Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Several conflicts, seemingly all over the place.

I used Stephen Rothwell's sample resolutions for many of these, if not
just to double check my own work, so definitely the credit largely
goes to him.

The NFP conflict consisted of a bug fix (moving operations
past the rhashtable operation) while chaning the initial
argument in the function call in the moved code.

The net/dsa/master.c conflict had to do with a bug fix intermixing of
making dsa_master_set_mtu() static with the fixing of the tagging
attribute location.

cls_flower had a conflict because the dup reject fix from Or
overlapped with the addition of port range classifiction.

__set_phy_supported()'s conflict was relatively easy to resolve
because Andrew fixed it in both trees, so it was just a matter
of taking the net-next copy.  Or at least I think it was :-)

Joe Stringer's fix to the handling of netns id 0 in bpf_sk_lookup()
intermixed with changes on how the sdif and caller_net are calculated
in these code paths in net-next.

The remaining BPF conflicts were largely about the addition of the
__bpf_md_ptr stuff in 'net' overlapping with adjustments and additions
to the relevant data structure where the MD pointer macros are used.

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 86 insertions, 29 deletions

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index bddd6b3cee1d..03b6b4c2238d 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -7,7 +7,6 @@
 #include <linux/export.h>
 #include <linux/cpu.h>
 #include <linux/debugfs.h>
-#include <linux/ptrace.h>
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
@@ -31,6 +30,12 @@
  */
 
 /*
+ * Use bit 0 to mangle the TIF_SPEC_IB state into the mm pointer which is
+ * stored in cpu_tlb_state.last_user_mm_ibpb.
+ */
+#define LAST_USER_MM_IBPB	0x1UL
+
+/*
  * We get here when we do something requiring a TLB invalidation
  * but could not go invalidate all of the contexts.  We do the
  * necessary invalidation by clearing out the 'ctx_id' which
@@ -181,17 +186,87 @@ static void sync_current_stack_to_mm(struct mm_struct *mm)
 	}
 }
 
-static bool ibpb_needed(struct task_struct *tsk, u64 last_ctx_id)
+static inline unsigned long mm_mangle_tif_spec_ib(struct task_struct *next)
+{
+	unsigned long next_tif = task_thread_info(next)->flags;
+	unsigned long ibpb = (next_tif >> TIF_SPEC_IB) & LAST_USER_MM_IBPB;
+
+	return (unsigned long)next->mm | ibpb;
+}
+
+static void cond_ibpb(struct task_struct *next)
 {
+	if (!next || !next->mm)
+		return;
+
 	/*
-	 * Check if the current (previous) task has access to the memory
-	 * of the @tsk (next) task. If access is denied, make sure to
-	 * issue a IBPB to stop user->user Spectre-v2 attacks.
-	 *
-	 * Note: __ptrace_may_access() returns 0 or -ERRNO.
+	 * Both, the conditional and the always IBPB mode use the mm
+	 * pointer to avoid the IBPB when switching between tasks of the
+	 * same process. Using the mm pointer instead of mm->context.ctx_id
+	 * opens a hypothetical hole vs. mm_struct reuse, which is more or
+	 * less impossible to control by an attacker. Aside of that it
+	 * would only affect the first schedule so the theoretically
+	 * exposed data is not really interesting.
 	 */
-	return (tsk && tsk->mm && tsk->mm->context.ctx_id != last_ctx_id &&
-		ptrace_may_access_sched(tsk, PTRACE_MODE_SPEC_IBPB));
+	if (static_branch_likely(&switch_mm_cond_ibpb)) {
+		unsigned long prev_mm, next_mm;
+
+		/*
+		 * This is a bit more complex than the always mode because
+		 * it has to handle two cases:
+		 *
+		 * 1) Switch from a user space task (potential attacker)
+		 *    which has TIF_SPEC_IB set to a user space task
+		 *    (potential victim) which has TIF_SPEC_IB not set.
+		 *
+		 * 2) Switch from a user space task (potential attacker)
+		 *    which has TIF_SPEC_IB not set to a user space task
+		 *    (potential victim) which has TIF_SPEC_IB set.
+		 *
+		 * This could be done by unconditionally issuing IBPB when
+		 * a task which has TIF_SPEC_IB set is either scheduled in
+		 * or out. Though that results in two flushes when:
+		 *
+		 * - the same user space task is scheduled out and later
+		 *   scheduled in again and only a kernel thread ran in
+		 *   between.
+		 *
+		 * - a user space task belonging to the same process is
+		 *   scheduled in after a kernel thread ran in between
+		 *
+		 * - a user space task belonging to the same process is
+		 *   scheduled in immediately.
+		 *
+		 * Optimize this with reasonably small overhead for the
+		 * above cases. Mangle the TIF_SPEC_IB bit into the mm
+		 * pointer of the incoming task which is stored in
+		 * cpu_tlbstate.last_user_mm_ibpb for comparison.
+		 */
+		next_mm = mm_mangle_tif_spec_ib(next);
+		prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_ibpb);
+
+		/*
+		 * Issue IBPB only if the mm's are different and one or
+		 * both have the IBPB bit set.
+		 */
+		if (next_mm != prev_mm &&
+		    (next_mm | prev_mm) & LAST_USER_MM_IBPB)
+			indirect_branch_prediction_barrier();
+
+		this_cpu_write(cpu_tlbstate.last_user_mm_ibpb, next_mm);
+	}
+
+	if (static_branch_unlikely(&switch_mm_always_ibpb)) {
+		/*
+		 * Only flush when switching to a user space task with a
+		 * different context than the user space task which ran
+		 * last on this CPU.
+		 */
+		if (this_cpu_read(cpu_tlbstate.last_user_mm) != next->mm) {
+			indirect_branch_prediction_barrier();
+			this_cpu_write(cpu_tlbstate.last_user_mm, next->mm);
+		}
+	}
 }
 
 void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
@@ -292,22 +367,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		new_asid = prev_asid;
 		need_flush = true;
 	} else {
-		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 a processes that can't be ptrace by the
-		 * current one (as in such case, attacker has much more
-		 * convenient way how to tamper with the next process than
-		 * branch buffer poisoning).
 		 */
-		if (static_cpu_has(X86_FEATURE_USE_IBPB) &&
-				ibpb_needed(tsk, last_ctx_id))
-			indirect_branch_prediction_barrier();
+		cond_ibpb(tsk);
 
 		if (IS_ENABLED(CONFIG_VMAP_STACK)) {
 			/*
@@ -365,14 +430,6 @@ 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);
-
 	/* Make sure we write CR3 before loaded_mm. */
 	barrier();
 
@@ -441,7 +498,7 @@ 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.last_user_mm_ibpb, LAST_USER_MM_IBPB);
 	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);