Merge remote-tracking branch 'origin/upstream/linux-linaro-lsk-v3.10-android+android-common-3.10' into develop-3.10

Documentation/arm/small_task_packing.txt

@@ -0,0 +1,136 @@
+Small Task Packing in the big.LITTLE MP Reference Patch Set
+
+What is small task packing?
+----
+Simply that the scheduler will fit as many small tasks on a single CPU
+as possible before using other CPUs. A small task is defined as one
+whose tracked load is less than 90% of a NICE_0 task. This is a change
+from the usual behavior since the scheduler will normally use an idle
+CPU for a waking task unless that task is considered cache hot.
+
+
+How is it implemented?
+----
+Since all small tasks must wake up relatively frequently, the main
+requirement for packing small tasks is to select a partly-busy CPU when
+waking rather than looking for an idle CPU. We use the tracked load of
+the CPU runqueue to determine how heavily loaded each CPU is and the
+tracked load of the task to determine if it will fit on the CPU. We
+always start with the lowest-numbered CPU in a sched domain and stop
+looking when we find a CPU with enough space for the task.
+
+Some further tweaks are necessary to suppress load balancing when the
+CPU is not fully loaded, otherwise the scheduler attempts to spread
+tasks evenly across the domain.
+
+
+How does it interact with the HMP patches?
+----
+Firstly, we only enable packing on the little domain. The intent is that
+the big domain is intended to spread tasks amongst the available CPUs
+one-task-per-CPU. The little domain however is attempting to use as
+little power as possible while servicing its tasks.
+
+Secondly, since we offload big tasks onto little CPUs in order to try
+to devote one CPU to each task, we have a threshold above which we do
+not try to pack a task and instead will select an idle CPU if possible.
+This maintains maximum forward progress for busy tasks temporarily
+demoted from big CPUs.
+
+
+Can the behaviour be tuned?
+----
+Yes, the load level of a 'full' CPU can be easily modified in the source
+and is exposed through sysfs as /sys/kernel/hmp/packing_limit to be
+changed at runtime. The presence of the packing behaviour is controlled
+by CONFIG_SCHED_HMP_LITTLE_PACKING and can be disabled at run-time
+using /sys/kernel/hmp/packing_enable.
+The definition of a small task is hard coded as 90% of NICE_0_LOAD
+and cannot be modified at run time.
+
+
+Why do I need to tune it?
+----
+The optimal configuration is likely to be different depending upon the
+design and manufacturing of your SoC.
+
+In the main, there are two system effects from enabling small task
+packing.
+
+1. CPU operating point may increase
+2. wakeup latency of tasks may be increased
+
+There are also likely to be secondary effects from loading one CPU
+rather than spreading tasks.
+
+Note that all of these system effects are dependent upon the workload
+under consideration.
+
+
+CPU Operating Point
+----
+The primary impact of loading one CPU with a number of light tasks is to
+increase the compute requirement of that CPU since it is no longer idle
+as often. Increased compute requirement causes an increase in the
+frequency of the CPU through CPUfreq.
+
+Consider this example:
+We have a system with 3 CPUs which can operate at any frequency between
+350MHz and 1GHz. The system has 6 tasks which would each produce 10%
+load at 1GHz. The scheduler has frequency-invariant load scaling
+enabled. Our DVFS governor aims for 80% utilization at the chosen
+frequency.
+
+Without task packing, these tasks will be spread out amongst all CPUs
+such that each has 2. This will produce roughly 20% system load, and
+the frequency of the package will remain at 350MHz.
+
+With task packing set to the default packing_limit, all of these tasks
+will sit on one CPU and require a package frequency of ~750MHz to reach
+80% utilization. (0.75 = 0.6 * 0.8).
+
+When a package operates on a single frequency domain, all CPUs in that
+package share frequency and voltage.
+
+Depending upon the SoC implementation there can be a significant amount
+of energy lost to leakage from idle CPUs. The decision about how
+loaded a CPU must be to be considered 'full' is therefore controllable
+through sysfs (sys/kernel/hmp/packing_limit) and directly in the code.
+
+Continuing the example, lets set packing_limit to 450 which means we
+will pack tasks until the total load of all running tasks >= 450. In
+practise, this is very similar to a 55% idle 1Ghz CPU.
+
+Now we are only able to place 4 tasks on CPU0, and two will overflow
+onto CPU1. CPU0 will have a load of 40% and CPU1 will have a load of
+20%. In order to still hit 80% utilization, CPU0 now only needs to
+operate at (0.4*0.8=0.32) 320MHz, which means that the lowest operating
+point will be selected, the same as in the non-packing case, except that
+now CPU2 is no longer needed and can be power-gated.
+
+In order to use less energy, the saving from power-gating CPU2 must be
+more than the energy spent running CPU0 for the extra cycles. This
+depends upon the SoC implementation.
+
+This is obviously a contrived example requiring all the tasks to
+be runnable at the same time, but it illustrates the point.
+
+
+Wakeup Latency
+----
+This is an unavoidable consequence of trying to pack tasks together
+rather than giving them a CPU each. If you cannot find an acceptable
+level of wakeup latency, you should turn packing off.
+
+Cyclictest is a good test application for determining the added latency
+when configuring packing.
+
+
+Why is it turned off for the VersatileExpress V2P_CA15A7 CoreTile?
+----
+Simply, this core tile only has power gating for the whole A7 package.
+When small task packing is enabled, all our low-energy use cases
+normally fit onto one A7 CPU. We therefore end up with 2 mostly-idle
+CPUs and one mostly-busy CPU. This decreases the amount of time
+available where the whole package is idle and can be turned off.
+

