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

Pull low-level x86 updates from Ingo Molnar:
 "In this cycle this topic tree has become one of those 'super topics'
  that accumulated a lot of changes:

   - Add CONFIG_VMAP_STACK=y support to the core kernel and enable it on
     x86 - preceded by an array of changes. v4.8 saw preparatory changes
     in this area already - this is the rest of the work. Includes the
     thread stack caching performance optimization. (Andy Lutomirski)

   - switch_to() cleanups and all around enhancements. (Brian Gerst)

   - A large number of dumpstack infrastructure enhancements and an
     unwinder abstraction. The secret long term plan is safe(r) live
     patching plus maybe another attempt at debuginfo based unwinding -
     but all these current bits are standalone enhancements in a frame
     pointer based debug environment as well. (Josh Poimboeuf)

   - More __ro_after_init and const annotations. (Kees Cook)

   - Enable KASLR for the vmemmap memory region. (Thomas Garnier)"

[ The virtually mapped stack changes are pretty fundamental, and not
  x86-specific per se, even if they are only used on x86 right now. ]

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (70 commits)
  x86/asm: Get rid of __read_cr4_safe()
  thread_info: Use unsigned long for flags
  x86/alternatives: Add stack frame dependency to alternative_call_2()
  x86/dumpstack: Fix show_stack() task pointer regression
  x86/dumpstack: Remove dump_trace() and related callbacks
  x86/dumpstack: Convert show_trace_log_lvl() to use the new unwinder
  oprofile/x86: Convert x86_backtrace() to use the new unwinder
  x86/stacktrace: Convert save_stack_trace_*() to use the new unwinder
  perf/x86: Convert perf_callchain_kernel() to use the new unwinder
  x86/unwind: Add new unwind interface and implementations
  x86/dumpstack: Remove NULL task pointer convention
  fork: Optimize task creation by caching two thread stacks per CPU if CONFIG_VMAP_STACK=y
  sched/core: Free the stack early if CONFIG_THREAD_INFO_IN_TASK
  lib/syscall: Pin the task stack in collect_syscall()
  x86/process: Pin the target stack in get_wchan()
  x86/dumpstack: Pin the target stack when dumping it
  kthread: Pin the stack via try_get_task_stack()/put_task_stack() in to_live_kthread() function
  sched/core: Add try_get_task_stack() and put_task_stack()
  x86/entry/64: Fix a minor comment rebase error
  iommu/amd: Don't put completion-wait semaphore on stack
  ...

2 files changed, 37 insertions, 16 deletions

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 96de97a46079..4025291ea0ae 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -940,15 +940,13 @@ static void build_inv_irt(struct iommu_cmd *cmd, u16 devid)
  * Writes the command to the IOMMUs command buffer and informs the
  * hardware about the new command.
  */
-static int iommu_queue_command_sync(struct amd_iommu *iommu,
-				    struct iommu_cmd *cmd,
-				    bool sync)
+static int __iommu_queue_command_sync(struct amd_iommu *iommu,
+				      struct iommu_cmd *cmd,
+				      bool sync)
 {
 	u32 left, tail, head, next_tail;
-	unsigned long flags;
 
 again:
-	spin_lock_irqsave(&iommu->lock, flags);
 
 	head      = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
 	tail      = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
@@ -957,15 +955,14 @@ again:
 
 	if (left <= 2) {
 		struct iommu_cmd sync_cmd;
-		volatile u64 sem = 0;
 		int ret;
 
-		build_completion_wait(&sync_cmd, (u64)&sem);
-		copy_cmd_to_buffer(iommu, &sync_cmd, tail);
+		iommu->cmd_sem = 0;
 
-		spin_unlock_irqrestore(&iommu->lock, flags);
+		build_completion_wait(&sync_cmd, (u64)&iommu->cmd_sem);
+		copy_cmd_to_buffer(iommu, &sync_cmd, tail);
 
-		if ((ret = wait_on_sem(&sem)) != 0)
+		if ((ret = wait_on_sem(&iommu->cmd_sem)) != 0)
 			return ret;
 
 		goto again;
@@ -976,9 +973,21 @@ again:
 	/* We need to sync now to make sure all commands are processed */
 	iommu->need_sync = sync;
 
+	return 0;
+}
+
+static int iommu_queue_command_sync(struct amd_iommu *iommu,
+				    struct iommu_cmd *cmd,
+				    bool sync)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	ret = __iommu_queue_command_sync(iommu, cmd, sync);
 	spin_unlock_irqrestore(&iommu->lock, flags);
 
-	return 0;
+	return ret;
 }
 
 static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
@@ -993,19 +1002,29 @@ static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
 static int iommu_completion_wait(struct amd_iommu *iommu)
 {
 	struct iommu_cmd cmd;
-	volatile u64 sem = 0;
+	unsigned long flags;
 	int ret;
 
 	if (!iommu->need_sync)
 		return 0;
 
-	build_completion_wait(&cmd, (u64)&sem);
 
-	ret = iommu_queue_command_sync(iommu, &cmd, false);
+	build_completion_wait(&cmd, (u64)&iommu->cmd_sem);
+
+	spin_lock_irqsave(&iommu->lock, flags);
+
+	iommu->cmd_sem = 0;
+
+	ret = __iommu_queue_command_sync(iommu, &cmd, false);
 	if (ret)
-		return ret;
+		goto out_unlock;
+
+	ret = wait_on_sem(&iommu->cmd_sem);
 
-	return wait_on_sem(&sem);
+out_unlock:
+	spin_unlock_irqrestore(&iommu->lock, flags);
+
+	return ret;
 }
 
 static int iommu_flush_dte(struct amd_iommu *iommu, u16 devid)
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index caf5e3822715..9652848e3155 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -524,6 +524,8 @@ struct amd_iommu {
 	struct irq_domain *ir_domain;
 	struct irq_domain *msi_domain;
 #endif
+
+	volatile u64 __aligned(8) cmd_sem;
 };
 
 #define ACPIHID_UID_LEN 256