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

Pull scheduler updates from Ingo Molnar:
 "The main changes are:

   - lockless wakeup support for futexes and IPC message queues
     (Davidlohr Bueso, Peter Zijlstra)

   - Replace spinlocks with atomics in thread_group_cputimer(), to
     improve scalability (Jason Low)

   - NUMA balancing improvements (Rik van Riel)

   - SCHED_DEADLINE improvements (Wanpeng Li)

   - clean up and reorganize preemption helpers (Frederic Weisbecker)

   - decouple page fault disabling machinery from the preemption
     counter, to improve debuggability and robustness (David
     Hildenbrand)

   - SCHED_DEADLINE documentation updates (Luca Abeni)

   - topology CPU masks cleanups (Bartosz Golaszewski)

   - /proc/sched_debug improvements (Srikar Dronamraju)"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (79 commits)
  sched/deadline: Remove needless parameter in dl_runtime_exceeded()
  sched: Remove superfluous resetting of the p->dl_throttled flag
  sched/deadline: Drop duplicate init_sched_dl_class() declaration
  sched/deadline: Reduce rq lock contention by eliminating locking of non-feasible target
  sched/deadline: Make init_sched_dl_class() __init
  sched/deadline: Optimize pull_dl_task()
  sched/preempt: Add static_key() to preempt_notifiers
  sched/preempt: Fix preempt notifiers documentation about hlist_del() within unsafe iteration
  sched/stop_machine: Fix deadlock between multiple stop_two_cpus()
  sched/debug: Add sum_sleep_runtime to /proc/<pid>/sched
  sched/debug: Replace vruntime with wait_sum in /proc/sched_debug
  sched/debug: Properly format runnable tasks in /proc/sched_debug
  sched/numa: Only consider less busy nodes as numa balancing destinations
  Revert 095bebf61a46 ("sched/numa: Do not move past the balance point if unbalanced")
  sched/fair: Prevent throttling in early pick_next_task_fair()
  preempt: Reorganize the notrace definitions a bit
  preempt: Use preempt_schedule_context() as the official tracing preemption point
  sched: Make preempt_schedule_context() function-tracing safe
  x86: Remove cpu_sibling_mask() and cpu_core_mask()
  x86: Replace cpu_**_mask() with topology_**_cpumask()
  ...

14 files changed, 39 insertions, 23 deletions

diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index 6bc9cbc01ad6..00b39802d7ec 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -105,7 +105,7 @@ static void round_robin_cpu(unsigned int tsk_index)
 	mutex_lock(&round_robin_lock);
 	cpumask_clear(tmp);
 	for_each_cpu(cpu, pad_busy_cpus)
-		cpumask_or(tmp, tmp, topology_thread_cpumask(cpu));
+		cpumask_or(tmp, tmp, topology_sibling_cpumask(cpu));
 	cpumask_andnot(tmp, cpu_online_mask, tmp);
 	/* avoid HT sibilings if possible */
 	if (cpumask_empty(tmp))
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index 6491f45200a7..8b7d7f8e5851 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -61,7 +61,7 @@ static DEVICE_ATTR_RO(physical_package_id);
 define_id_show_func(core_id);
 static DEVICE_ATTR_RO(core_id);
 
-define_siblings_show_func(thread_siblings, thread_cpumask);
+define_siblings_show_func(thread_siblings, sibling_cpumask);
 static DEVICE_ATTR_RO(thread_siblings);
 static DEVICE_ATTR_RO(thread_siblings_list);
 
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index b0c18ed8d83f..0136dfcdabf0 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -699,13 +699,14 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	dmi_check_system(sw_any_bug_dmi_table);
 	if (bios_with_sw_any_bug && !policy_is_shared(policy)) {
 		policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
-		cpumask_copy(policy->cpus, cpu_core_mask(cpu));
+		cpumask_copy(policy->cpus, topology_core_cpumask(cpu));
 	}
 
 	if (check_amd_hwpstate_cpu(cpu) && !acpi_pstate_strict) {
 		cpumask_clear(policy->cpus);
 		cpumask_set_cpu(cpu, policy->cpus);
-		cpumask_copy(data->freqdomain_cpus, cpu_sibling_mask(cpu));
+		cpumask_copy(data->freqdomain_cpus,
+			     topology_sibling_cpumask(cpu));
 		policy->shared_type = CPUFREQ_SHARED_TYPE_HW;
 		pr_info_once(PFX "overriding BIOS provided _PSD data\n");
 	}
diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c
index 529cfd92158f..5dd95dab580d 100644
--- a/drivers/cpufreq/p4-clockmod.c
+++ b/drivers/cpufreq/p4-clockmod.c
@@ -172,7 +172,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy)
 	unsigned int i;
 