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 10
-SUBLEVEL = 19
+SUBLEVEL = 21
 EXTRAVERSION =
 NAME = TOSSUG Baby Fish
 

arch/arm/Kconfig

@@ -1513,6 +1513,17 @@ config SCHED_HMP
 	  There is currently no support for migration of task groups, hence
 	  !SCHED_AUTOGROUP. Furthermore, normal load-balancing must be disabled
 	  between cpus of different type (DISABLE_CPU_SCHED_DOMAIN_BALANCE).
+	  When turned on, this option adds sys/kernel/hmp directory which
+	  contains the following files:
+	  up_threshold - the load average threshold used for up migration
+	                 (0 - 1023)
+	  down_threshold - the load average threshold used for down migration
+	                 (0 - 1023)
+	  hmp_domains - a list of cpumasks for the present HMP domains,
+	                starting with the 'biggest' and ending with the
+	                'smallest'.
+	  Note that both the threshold files can be written at runtime to
+	  control scheduler behaviour.
 
 config SCHED_HMP_PRIO_FILTER
 	bool "(EXPERIMENTAL) Filter HMP migrations by task priority"
@@ -1547,28 +1558,24 @@ config HMP_VARIABLE_SCALE
 	bool "Allows changing the load tracking scale through sysfs"
 	depends on SCHED_HMP
 	help
-	  When turned on, this option exports the thresholds and load average
-	  period value for the load tracking patches through sysfs.
+	  When turned on, this option exports the load average period value
+	  for the load tracking patches through sysfs.
 	  The values can be modified to change the rate of load accumulation
-	  and the thresholds used for HMP migration.
-	  The load_avg_period_ms is the time in ms to reach a load average of
-	  0.5 for an idle task of 0 load average ratio that start a busy loop.
-	  The up_threshold and down_threshold is the value to go to a faster
-	  CPU or to go back to a slower cpu.
-	  The {up,down}_threshold are devided by 1024 before being compared
-	  to the load average.
-	  For examples, with load_avg_period_ms = 128 and up_threshold = 512,
+	  used for HMP migration. 'load_avg_period_ms' is the time in ms to
+	  reach a load average of 0.5 for an idle task of 0 load average
+	  ratio which becomes 100% busy.
+	  For example, with load_avg_period_ms = 128 and up_threshold = 512,
 	  a running task with a load of 0 will be migrated to a bigger CPU after
 	  128ms, because after 128ms its load_avg_ratio is 0.5 and the real
 	  up_threshold is 0.5.
 	  This patch has the same behavior as changing the Y of the load
 	  average computation to
 	        (1002/1024)^(LOAD_AVG_PERIOD/load_avg_period_ms)
-	  but it remove intermadiate overflows in computation.
+	  but removes intermediate overflows in computation.
 
