3 files changed, 53 insertions, 25 deletions

diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index 169a120587b..87b67e3a765 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -729,7 +729,7 @@ struct pebs_tracer *ds_request_pebs(struct task_struct *task,
 
 	spin_unlock_irqrestore(&ds_lock, irq);
 
-	ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts);
+	ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_pebs);
 	ds_resume_pebs(tracer);
 
 	return tracer;
@@ -1029,5 +1029,4 @@ void ds_copy_thread(struct task_struct *tsk, struct task_struct *father)
 
 void ds_exit_thread(struct task_struct *tsk)
 {
-	WARN_ON(tsk->thread.ds_ctx);
 }
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index c29f301d388..efa615f2bf4 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -42,6 +42,19 @@ unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
 };
 EXPORT_SYMBOL(__per_cpu_offset);
 
+/*
+ * On x86_64 symbols referenced from code should be reachable using
+ * 32bit relocations.  Reserve space for static percpu variables in
+ * modules so that they are always served from the first chunk which
+ * is located at the percpu segment base.  On x86_32, anything can
+ * address anywhere.  No need to reserve space in the first chunk.
+ */
+#ifdef CONFIG_X86_64
+#define PERCPU_FIRST_CHUNK_RESERVE	PERCPU_MODULE_RESERVE
+#else
+#define PERCPU_FIRST_CHUNK_RESERVE	0
+#endif
+
 /**
  * pcpu_need_numa - determine percpu allocation needs to consider NUMA
  *
@@ -141,7 +154,7 @@ static ssize_t __init setup_pcpu_remap(size_t static_size)
 {
 	static struct vm_struct vm;
 	pg_data_t *last;
-	size_t ptrs_size;
+	size_t ptrs_size, dyn_size;
 	unsigned int cpu;
 	ssize_t ret;
 
@@ -169,12 +182,14 @@ proceed:
 	 * Currently supports only single page.  Supporting multiple
 	 * pages won't be too difficult if it ever becomes necessary.
 	 */
-	pcpur_size = PFN_ALIGN(static_size + PERCPU_DYNAMIC_RESERVE);
+	pcpur_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE +
+			       PERCPU_DYNAMIC_RESERVE);
 	if (pcpur_size > PMD_SIZE) {
 		pr_warning("PERCPU: static data is larger than large page, "
 			   "can't use large page\n");
 		return -EINVAL;
 	}
+	dyn_size = pcpur_size - static_size - PERCPU_FIRST_CHUNK_RESERVE;
 
 	/* allocate pointer array and alloc large pages */
 	ptrs_size = PFN_ALIGN(num_possible_cpus() * sizeof(pcpur_ptrs[0]));
@@ -217,8 +232,9 @@ proceed:
 	pr_info("PERCPU: Remapped at %p with large pages, static data "
 		"%zu bytes\n", vm.addr, static_size);
 
-	ret = pcpu_setup_first_chunk(pcpur_get_page, static_size, PMD_SIZE,
-				     pcpur_size - static_size, vm.addr, NULL);
+	ret = pcpu_setup_first_chunk(pcpur_get_page, static_size,
+				     PERCPU_FIRST_CHUNK_RESERVE,
+				     PMD_SIZE, dyn_size, vm.addr, NULL);
 	goto out_free_ar;
 
 enomem:
@@ -241,24 +257,31 @@ static ssize_t __init setup_pcpu_remap(size_t static_size)
  * Embedding allocator
  *
  * The first chunk is sized to just contain the static area plus
- * PERCPU_DYNAMIC_RESERVE and allocated as a contiguous area using
- * bootmem allocator and used as-is without being mapped into vmalloc
- * area.  This enables the first chunk to piggy back on the linear
- * physical PMD mapping and doesn't add any additional pressure to
- * TLB.
+ * module and dynamic reserves, and allocated as a contiguous area
+ * using bootmem allocator and used as-is without being mapped into
+ * vmalloc area.  This enables the first chunk to piggy back on the
+ * linear physical PMD mapping and doesn't add any additional pressure
+ * to TLB.  Note that if the needed size is smaller than the minimum
+ * unit size, the leftover is returned to the bootmem allocator.
  */
 static void *pcpue_ptr __initdata;
+static size_t pcpue_size __initdata;
 static size_t pcpue_unit_size __initdata;
 
