x86/entry/64: Create a per-CPU SYSCALL entry trampoline

commit 3386bc8aed825e9f1f65ce38df4b109b2019b71a upstream.

Handling SYSCALL is tricky: the SYSCALL handler is entered with every
single register (except FLAGS), including RSP, live.  It somehow needs
to set RSP to point to a valid stack, which means it needs to save the
user RSP somewhere and find its own stack pointer.  The canonical way
to do this is with SWAPGS, which lets us access percpu data using the
%gs prefix.

With PAGE_TABLE_ISOLATION-like pagetable switching, this is
problematic.  Without a scratch register, switching CR3 is impossible, so
%gs-based percpu memory would need to be mapped in the user pagetables.
Doing that without information leaks is difficult or impossible.

Instead, use a different sneaky trick.  Map a copy of the first part
of the SYSCALL asm at a different address for each CPU.  Now RIP
varies depending on the CPU, so we can use RIP-relative memory access
to access percpu memory.  By putting the relevant information (one
scratch slot and the stack address) at a constant offset relative to
RIP, we can make SYSCALL work without relying on %gs.

A nice thing about this approach is that we can easily switch it on
and off if we want pagetable switching to be configurable.

The compat variant of SYSCALL doesn't have this problem in the first
place -- there are plenty of scratch registers, since we don't care
about preserving r8-r15.  This patch therefore doesn't touch SYSCALL32
at all.

This patch actually seems to be a small speedup.  With this patch,
SYSCALL touches an extra cache line and an extra virtual page, but
the pipeline no longer stalls waiting for SWAPGS.  It seems that, at
least in a tight loop, the latter outweights the former.

Thanks to David Laight for an optimization tip.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bpetkov@suse.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Link: https://lkml.kernel.org/r/20171204150606.403607157@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 9323585c4de6189a0128dbcfba615782e5cdf7a6..47ec428d101a4cc1adc7f6c14ee8b76081340aea 100644 (file)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -136,6 +136,64 @@ END(native_usergs_sysret64)
  * with them due to bugs in both AMD and Intel CPUs.
  */
 
+       .pushsection .entry_trampoline, "ax"
+
+/*
+ * The code in here gets remapped into cpu_entry_area's trampoline.  This means
+ * that the assembler and linker have the wrong idea as to where this code
+ * lives (and, in fact, it's mapped more than once, so it's not even at a
+ * fixed address).  So we can't reference any symbols outside the entry
+ * trampoline and expect it to work.
+ *
+ * Instead, we carefully abuse %rip-relative addressing.
+ * _entry_trampoline(%rip) refers to the start of the remapped) entry
+ * trampoline.  We can thus find cpu_entry_area with this macro:
+ */
+
+#define CPU_ENTRY_AREA \
+       _entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip)
+
+/* The top word of the SYSENTER stack is hot and is usable as scratch space. */
+#define RSP_SCRATCH    CPU_ENTRY_AREA_tss + CPU_TSS_SYSENTER_stack + \
+                       SIZEOF_SYSENTER_stack - 8 + CPU_ENTRY_AREA
+
+ENTRY(entry_SYSCALL_64_trampoline)
+       UNWIND_HINT_EMPTY
+       swapgs
+
+       /* Stash the user RSP. */
+       movq    %rsp, RSP_SCRATCH
+
+       /* Load the top of the task stack into RSP */
+       movq    CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp
+
+       /* Start building the simulated IRET frame. */
+       pushq   $__USER_DS                      /* pt_regs->ss */
+       pushq   RSP_SCRATCH                     /* pt_regs->sp */
+       pushq   %r11                            /* pt_regs->flags */
+       pushq   $__USER_CS                      /* pt_regs->cs */
+       pushq   %rcx                            /* pt_regs->ip */
+
+       /*
+        * x86 lacks a near absolute jump, and we can't jump to the real
+        * entry text with a relative jump.  We could push the target
+        * address and then use retq, but this destroys the pipeline on
+        * many CPUs (wasting over 20 cycles on Sandy Bridge).  Instead,
+        * spill RDI and restore it in a second-stage trampoline.
+        */
+       pushq   %rdi
+       movq    $entry_SYSCALL_64_stage2, %rdi
+       jmp     *%rdi
+END(entry_SYSCALL_64_trampoline)
+
+       .popsection
+
+ENTRY(entry_SYSCALL_64_stage2)
+       UNWIND_HINT_EMPTY
+       popq    %rdi
+       jmp     entry_SYSCALL_64_after_hwframe
+END(entry_SYSCALL_64_stage2)
+
 ENTRY(entry_SYSCALL_64)
        UNWIND_HINT_EMPTY
        /*

diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 84558b611ad33dc215500058031d1384e59253e3..6a699474c2c7dd9b6d94e8d7b82045768cf695ac 100644 (file)
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -61,6 +61,8 @@ struct cpu_entry_area {
         * of the TSS region.
         */
        struct tss_struct tss;
+
+       char entry_trampoline[PAGE_SIZE];
 };
 
 #define CPU_ENTRY_AREA_PAGES (sizeof(struct cpu_entry_area) / PAGE_SIZE)

diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 55858b277cf6203bbec09153690cb90adb888ab7..61b1af88ac0707fda38e86627be42a35c6e5bddf 100644 (file)
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -101,4 +101,5 @@ void common(void) {
 
        /* Layout info for cpu_entry_area */
        OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss);
+       OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
 }

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 57968880e39b6d1fff3f602605e715d766146dba..430f950b0b7fa3ad5baa10008cb92b6cc16bf54e 100644 (file)
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -486,6 +486,8 @@ DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
 static inline void setup_cpu_entry_area(int cpu)
 {
 #ifdef CONFIG_X86_64
+       extern char _entry_trampoline[];
+
        /* On 64-bit systems, we use a read-only fixmap GDT. */
        pgprot_t gdt_prot = PAGE_KERNEL_RO;
 #else
@@ -532,6 +534,11 @@ static inline void setup_cpu_entry_area(int cpu)
 #ifdef CONFIG_X86_32
        this_cpu_write(cpu_entry_area, get_cpu_entry_area(cpu));
 #endif
+
+#ifdef CONFIG_X86_64
+       __set_fixmap(get_cpu_entry_area_index(cpu, entry_trampoline),
+                    __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
+#endif
 }
 
 /* Load the original GDT from the per-cpu structure */
@@ -1395,10 +1402,16 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
 /* May not be marked __init: used by software suspend */
 void syscall_init(void)
 {
+       extern char _entry_trampoline[];
+       extern char entry_SYSCALL_64_trampoline[];
+
        int cpu = smp_processor_id();
+       unsigned long SYSCALL64_entry_trampoline =
+               (unsigned long)get_cpu_entry_area(cpu)->entry_trampoline +
+               (entry_SYSCALL_64_trampoline - _entry_trampoline);
 
        wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
-       wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
+       wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline);
 
 #ifdef CONFIG_IA32_EMULATION
        wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat);

diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index a4009fb9be8725ce7bda96cd5e8160e524903266..d2a8b5a24a44a554e2f81f3b30309ef39aba0d8a 100644 (file)
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -107,6 +107,15 @@ SECTIONS
                SOFTIRQENTRY_TEXT
                *(.fixup)
                *(.gnu.warning)
+
+#ifdef CONFIG_X86_64
+               . = ALIGN(PAGE_SIZE);
+               _entry_trampoline = .;
+               *(.entry_trampoline)
+               . = ALIGN(PAGE_SIZE);
+               ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big");
+#endif
+
                /* End of text section */
                _etext = .;
        } :text = 0x9090