 config HMP_FREQUENCY_INVARIANT_SCALE
 	bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP"
-	depends on HMP_VARIABLE_SCALE && CPU_FREQ
+	depends on SCHED_HMP && CPU_FREQ
 	help
 	  Scales the current load contribution in line with the frequency
 	  of the CPU that the task was executed on.

arch/arm/kvm/mmu.c

@@ -313,6 +313,17 @@ out:
 	return err;
 }
 
+static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
+{
+	if (!is_vmalloc_addr(kaddr)) {
+		BUG_ON(!virt_addr_valid(kaddr));
+		return __pa(kaddr);
+	} else {
+		return page_to_phys(vmalloc_to_page(kaddr)) +
+		       offset_in_page(kaddr);
+	}
+}
+
 /**
  * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
  * @from:	The virtual kernel start address of the range
@@ -324,16 +335,27 @@ out:
  */
 int create_hyp_mappings(void *from, void *to)
 {
-	unsigned long phys_addr = virt_to_phys(from);
+	phys_addr_t phys_addr;
+	unsigned long virt_addr;
 	unsigned long start = KERN_TO_HYP((unsigned long)from);
 	unsigned long end = KERN_TO_HYP((unsigned long)to);
 
-	/* Check for a valid kernel memory mapping */
-	if (!virt_addr_valid(from) || !virt_addr_valid(to - 1))
-		return -EINVAL;
+	start = start & PAGE_MASK;
+	end = PAGE_ALIGN(end);
 
-	return __create_hyp_mappings(hyp_pgd, start, end,
-				     __phys_to_pfn(phys_addr), PAGE_HYP);
+	for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) {
+		int err;
+
+		phys_addr = kvm_kaddr_to_phys(from + virt_addr - start);
+		err = __create_hyp_mappings(hyp_pgd, virt_addr,
+					    virt_addr + PAGE_SIZE,
+					    __phys_to_pfn(phys_addr),
+					    PAGE_HYP);
+		if (err)
+			return err;
+	}
+
+	return 0;
 }
 
 /**

arch/arm/mach-vexpress/tc2_pm.c

@@ -122,7 +122,15 @@ static void tc2_pm_down(u64 residency)
 	} else
 		BUG();
 
-	gic_cpu_if_down();
+	/*
+	 * If the CPU is committed to power down, make sure
+	 * the power controller will be in charge of waking it
+	 * up upon IRQ, ie IRQ lines are cut from GIC CPU IF
+	 * to the CPU by disabling the GIC CPU IF to prevent wfi
+	 * from completing execution behind power controller back
+	 */
+	if (!skip_wfi)
+		gic_cpu_if_down();
 
 	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
 		arch_spin_unlock(&tc2_pm_lock);

arch/cris/include/asm/io.h

@@ -3,6 +3,7 @@
 
 #include <asm/page.h>   /* for __va, __pa */
 #include <arch/io.h>
+#include <asm-generic/iomap.h>
 #include <linux/kernel.h>
 
 struct cris_io_operations

arch/ia64/include/asm/processor.h

@@ -319,7 +319,7 @@ struct thread_struct {
 	regs->loadrs = 0;									\
 	regs->r8 = get_dumpable(current->mm);	/* set "don't zap registers" flag */		\
 	regs->r12 = new_sp - 16;	/* allocate 16 byte scratch area */			\
-	if (unlikely(!get_dumpable(current->mm))) {							\
+	if (unlikely(get_dumpable(current->mm) != SUID_DUMP_USER)) {	\
 		/*										\
 		 * Zap scratch regs to avoid leaking bits between processes with different	\
 		 * uid/privileges.								\

arch/powerpc/kernel/signal_32.c

@@ -454,7 +454,15 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
 		if (copy_vsx_to_user(&frame->mc_vsregs, current))
 			return 1;
 		msr |= MSR_VSX;
-	}
+	} else if (!ctx_has_vsx_region)
+		/*
+		 * With a small context structure we can't hold the VSX
+		 * registers, hence clear the MSR value to indicate the state
+		 * was not saved.
+		 */
+		msr &= ~MSR_VSX;
+
+
 #endif /* CONFIG_VSX */
 #ifdef CONFIG_SPE
 	/* save spe registers */

