct)
* non-zero.
*/
ENTRY(xen_irq_disable_direct)
- movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+ movb $1, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
ret
ENDPROC(xen_irq_disable_direct)
@@ -59,7 +59,7 @@ ENDPROC(xen_irq_disable_direct)
* x86 use opposite senses (mask vs enable).
*/
ENTRY(xen_save_fl_direct)
- testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+ testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
setz %ah
addb %ah, %ah
ret
@@ -80,7 +80,7 @@ ENTRY(xen_restore_fl_direct)
#else
testb $X86_EFLAGS_IF>>8, %ah
#endif
- setz PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+ setz PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
/*
* Preempt here doesn't matter because that will deal with any
* pending interrupts. The pending check may end up being run
@@ -88,7 +88,7 @@ ENTRY(xen_restore_fl_direct)
*/
/* check for unmasked and pending */
- cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
+ cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_pending)
jnz 1f
call check_events
1:
diff --git a/init/Kconfig b/init/Kconfig
index 8fec5d136f1f..e4acab9f9fd1 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1391,7 +1391,7 @@ config KALLSYMS_ALL
config KALLSYMS_ABSOLUTE_PERCPU
bool
depends on KALLSYMS
- default X86_64 && SMP
+ default X86_64 && SMP && !X86_PIE
config KALLSYMS_BASE_RELATIVE
bool
--
2.17.0.921.gf22659ad46-goog
On Tue, 29 May 2018, Thomas Garnier wrote:
> Perpcu uses a clever design where the .percu ELF section has a virtual
> address of zero and the relocation code avoid relocating specific
> symbols. It makes the code simple and easily adaptable with or without
> SMP support.
>
> This design is incompatible with PIE because generated code always try to
> access the zero virtual address relative to the default mapping address.
We always access relative to the "segment register".
You can already change the segment register to relocate the per cpu
sections arbitrarily since all per cpu "addresses" are offsets relative to
the segment register. I am not sure what exactly you are trying to
accomplish here?
Maybe you need to explain it better?
On Tue, May 29, 2018 at 3:46 PM Christopher Lameter <[email protected]> wrote:
> On Tue, 29 May 2018, Thomas Garnier wrote:
> > Perpcu uses a clever design where the .percu ELF section has a virtual
> > address of zero and the relocation code avoid relocating specific
> > symbols. It makes the code simple and easily adaptable with or without
> > SMP support.
> >
> > This design is incompatible with PIE because generated code always try
to
> > access the zero virtual address relative to the default mapping address.
> We always access relative to the "segment register".
> You can already change the segment register to relocate the per cpu
> sections arbitrarily since all per cpu "addresses" are offsets relative to
> the segment register. I am not sure what exactly you are trying to
> accomplish here?
When building with PIE, the compiler wants the code to be relocatable
anywhere in the 64-bit VA space. Instead of taking the segment register as
an immediate value, it takes it as VA that need to be relocated relative to
where the kernel is mapped. The per-cpu section VA is zero to create the
proper offset to the different variable. The kernel could be at the top of
the 64-bit VA space. PIE will try to create the delta between any VA and
zero and fail because segment register based operations do not have full
64-bit VA range. Does it make sense?
For PIE only, this change will remove the per-cpu section VA of zero. Now
the distance between the per-cpu symbol and the kernel base VA can fit in
the generated instructions.
> Maybe you need to explain it better?
I will try do explain it better on the next patch set.
--
Thomas