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
+	cpumask_copy(policy->cpus, topology_sibling_cpumask(policy->cpu));
 #endif
 
 	/* Errata workaround */
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index f9ce7e4bf0fe..5c035d04d827 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -57,13 +57,6 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
 
 static struct cpufreq_driver cpufreq_amd64_driver;
 
-#ifndef CONFIG_SMP
-static inline const struct cpumask *cpu_core_mask(int cpu)
-{
-	return cpumask_of(0);
-}
-#endif
-
 /* Return a frequency in MHz, given an input fid */
 static u32 find_freq_from_fid(u32 fid)
 {
@@ -620,7 +613,7 @@ static int fill_powernow_table(struct powernow_k8_data *data,
 
 	pr_debug("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid);
 	data->powernow_table = powernow_table;
-	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
+	if (cpumask_first(topology_core_cpumask(data->cpu)) == data->cpu)
 		print_basics(data);
 
 	for (j = 0; j < data->numps; j++)
@@ -784,7 +777,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 		CPUFREQ_TABLE_END;
 	data->powernow_table = powernow_table;
 
-	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
+	if (cpumask_first(topology_core_cpumask(data->cpu)) == data->cpu)
 		print_basics(data);
 
 	/* notify BIOS that we exist */
@@ -1090,7 +1083,7 @@ static int powernowk8_cpu_init(struct cpufreq_policy *pol)
 	if (rc != 0)
 		goto err_out_exit_acpi;
 
-	cpumask_copy(pol->cpus, cpu_core_mask(pol->cpu));
+	cpumask_copy(pol->cpus, topology_core_cpumask(pol->cpu));
 	data->available_cores = pol->cpus;
 
 	/* min/max the cpu is capable of */
diff --git a/drivers/cpufreq/speedstep-ich.c b/drivers/cpufreq/speedstep-ich.c
index e56d632a8b21..37555c6b86a7 100644
--- a/drivers/cpufreq/speedstep-ich.c
+++ b/drivers/cpufreq/speedstep-ich.c
@@ -292,7 +292,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 
 	/* only run on CPU to be set, or on its sibling */
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
+	cpumask_copy(policy->cpus, topology_sibling_cpumask(policy->cpu));
 #endif
 	policy_cpu = cpumask_any_and(policy->cpus, cpu_online_mask);
 
diff --git a/drivers/crypto/vmx/aes.c b/drivers/crypto/vmx/aes.c
index ab300ea19434..a9064e36e7b5 100644
--- a/drivers/crypto/vmx/aes.c
+++ b/drivers/crypto/vmx/aes.c
@@ -78,12 +78,14 @@ static int p8_aes_setkey(struct crypto_tfm *tfm, const u8 *key,
     int ret;
     struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 
+    preempt_disable();
     pagefault_disable();
     enable_kernel_altivec();
     ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
     ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
     pagefault_enable();
-    
+    preempt_enable();
+
     ret += crypto_cipher_setkey(ctx->fallback, key, keylen);
     return ret;
 }
@@ -95,10 +97,12 @@ static void p8_aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
     if (in_interrupt()) {
         crypto_cipher_encrypt_one(ctx->fallback, dst, src);
     } else {
+	preempt_disable();
         pagefault_disable();
         enable_kernel_altivec();
         aes_p8_encrypt(src, dst, &ctx->enc_key);
         pagefault_enable();
+	preempt_enable();
     }
 }
 