 static struct page * __init pcpue_get_page(unsigned int cpu, int pageno)
 {
-	return virt_to_page(pcpue_ptr + cpu * pcpue_unit_size
-			    + ((size_t)pageno << PAGE_SHIFT));
+	size_t off = (size_t)pageno << PAGE_SHIFT;
+
+	if (off >= pcpue_size)
+		return NULL;
+
+	return virt_to_page(pcpue_ptr + cpu * pcpue_unit_size + off);
 }
 
 static ssize_t __init setup_pcpu_embed(size_t static_size)
 {
 	unsigned int cpu;
+	size_t dyn_size;
 
 	/*
 	 * If large page isn't supported, there's no benefit in doing
@@ -269,25 +292,32 @@ static ssize_t __init setup_pcpu_embed(size_t static_size)
 		return -EINVAL;
 
 	/* allocate and copy */
-	pcpue_unit_size = PFN_ALIGN(static_size + PERCPU_DYNAMIC_RESERVE);
-	pcpue_unit_size = max_t(size_t, pcpue_unit_size, PCPU_MIN_UNIT_SIZE);
+	pcpue_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE +
+			       PERCPU_DYNAMIC_RESERVE);
+	pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE);
+	dyn_size = pcpue_size - static_size - PERCPU_FIRST_CHUNK_RESERVE;
+
 	pcpue_ptr = pcpu_alloc_bootmem(0, num_possible_cpus() * pcpue_unit_size,
 				       PAGE_SIZE);
 	if (!pcpue_ptr)
 		return -ENOMEM;
 
-	for_each_possible_cpu(cpu)
-		memcpy(pcpue_ptr + cpu * pcpue_unit_size, __per_cpu_load,
-		       static_size);
+	for_each_possible_cpu(cpu) {
+		void *ptr = pcpue_ptr + cpu * pcpue_unit_size;
+
+		free_bootmem(__pa(ptr + pcpue_size),
+			     pcpue_unit_size - pcpue_size);
+		memcpy(ptr, __per_cpu_load, static_size);
+	}
 
 	/* we're ready, commit */
 	pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n",
-		pcpue_unit_size >> PAGE_SHIFT, pcpue_ptr, static_size);
+		pcpue_size >> PAGE_SHIFT, pcpue_ptr, static_size);
 
 	return pcpu_setup_first_chunk(pcpue_get_page, static_size,
-				      pcpue_unit_size,
-				      pcpue_unit_size - static_size, pcpue_ptr,
-				      NULL);
+				      PERCPU_FIRST_CHUNK_RESERVE,
+				      pcpue_unit_size, dyn_size,
+				      pcpue_ptr, NULL);
 }
 
 /*
@@ -344,7 +374,8 @@ static ssize_t __init setup_pcpu_4k(size_t static_size)
 	pr_info("PERCPU: Allocated %d 4k pages, static data %zu bytes\n",
 		pcpu4k_nr_static_pages, static_size);
 
-	ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size, 0, 0, NULL,
+	ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size,
+				     PERCPU_FIRST_CHUNK_RESERVE, -1, -1, NULL,
 				     pcpu4k_populate_pte);
 	goto out_free_ar;
 
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index f04549afcfe..d038b9c45cf 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -314,8 +314,6 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 	int locals = 0;
 	struct bau_desc *bau_desc;
 
-	WARN_ON(!in_atomic());
-
 	cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu));
 
 	uv_cpu = uv_blade_processor_id();