Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus

Pull MIPS updates from Ralf Baechle:
 "This is the main pull request for MIPS for Linux 4.1.  Most
  noteworthy:

   - Add more Octeon-optimized crypto functions
   - Octeon crypto preemption and locking fixes
   - Little endian support for Octeon
   - Use correct CSR to soft reset Octeons
   - Support LEDs on the Octeon-based DSR-1000N
   - Fix PCI interrupt mapping for the Octeon-based DSR-1000N
   - Mark prom_free_prom_memory() as __init for a number of systems
   - Support for Imagination's Pistachio SOC.  This includes arch and
     CLK bits.  I'd like to merge pinctrl bits later
   - Improve parallelism of csum_partial for certain pipelines
   - Organize DTB files in subdirs like other architectures
   - Implement read_sched_clock for all MIPS platforms other than
     Octeon
   - Massive series of 38 fixes and cleanups for the FPU emulator /
     kernel
   - Further FPU remulator work to support new features.  This sits on a
     separate branch which also has been pulled into the 4.1 KVM branch
   - Clean up and fixes for the SEAD3 eval board; remove unused file
   - Various updates for Netlogic platforms
   - A number of small updates for Loongson 3 platforms
   - Increase the memory limit for ATH79 platforms to 256MB
   - A fair number of fixes and updates for BCM47xx platforms
   - Finish the implementation of XPA support
   - MIPS FDC support.  No, not floppy controller but Fast Debug Channel :)
   - Detect the R16000 used in SGI legacy platforms
   - Fix Kconfig dependencies for the SSB bus support"

* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: (265 commits)
  MIPS: Makefile: Fix MIPS ASE detection code
  MIPS: asm: elf: Set O32 default FPU flags
  MIPS: BCM47XX: Fix detecting Microsoft MN-700 & Asus WL500G
  MIPS: Kconfig: Disable SMP/CPS for 64-bit
  MIPS: Hibernate: flush TLB entries earlier
  MIPS: smp-cps: cpu_set FPU mask if FPU present
  MIPS: lose_fpu(): Disable FPU when MSA enabled
  MIPS: ralink: add missing symbol for RALINK_ILL_ACC
  MIPS: ralink: Fix bad config symbol in PCI makefile.
  SSB: fix Kconfig dependencies
  MIPS: Malta: Detect and fix bad memsize values
  Revert "MIPS: Avoid pipeline stalls on some MIPS32R2 cores."
  MIPS: Octeon: Delete override of cpu_has_mips_r2_exec_hazard.
  MIPS: Fix cpu_has_mips_r2_exec_hazard.
  MIPS: kernel: entry.S: Set correct ISA level for mips_ihb
  MIPS: asm: spinlock: Fix addiu instruction for R10000_LLSC_WAR case
  MIPS: r4kcache: Use correct base register for MIPS R6 cache flushes
  MIPS: Kconfig: Fix typo for the r2-to-r6 emulator kernel parameter
  MIPS: unaligned: Fix regular load/store instruction emulation for EVA
  MIPS: unaligned: Surround load/store macros in do {} while statements
  ...

4 files changed, 40 insertions, 18 deletions

diff --git a/arch/mips/netlogic/common/irq.c b/arch/mips/netlogic/common/irq.c
index c100b9afa0ab..5f5d18b0e94d 100644
--- a/arch/mips/netlogic/common/irq.c
+++ b/arch/mips/netlogic/common/irq.c
@@ -230,16 +230,16 @@ static void nlm_init_node_irqs(int node)
 	}
 }
 
-void nlm_smp_irq_init(int hwcpuid)
+void nlm_smp_irq_init(int hwtid)
 {
-	int node, cpu;
+	int cpu, node;
 
-	node = nlm_cpuid_to_node(hwcpuid);
-	cpu  = hwcpuid % nlm_threads_per_node();
+	cpu = hwtid % nlm_threads_per_node();
+	node = hwtid / nlm_threads_per_node();
 
 	if (cpu == 0 && node != 0)
 		nlm_init_node_irqs(node);
-	write_c0_eimr(nlm_current_node()->irqmask);
+	write_c0_eimr(nlm_get_node(node)->irqmask);
 }
 
 asmlinkage void plat_irq_dispatch(void)
diff --git a/arch/mips/netlogic/common/reset.S b/arch/mips/netlogic/common/reset.S
index 701c4bcb9e47..edbab9b8691f 100644
--- a/arch/mips/netlogic/common/reset.S
+++ b/arch/mips/netlogic/common/reset.S
@@ -60,7 +60,7 @@
 	li	t0, LSU_DEFEATURE
 	mfcr	t1, t0
 
-	lui	t2, 0xc080	/* SUE, Enable Unaligned Access, L2HPE */
+	lui	t2, 0x4080	/* Enable Unaligned Access, L2HPE */
 	or	t1, t1, t2
 	mtcr	t1, t0
 
