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

Pull spectre/meltdown updates from Thomas Gleixner:
 "The next round of updates related to melted spectrum:

   - The initial set of spectre V1 mitigations:

       - Array index speculation blocker and its usage for syscall,
         fdtable and the n180211 driver.

       - Speculation barrier and its usage in user access functions

   - Make indirect calls in KVM speculation safe

   - Blacklisting of known to be broken microcodes so IPBP/IBSR are not
     touched.

   - The initial IBPB support and its usage in context switch

   - The exposure of the new speculation MSRs to KVM guests.

   - A fix for a regression in x86/32 related to the cpu entry area

   - Proper whitelisting for known to be safe CPUs from the mitigations.

   - objtool fixes to deal proper with retpolines and alternatives

   - Exclude __init functions from retpolines which speeds up the boot
     process.

   - Removal of the syscall64 fast path and related cleanups and
     simplifications

   - Removal of the unpatched paravirt mode which is yet another source
     of indirect unproteced calls.

   - A new and undisputed version of the module mismatch warning

   - A couple of cleanup and correctness fixes all over the place

  Yet another step towards full mitigation. There are a few things still
  missing like the RBS underflow mitigation for Skylake and other small
  details, but that's being worked on.

  That said, I'm taking a belated christmas vacation for a week and hope
  that everything is magically solved when I'm back on Feb 12th"

* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (37 commits)
  KVM/SVM: Allow direct access to MSR_IA32_SPEC_CTRL
  KVM/VMX: Allow direct access to MSR_IA32_SPEC_CTRL
  KVM/VMX: Emulate MSR_IA32_ARCH_CAPABILITIES
  KVM/x86: Add IBPB support
  KVM/x86: Update the reverse_cpuid list to include CPUID_7_EDX
  x86/speculation: Fix typo IBRS_ATT, which should be IBRS_ALL
  x86/pti: Mark constant arrays as __initconst
  x86/spectre: Simplify spectre_v2 command line parsing
  x86/retpoline: Avoid retpolines for built-in __init functions
  x86/kvm: Update spectre-v1 mitigation
  KVM: VMX: make MSR bitmaps per-VCPU
  x86/paravirt: Remove 'noreplace-paravirt' cmdline option
  x86/speculation: Use Indirect Branch Prediction Barrier in context switch
  x86/cpuid: Fix up "virtual" IBRS/IBPB/STIBP feature bits on Intel
  x86/spectre: Fix spelling mistake: "vunerable"-> "vulnerable"
  x86/spectre: Report get_user mitigation for spectre_v1
  nl80211: Sanitize array index in parse_txq_params
  vfs, fdtable: Prevent bounds-check bypass via speculative execution
  x86/syscall: Sanitize syscall table de-references under speculation
  x86/get_user: Use pointer masking to limit speculation
  ...

1 files changed, 32 insertions, 1 deletions

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 5bfe61a5e8e3..012d02624848 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -6,13 +6,14 @@
 #include <linux/interrupt.h>
 #include <linux/export.h>
 #include <linux/cpu.h>
+#include <linux/debugfs.h>
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
+#include <asm/nospec-branch.h>
 #include <asm/cache.h>
 #include <asm/apic.h>
 #include <asm/uv/uv.h>
-#include <linux/debugfs.h>
 
 /*
  *	TLB flushing, formerly SMP-only
@@ -247,6 +248,27 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	} else {
 		u16 new_asid;
 		bool need_flush;
+		u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id);
+
+		/*
+		 * Avoid user/user BTB poisoning by flushing the branch
+		 * predictor when switching between processes. This stops
+		 * one process from doing Spectre-v2 attacks on another.
+		 *
+		 * As an optimization, flush indirect branches only when
+		 * switching into processes that disable dumping. This
+		 * protects high value processes like gpg, without having
+		 * too high performance overhead. IBPB is *expensive*!
+		 *
+		 * This will not flush branches when switching into kernel
+		 * threads. It will also not flush if we switch to idle
+		 * thread and back to the same process. It will flush if we
+		 * switch to a different non-dumpable process.
+		 */
+		if (tsk && tsk->mm &&
+		    tsk->mm->context.ctx_id != last_ctx_id &&
+		    get_dumpable(tsk->mm) != SUID_DUMP_USER)
+			indirect_branch_prediction_barrier();
 
 		if (IS_ENABLED(CONFIG_VMAP_STACK)) {
 			/*
@@ -292,6 +314,14 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
 		}
 
+		/*
+		 * Record last user mm's context id, so we can avoid
+		 * flushing branch buffer with IBPB if we switch back
+		 * to the same user.
+		 */
+		if (next != &init_mm)
+			this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
+
 		this_cpu_write(cpu_tlbstate.loaded_mm, next);
 		this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
 	}
@@ -369,6 +399,7 @@ void initialize_tlbstate_and_flush(void)
 	write_cr3(build_cr3(mm->pgd, 0));
 
 	/* Reinitialize tlbstate. */
+	this_cpu_write(cpu_tlbstate.last_ctx_id, mm->context.ctx_id);
 	this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0);
 	this_cpu_write(cpu_tlbstate.next_asid, 1);
 	this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id);