@@ -109,10 +113,12 @@ static void p8_aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
     if (in_interrupt()) {
         crypto_cipher_decrypt_one(ctx->fallback, dst, src);
     } else {
+	preempt_disable();
         pagefault_disable();
         enable_kernel_altivec();
         aes_p8_decrypt(src, dst, &ctx->dec_key);
         pagefault_enable();
+	preempt_enable();
     }
 }
 
diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c
index 1a559b7dddb5..477284abdd11 100644
--- a/drivers/crypto/vmx/aes_cbc.c
+++ b/drivers/crypto/vmx/aes_cbc.c
@@ -79,11 +79,13 @@ static int p8_aes_cbc_setkey(struct crypto_tfm *tfm, const u8 *key,
     int ret;
     struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
 
+    preempt_disable();
     pagefault_disable();
     enable_kernel_altivec();
     ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
     ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
     pagefault_enable();
+    preempt_enable();
 
     ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen);
     return ret;
@@ -106,6 +108,7 @@ static int p8_aes_cbc_encrypt(struct blkcipher_desc *desc,
     if (in_interrupt()) {
         ret = crypto_blkcipher_encrypt(&fallback_desc, dst, src, nbytes);
     } else {
+	preempt_disable();
         pagefault_disable();
         enable_kernel_altivec();
 
@@ -119,6 +122,7 @@ static int p8_aes_cbc_encrypt(struct blkcipher_desc *desc,
 	}
 
         pagefault_enable();
+	preempt_enable();
     }
 
     return ret;
@@ -141,6 +145,7 @@ static int p8_aes_cbc_decrypt(struct blkcipher_desc *desc,
     if (in_interrupt()) {
         ret = crypto_blkcipher_decrypt(&fallback_desc, dst, src, nbytes);
     } else {
+	preempt_disable();
         pagefault_disable();
         enable_kernel_altivec();
 
@@ -154,6 +159,7 @@ static int p8_aes_cbc_decrypt(struct blkcipher_desc *desc,
 		}
 
         pagefault_enable();
+	preempt_enable();
     }
 
     return ret;
diff --git a/drivers/crypto/vmx/ghash.c b/drivers/crypto/vmx/ghash.c
index d0ffe277af5c..f255ec4a04d4 100644
--- a/drivers/crypto/vmx/ghash.c
+++ b/drivers/crypto/vmx/ghash.c
@@ -114,11 +114,13 @@ static int p8_ghash_setkey(struct crypto_shash *tfm, const u8 *key,
     if (keylen != GHASH_KEY_LEN)
         return -EINVAL;
 
+    preempt_disable();
     pagefault_disable();
     enable_kernel_altivec();
     enable_kernel_fp();
     gcm_init_p8(ctx->htable, (const u64 *) key);
     pagefault_enable();
+    preempt_enable();
     return crypto_shash_setkey(ctx->fallback, key, keylen);
 }
 
@@ -140,23 +142,27 @@ static int p8_ghash_update(struct shash_desc *desc,
             }
             memcpy(dctx->buffer + dctx->bytes, src,
                     GHASH_DIGEST_SIZE - dctx->bytes);
+	    preempt_disable();
             pagefault_disable();
             enable_kernel_altivec();
             enable_kernel_fp();
             gcm_ghash_p8(dctx->shash, ctx->htable, dctx->buffer,
                     GHASH_DIGEST_SIZE);
             pagefault_enable();
+	    preempt_enable();
             src += GHASH_DIGEST_SIZE - dctx->bytes;
             srclen -= GHASH_DIGEST_SIZE - dctx->bytes;
             dctx->bytes = 0;
         }
         len = srclen & ~(GHASH_DIGEST_SIZE - 1);
         if (len) {
+	    preempt_disable();
             pagefault_disable();
             enable_kernel_altivec();
             enable_kernel_fp();
             gcm_ghash_p8(dctx->shash, ctx->htable, src, len);
             pagefault_enable();
+	    preempt_enable();
             src += len;
             srclen -= len;
         }
@@ -180,12 +186,14 @@ static int p8_ghash_final(struct shash_desc *desc, u8 *out)
         if (dctx->bytes) {
             for (i = dctx->bytes; i < GHASH_DIGEST_SIZE; i++)
                 dctx->buffer[i] = 0;
+	    preempt_disable();
             pagefault_disable();
             enable_kernel_altivec();
             enable_kernel_fp();
             gcm_ghash_p8(dctx->shash, ctx->htable, dctx->buffer,
                     GHASH_DIGEST_SIZE);
             pagefault_enable();
+	    preempt_enable();
             dctx->bytes = 0;
         }
         memcpy(out, dctx->shash, GHASH_DIGEST_SIZE);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index a3190e793ed4..cc552a4c1f3b 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -32,6 +32,7 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 #include <linux/dma_remapping.h>
+#include <linux/uaccess.h>
 