@@ -235,6 +235,26 @@ EXPORT(nlm_boot_siblings)
 	mfc0	v0, CP0_EBASE, 1
 	andi	v0, 0x3ff		/* v0 <- node/core */
 
+	/*
+	 * Errata: to avoid potential live lock, setup IFU_BRUB_RESERVE
+	 * when running 4 threads per core
+	 */
+	andi	v1, v0, 0x3             /* v1 <- thread id */
+	bnez	v1, 2f
+	nop
+
+	/* thread 0 of each core. */
+	li	t0, CKSEG1ADDR(RESET_DATA_PHYS)
+	lw	t1, BOOT_THREAD_MODE(t0)        /* t1 <- thread mode */
+	subu	t1, 0x3				/* 4-thread per core mode? */
+	bnez	t1, 2f
+	nop
+
+	li	t0, IFU_BRUB_RESERVE
+	li	t1, 0x55
+	mtcr	t1, t0
+	_ehb
+2:
 	beqz	v0, 4f		/* boot cpu (cpuid == 0)? */
 	nop
 
diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c
index e743bdd6e20c..dc3e327fbbac 100644
--- a/arch/mips/netlogic/common/smp.c
+++ b/arch/mips/netlogic/common/smp.c
@@ -59,17 +59,17 @@
 
 void nlm_send_ipi_single(int logical_cpu, unsigned int action)
 {
-	int cpu, node;
+	unsigned int hwtid;
 	uint64_t picbase;
 
-	cpu = cpu_logical_map(logical_cpu);
-	node = nlm_cpuid_to_node(cpu);
-	picbase = nlm_get_node(node)->picbase;
+	/* node id is part of hwtid, and needed for send_ipi */
+	hwtid = cpu_logical_map(logical_cpu);
+	picbase = nlm_get_node(nlm_hwtid_to_node(hwtid))->picbase;
 
 	if (action & SMP_CALL_FUNCTION)
-		nlm_pic_send_ipi(picbase, cpu, IRQ_IPI_SMP_FUNCTION, 0);
+		nlm_pic_send_ipi(picbase, hwtid, IRQ_IPI_SMP_FUNCTION, 0);
 	if (action & SMP_RESCHEDULE_YOURSELF)
-		nlm_pic_send_ipi(picbase, cpu, IRQ_IPI_SMP_RESCHEDULE, 0);
+		nlm_pic_send_ipi(picbase, hwtid, IRQ_IPI_SMP_RESCHEDULE, 0);
 }
 
 void nlm_send_ipi_mask(const struct cpumask *mask, unsigned int action)
@@ -120,6 +120,7 @@ static void nlm_init_secondary(void)
 
 	hwtid = hard_smp_processor_id();
 	current_cpu_data.core = hwtid / NLM_THREADS_PER_CORE;
+	current_cpu_data.package = nlm_nodeid();
 	nlm_percpu_init(hwtid);
 	nlm_smp_irq_init(hwtid);
 }
@@ -145,16 +146,18 @@ static cpumask_t phys_cpu_present_mask;
 
 void nlm_boot_secondary(int logical_cpu, struct task_struct *idle)
 {
-	int cpu, node;
+	uint64_t picbase;
+	int hwtid;
+
+	hwtid = cpu_logical_map(logical_cpu);
+	picbase = nlm_get_node(nlm_hwtid_to_node(hwtid))->picbase;
 
-	cpu = cpu_logical_map(logical_cpu);
-	node = nlm_cpuid_to_node(logical_cpu);
 	nlm_next_sp = (unsigned long)__KSTK_TOS(idle);
 	nlm_next_gp = (unsigned long)task_thread_info(idle);
 
 	/* barrier for sp/gp store above */
 	__sync();
-	nlm_pic_send_ipi(nlm_get_node(node)->picbase, cpu, 1, 1);  /* NMI */
+	nlm_pic_send_ipi(picbase, hwtid, 1, 1);  /* NMI */
 }
 
 void __init nlm_smp_setup(void)
@@ -182,7 +185,7 @@ void __init nlm_smp_setup(void)
 			__cpu_number_map[i] = num_cpus;
 			__cpu_logical_map[num_cpus] = i;
 			set_cpu_possible(num_cpus, true);
-			node = nlm_cpuid_to_node(i);
+			node = nlm_hwtid_to_node(i);
 			cpumask_set_cpu(num_cpus, &nlm_get_node(node)->cpumask);
 			++num_cpus;
 		}
diff --git a/arch/mips/netlogic/common/time.c b/arch/mips/netlogic/common/time.c
index 0c0a1a606f73..5873c83e65be 100644
--- a/arch/mips/netlogic/common/time.c
+++ b/arch/mips/netlogic/common/time.c
@@ -40,7 +40,6 @@
 #include <asm/netlogic/interrupt.h>
 #include <asm/netlogic/common.h>
 #include <asm/netlogic/haldefs.h>
-#include <asm/netlogic/common.h>
 
 #if defined(CONFIG_CPU_XLP)
 #include <asm/netlogic/xlp-hal/iomap.h>