Merge branch 'x86/pti' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 PTI updates from Thomas Gleixner:
 "The Speck brigade sadly provides yet another large set of patches
  destroying the perfomance which we carefully built and preserved

   - PTI support for 32bit PAE. The missing counter part to the 64bit
     PTI code implemented by Joerg.

   - A set of fixes for the Global Bit mechanics for non PCID CPUs which
     were setting the Global Bit too widely and therefore possibly
     exposing interesting memory needlessly.

   - Protection against userspace-userspace SpectreRSB

   - Support for the upcoming Enhanced IBRS mode, which is preferred
     over IBRS. Unfortunately we dont know the performance impact of
     this, but it's expected to be less horrible than the IBRS
     hammering.

   - Cleanups and simplifications"

* 'x86/pti' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (60 commits)
  x86/mm/pti: Move user W+X check into pti_finalize()
  x86/relocs: Add __end_rodata_aligned to S_REL
  x86/mm/pti: Clone kernel-image on PTE level for 32 bit
  x86/mm/pti: Don't clear permissions in pti_clone_pmd()
  x86/mm/pti: Fix 32 bit PCID check
  x86/mm/init: Remove freed kernel image areas from alias mapping
  x86/mm/init: Add helper for freeing kernel image pages
  x86/mm/init: Pass unconverted symbol addresses to free_init_pages()
  mm: Allow non-direct-map arguments to free_reserved_area()
  x86/mm/pti: Clear Global bit more aggressively
  x86/speculation: Support Enhanced IBRS on future CPUs
  x86/speculation: Protect against userspace-userspace spectreRSB
  x86/kexec: Allocate 8k PGDs for PTI
  Revert "perf/core: Make sure the ring-buffer is mapped in all page-tables"
  x86/mm: Remove in_nmi() warning from vmalloc_fault()
  x86/entry/32: Check for VM86 mode in slow-path check
  perf/core: Make sure the ring-buffer is mapped in all page-tables
  x86/pti: Check the return value of pti_user_pagetable_walk_pmd()
  x86/pti: Check the return value of pti_user_pagetable_walk_p4d()
  x86/entry/32: Add debug code to check entry/exit CR3
  ...
This commit is contained in:
Linus Torvalds
2018-08-13 17:54:17 -07:00
45 changed files with 1269 additions and 411 deletions

View File

@@ -130,6 +130,7 @@ static const char *spectre_v2_strings[] = {
[SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline",
[SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline",
[SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline",
[SPECTRE_V2_IBRS_ENHANCED] = "Mitigation: Enhanced IBRS",
};
#undef pr_fmt
@@ -313,23 +314,6 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
return cmd;
}
/* Check for Skylake-like CPUs (for RSB handling) */
static bool __init is_skylake_era(void)
{
if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
boot_cpu_data.x86 == 6) {
switch (boot_cpu_data.x86_model) {
case INTEL_FAM6_SKYLAKE_MOBILE:
case INTEL_FAM6_SKYLAKE_DESKTOP:
case INTEL_FAM6_SKYLAKE_X:
case INTEL_FAM6_KABYLAKE_MOBILE:
case INTEL_FAM6_KABYLAKE_DESKTOP:
return true;
}
}
return false;
}
static void __init spectre_v2_select_mitigation(void)
{
enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -349,6 +333,13 @@ static void __init spectre_v2_select_mitigation(void)
case SPECTRE_V2_CMD_FORCE:
case SPECTRE_V2_CMD_AUTO:
if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) {
mode = SPECTRE_V2_IBRS_ENHANCED;
/* Force it so VMEXIT will restore correctly */
x86_spec_ctrl_base |= SPEC_CTRL_IBRS;
wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
goto specv2_set_mode;
}
if (IS_ENABLED(CONFIG_RETPOLINE))
goto retpoline_auto;
break;
@@ -386,26 +377,20 @@ retpoline_auto:
setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
}
specv2_set_mode:
spectre_v2_enabled = mode;
pr_info("%s\n", spectre_v2_strings[mode]);
/*
* If neither SMEP nor PTI are available, there is a risk of
* hitting userspace addresses in the RSB after a context switch
* from a shallow call stack to a deeper one. To prevent this fill
* the entire RSB, even when using IBRS.
* If spectre v2 protection has been enabled, unconditionally fill
* RSB during a context switch; this protects against two independent
* issues:
*
* Skylake era CPUs have a separate issue with *underflow* of the
* RSB, when they will predict 'ret' targets from the generic BTB.
* The proper mitigation for this is IBRS. If IBRS is not supported
* or deactivated in favour of retpolines the RSB fill on context
* switch is required.
* - RSB underflow (and switch to BTB) on Skylake+
* - SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs
*/
if ((!boot_cpu_has(X86_FEATURE_PTI) &&
!boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
pr_info("Spectre v2 mitigation: Filling RSB on context switch\n");
}
setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
/* Initialize Indirect Branch Prediction Barrier if supported */
if (boot_cpu_has(X86_FEATURE_IBPB)) {
@@ -415,9 +400,16 @@ retpoline_auto:
/*
* Retpoline means the kernel is safe because it has no indirect
* branches. But firmware isn't, so use IBRS to protect that.
* branches. Enhanced IBRS protects firmware too, so, enable restricted
* speculation around firmware calls only when Enhanced IBRS isn't
* supported.
*
* Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because
* the user might select retpoline on the kernel command line and if
* the CPU supports Enhanced IBRS, kernel might un-intentionally not
* enable IBRS around firmware calls.
*/
if (boot_cpu_has(X86_FEATURE_IBRS)) {
if (boot_cpu_has(X86_FEATURE_IBRS) && mode != SPECTRE_V2_IBRS_ENHANCED) {
setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
pr_info("Enabling Restricted Speculation for firmware calls\n");
}

View File

@@ -1005,6 +1005,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
!cpu_has(c, X86_FEATURE_AMD_SSB_NO))
setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
if (ia32_cap & ARCH_CAP_IBRS_ALL)
setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
if (x86_match_cpu(cpu_no_meltdown))
return;
@@ -1804,11 +1807,12 @@ void cpu_init(void)
enter_lazy_tlb(&init_mm, curr);
/*
* Initialize the TSS. Don't bother initializing sp0, as the initial
* task never enters user mode.
* Initialize the TSS. sp0 points to the entry trampoline stack
* regardless of what task is running.
*/
set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
load_TR_desc();
load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1));
load_mm_ldt(&init_mm);