 #define  __EXEC_OBJECT_HAS_PIN (1<<31)
 #define  __EXEC_OBJECT_HAS_FENCE (1<<30)
@@ -465,7 +466,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 	}
 
 	/* We can't wait for rendering with pagefaults disabled */
-	if (obj->active && in_atomic())
+	if (obj->active && pagefault_disabled())
 		return -EFAULT;
 
 	if (use_cpu_reloc(obj))
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index ed303ba3a593..3e03379e7c5d 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -63,7 +63,8 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
 #define TO_ATTR_NO(cpu)		(TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO)
 
 #ifdef CONFIG_SMP
-#define for_each_sibling(i, cpu)	for_each_cpu(i, cpu_sibling_mask(cpu))
+#define for_each_sibling(i, cpu) \
+	for_each_cpu(i, topology_sibling_cpumask(cpu))
 #else
 #define for_each_sibling(i, cpu)	for (i = 0; false; )
 #endif
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 4b00545a3ace..65944dd8bf6b 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1304,7 +1304,7 @@ static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
 			if (!cpumask_test_cpu(cpu, thread_mask)) {
 				++count;
 				cpumask_or(thread_mask, thread_mask,
-					   topology_thread_cpumask(cpu));
+					   topology_sibling_cpumask(cpu));
 			}
 		}
 
diff --git a/drivers/staging/lustre/lustre/libcfs/linux/linux-cpu.c b/drivers/staging/lustre/lustre/libcfs/linux/linux-cpu.c
index cc3ab351943e..f9262243f935 100644
--- a/drivers/staging/lustre/lustre/libcfs/linux/linux-cpu.c
+++ b/drivers/staging/lustre/lustre/libcfs/linux/linux-cpu.c
@@ -87,7 +87,7 @@ static void cfs_cpu_core_siblings(int cpu, cpumask_t *mask)
 /* return cpumask of HTs in the same core */
 static void cfs_cpu_ht_siblings(int cpu, cpumask_t *mask)
 {
-	cpumask_copy(mask, topology_thread_cpumask(cpu));
+	cpumask_copy(mask, topology_sibling_cpumask(cpu));
 }
 
 static void cfs_node_to_cpumask(int node, cpumask_t *mask)
diff --git a/drivers/staging/lustre/lustre/ptlrpc/service.c b/drivers/staging/lustre/lustre/ptlrpc/service.c
index 8e61421515cb..344189ac5698 100644
--- a/drivers/staging/lustre/lustre/ptlrpc/service.c
+++ b/drivers/staging/lustre/lustre/ptlrpc/service.c
@@ -557,7 +557,7 @@ ptlrpc_server_nthreads_check(struct ptlrpc_service *svc,
 		 * there are.
 		 */
 		/* weight is # of HTs */
-		if (cpumask_weight(topology_thread_cpumask(0)) > 1) {
+		if (cpumask_weight(topology_sibling_cpumask(0)) > 1) {
 			/* depress thread factor for hyper-thread */
 			factor = factor - (factor >> 1) + (factor >> 3);
 		}
@@ -2768,7 +2768,7 @@ int ptlrpc_hr_init(void)
 
 	init_waitqueue_head(&ptlrpc_hr.hr_waitq);
 
-	weight = cpumask_weight(topology_thread_cpumask(0));
+	weight = cpumask_weight(topology_sibling_cpumask(0));
 
 	cfs_percpt_for_each(hrp, i, ptlrpc_hr.hr_partitions) {
 		hrp->hrp_cpt = i;