arch/powerpc/kernel/vio.c

@@ -1530,12 +1530,12 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 
 	dn = dev->of_node;
 	if (!dn) {
-		strcat(buf, "\n");
+		strcpy(buf, "\n");
 		return strlen(buf);
 	}
 	cp = of_get_property(dn, "compatible", NULL);
 	if (!cp) {
-		strcat(buf, "\n");
+		strcpy(buf, "\n");
 		return strlen(buf);
 	}
 

arch/powerpc/mm/slice.c

@@ -258,7 +258,7 @@ static bool slice_scan_available(unsigned long addr,
 		slice = GET_HIGH_SLICE_INDEX(addr);
 		*boundary_addr = (slice + end) ?
 			((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP;
-		return !!(available.high_slices & (1u << slice));
+		return !!(available.high_slices & (1ul << slice));
 	}
 }
 

arch/powerpc/platforms/52xx/Kconfig

@@ -57,5 +57,5 @@ config PPC_MPC5200_BUGFIX
 
 config PPC_MPC5200_LPBFIFO
 	tristate "MPC5200 LocalPlus bus FIFO driver"
-	depends on PPC_MPC52xx
+	depends on PPC_MPC52xx && PPC_BESTCOMM
 	select PPC_BESTCOMM_GEN_BD

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -151,13 +151,23 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 		rid_end = pe->rid + 1;
 	}
 
-	/* Associate PE in PELT */
+	/*
+	 * Associate PE in PELT. We need add the PE into the
+	 * corresponding PELT-V as well. Otherwise, the error
+	 * originated from the PE might contribute to other
+	 * PEs.
+	 */
 	rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
 			     bcomp, dcomp, fcomp, OPAL_MAP_PE);
 	if (rc) {
 		pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc);
 		return -ENXIO;
 	}
+
+	rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
+				pe->pe_number, OPAL_ADD_PE_TO_DOMAIN);
+	if (rc)
+		pe_warn(pe, "OPAL error %d adding self to PELTV\n", rc);
 	opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
 				  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
 

arch/s390/crypto/aes_s390.c

@@ -35,7 +35,6 @@ static u8 *ctrblk;
 static char keylen_flag;
 
 struct s390_aes_ctx {
-	u8 iv[AES_BLOCK_SIZE];
 	u8 key[AES_MAX_KEY_SIZE];
 	long enc;
 	long dec;
@@ -441,30 +440,36 @@ static int cbc_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 	return aes_set_key(tfm, in_key, key_len);
 }
 
-static int cbc_aes_crypt(struct blkcipher_desc *desc, long func, void *param,
+static int cbc_aes_crypt(struct blkcipher_desc *desc, long func,
 			 struct blkcipher_walk *walk)
 {
+	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
 	int ret = blkcipher_walk_virt(desc, walk);
 	unsigned int nbytes = walk->nbytes;
+	struct {
+		u8 iv[AES_BLOCK_SIZE];
+		u8 key[AES_MAX_KEY_SIZE];
+	} param;
 
 	if (!nbytes)
 		goto out;
 
-	memcpy(param, walk->iv, AES_BLOCK_SIZE);
+	memcpy(param.iv, walk->iv, AES_BLOCK_SIZE);
+	memcpy(param.key, sctx->key, sctx->key_len);
 	do {
 		/* only use complete blocks */
 		unsigned int n = nbytes & ~(AES_BLOCK_SIZE - 1);
 		u8 *out = walk->dst.virt.addr;
 		u8 *in = walk->src.virt.addr;
 
-		ret = crypt_s390_kmc(func, param, out, in, n);
+		ret = crypt_s390_kmc(func, &param, out, in, n);
 		if (ret < 0 || ret != n)
 			return -EIO;
 
 		nbytes &= AES_BLOCK_SIZE - 1;
 		ret = blkcipher_walk_done(desc, walk, nbytes);
 	} while ((nbytes = walk->nbytes));
-	memcpy(walk->iv, param, AES_BLOCK_SIZE);
+	memcpy(walk->iv, param.iv, AES_BLOCK_SIZE);
 
 out:
 	return ret;
@@ -481,7 +486,7 @@ static int cbc_aes_encrypt(struct blkcipher_desc *desc,
 		return fallback_blk_enc(desc, dst, src, nbytes);
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_aes_crypt(desc, sctx->enc, sctx->iv, &walk);
+	return cbc_aes_crypt(desc, sctx->enc, &walk);
 }
 
 static int cbc_aes_decrypt(struct blkcipher_desc *desc,
@@ -495,7 +500,7 @@ static int cbc_aes_decrypt(struct blkcipher_desc *desc,
 		return fallback_blk_dec(desc, dst, src, nbytes);
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_aes_crypt(desc, sctx->dec, sctx->iv, &walk);
+	return cbc_aes_crypt(desc, sctx->dec, &walk);
 }
 
 static struct crypto_alg cbc_aes_alg = {

arch/s390/kernel/smp.c

@@ -933,7 +933,7 @@ static ssize_t show_idle_count(struct device *dev,
 		idle_count = ACCESS_ONCE(idle->idle_count);
 		if (ACCESS_ONCE(idle->clock_idle_enter))
 			idle_count++;
-	} while ((sequence & 1) || (idle->sequence != sequence));
+	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
 	return sprintf(buf, "%llu\n", idle_count);
 }
 static DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
@@ -951,7 +951,7 @@ static ssize_t show_idle_time(struct device *dev,
 		idle_time = ACCESS_ONCE(idle->idle_time);
 		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
 		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
-	} while ((sequence & 1) || (idle->sequence != sequence));
+	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
 	idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0;
 	return sprintf(buf, "%llu\n", idle_time >> 12);
 }

arch/s390/kernel/vtime.c

@@ -190,7 +190,7 @@ cputime64_t s390_get_idle_time(int cpu)
 		sequence = ACCESS_ONCE(idle->sequence);
 		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
 		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
-	} while ((sequence & 1) || (idle->sequence != sequence));
+	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
 	return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0;
 }
 

arch/x86/kernel/ftrace.c

@@ -248,6 +248,15 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ret;
 }
 
+static int is_ftrace_caller(unsigned long ip)
+{
+	if (ip == (unsigned long)(&ftrace_call) ||
+		ip == (unsigned long)(&ftrace_regs_call))
+		return 1;
+
+	return 0;
+}
+
 /*
  * A breakpoint was added to the code address we are about to
  * modify, and this is the handle that will just skip over it.
@@ -257,10 +266,13 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
  */
 int ftrace_int3_handler(struct pt_regs *regs)
 {
+	unsigned long ip;
+
 	if (WARN_ON_ONCE(!regs))
 		return 0;
 
-	if (!ftrace_location(regs->ip - 1))
+	ip = regs->ip - 1;
+	if (!ftrace_location(ip) && !is_ftrace_caller(ip))
 		return 0;
 
 	regs->ip += MCOUNT_INSN_SIZE - 1;

arch/x86/kernel/microcode_amd.c

@@ -430,7 +430,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 		snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
 
 	if (request_firmware(&fw, (const char *)fw_name, device)) {
-		pr_err("failed to load file %s\n", fw_name);
+		pr_debug("failed to load file %s\n", fw_name);
 		goto out;
 	}
 

arch/x86/kernel/process.c

@@ -378,9 +378,9 @@ static void amd_e400_idle(void)
 		 * The switch back from broadcast mode needs to be
 		 * called with interrupts disabled.
 		 */
-		 local_irq_disable();
-		 clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
-		 local_irq_enable();
+		local_irq_disable();
+		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+		local_irq_enable();
 	} else
 		default_idle();
 }

arch/x86/kvm/emulate.c

@@ -4207,7 +4207,10 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
 	case OpMem8:
 		ctxt->memop.bytes = 1;
 		if (ctxt->memop.type == OP_REG) {
-			ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm, 1);
+			int highbyte_regs = ctxt->rex_prefix == 0;
+
+			ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm,
+					       highbyte_regs);
 			fetch_register_operand(&ctxt->memop);
 		}
 		goto mem_common;

block/blk-core.c

@@ -2229,6 +2229,7 @@ void blk_start_request(struct request *req)
 	if (unlikely(blk_bidi_rq(req)))
 		req->next_rq->resid_len = blk_rq_bytes(req->next_rq);
 
+	BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
 	blk_add_timer(req);
 }
 EXPORT_SYMBOL(blk_start_request);