Bladeren bron

Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
  powerpc: Fix hcall tracepoint recursion
  powerpc/numa: Fix bug in unmap_cpu_from_node
  powerpc/numa: Disable VPHN on dedicated processor partitions
  powerpc/numa: Add length when creating OF properties via VPHN
  powerpc/numa: Check for all VPHN changes
  powerpc/numa: Only use active VPHN count fields
  powerpc/pseries: Remove unnecessary variable initializations in numa.c
  powerpc/pseries: Fix brace placement in numa.c
  powerpc/pseries: Fix typo in VPHN comments
  powerpc: Fix some 6xx/7xxx CPU setup functions
  powerpc: Pass the right cpu_spec to ->setup_cpu() on 64-bit
  powerpc/book3e: Protect complex macro args in mmu-book3e.h
  powerpc: Fix pfn_valid() when memory starts at a non-zero address
Linus Torvalds 14 jaren geleden
bovenliggende
commit
eee4da2cef

+ 4 - 4
arch/powerpc/include/asm/mmu-book3e.h

@@ -40,8 +40,8 @@
 
 /* MAS registers bit definitions */
 
-#define MAS0_TLBSEL(x)		((x << 28) & 0x30000000)
-#define MAS0_ESEL(x)		((x << 16) & 0x0FFF0000)
+#define MAS0_TLBSEL(x)		(((x) << 28) & 0x30000000)
+#define MAS0_ESEL(x)		(((x) << 16) & 0x0FFF0000)
 #define MAS0_NV(x)		((x) & 0x00000FFF)
 #define MAS0_HES		0x00004000
 #define MAS0_WQ_ALLWAYS		0x00000000
@@ -50,12 +50,12 @@
 
 #define MAS1_VALID		0x80000000
 #define MAS1_IPROT		0x40000000
-#define MAS1_TID(x)		((x << 16) & 0x3FFF0000)
+#define MAS1_TID(x)		(((x) << 16) & 0x3FFF0000)
 #define MAS1_IND		0x00002000
 #define MAS1_TS			0x00001000
 #define MAS1_TSIZE_MASK		0x00000f80
 #define MAS1_TSIZE_SHIFT	7
-#define MAS1_TSIZE(x)		((x << MAS1_TSIZE_SHIFT) & MAS1_TSIZE_MASK)
+#define MAS1_TSIZE(x)		(((x) << MAS1_TSIZE_SHIFT) & MAS1_TSIZE_MASK)
 
 #define MAS2_EPN		0xFFFFF000
 #define MAS2_X0			0x00000040

+ 1 - 1
arch/powerpc/include/asm/page.h

@@ -101,7 +101,7 @@ extern phys_addr_t kernstart_addr;
 
 #ifdef CONFIG_FLATMEM
 #define ARCH_PFN_OFFSET		(MEMORY_START >> PAGE_SHIFT)
-#define pfn_valid(pfn)		((pfn) >= ARCH_PFN_OFFSET && (pfn) < (ARCH_PFN_OFFSET + max_mapnr))
+#define pfn_valid(pfn)		((pfn) >= ARCH_PFN_OFFSET && (pfn) < max_mapnr)
 #endif
 
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)

+ 20 - 20
arch/powerpc/kernel/cpu_setup_6xx.S

@@ -18,7 +18,7 @@
 #include <asm/mmu.h>
 
 _GLOBAL(__setup_cpu_603)
-	mflr	r4
+	mflr	r5
 BEGIN_MMU_FTR_SECTION
 	li	r10,0
 	mtspr	SPRN_SPRG_603_LRU,r10		/* init SW LRU tracking */
@@ -27,60 +27,60 @@ BEGIN_FTR_SECTION
 	bl	__init_fpu_registers
 END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE)
 	bl	setup_common_caches
-	mtlr	r4
+	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_604)
-	mflr	r4
+	mflr	r5
 	bl	setup_common_caches
 	bl	setup_604_hid0
-	mtlr	r4
+	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_750)
-	mflr	r4
+	mflr	r5
 	bl	__init_fpu_registers
 	bl	setup_common_caches
 	bl	setup_750_7400_hid0
-	mtlr	r4
+	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_750cx)
-	mflr	r4
+	mflr	r5
 	bl	__init_fpu_registers
 	bl	setup_common_caches
 	bl	setup_750_7400_hid0
 	bl	setup_750cx
-	mtlr	r4
+	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_750fx)
-	mflr	r4
+	mflr	r5
 	bl	__init_fpu_registers
 	bl	setup_common_caches
 	bl	setup_750_7400_hid0
 	bl	setup_750fx
-	mtlr	r4
+	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_7400)
-	mflr	r4
+	mflr	r5
 	bl	__init_fpu_registers
 	bl	setup_7400_workarounds
 	bl	setup_common_caches
 	bl	setup_750_7400_hid0
-	mtlr	r4
+	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_7410)
-	mflr	r4
+	mflr	r5
 	bl	__init_fpu_registers
 	bl	setup_7410_workarounds
 	bl	setup_common_caches
 	bl	setup_750_7400_hid0
 	li	r3,0
 	mtspr	SPRN_L2CR2,r3
-	mtlr	r4
+	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_745x)
-	mflr	r4
+	mflr	r5
 	bl	setup_common_caches
 	bl	setup_745x_specifics
-	mtlr	r4
+	mtlr	r5
 	blr
 
 /* Enable caches for 603's, 604, 750 & 7400 */
@@ -194,10 +194,10 @@ setup_750cx:
 	cror	4*cr0+eq,4*cr0+eq,4*cr1+eq
 	cror	4*cr0+eq,4*cr0+eq,4*cr2+eq
 	bnelr
-	lwz	r6,CPU_SPEC_FEATURES(r5)
+	lwz	r6,CPU_SPEC_FEATURES(r4)
 	li	r7,CPU_FTR_CAN_NAP
 	andc	r6,r6,r7
-	stw	r6,CPU_SPEC_FEATURES(r5)
+	stw	r6,CPU_SPEC_FEATURES(r4)
 	blr
 
 /* 750fx specific
@@ -225,12 +225,12 @@ BEGIN_FTR_SECTION
 	andis.	r11,r11,L3CR_L3E@h
 	beq	1f
 END_FTR_SECTION_IFSET(CPU_FTR_L3CR)
-	lwz	r6,CPU_SPEC_FEATURES(r5)
+	lwz	r6,CPU_SPEC_FEATURES(r4)
 	andi.	r0,r6,CPU_FTR_L3_DISABLE_NAP
 	beq	1f
 	li	r7,CPU_FTR_CAN_NAP
 	andc	r6,r6,r7
-	stw	r6,CPU_SPEC_FEATURES(r5)
+	stw	r6,CPU_SPEC_FEATURES(r4)
 1:
 	mfspr	r11,SPRN_HID0
 

+ 2 - 2
arch/powerpc/kernel/cputable.c

@@ -2076,8 +2076,8 @@ static void __init setup_cpu_spec(unsigned long offset, struct cpu_spec *s)
 	 * pointer on ppc64 and booke as we are running at 0 in real mode
 	 * on ppc64 and reloc_offset is always 0 on booke.
 	 */
-	if (s->cpu_setup) {
-		s->cpu_setup(offset, s);
+	if (t->cpu_setup) {
+		t->cpu_setup(offset, t);
 	}
 #endif /* CONFIG_PPC64 || CONFIG_BOOKE */
 }

+ 30 - 25
arch/powerpc/mm/numa.c

@@ -186,7 +186,7 @@ static void unmap_cpu_from_node(unsigned long cpu)
 	dbg("removing cpu %lu from node %d\n", cpu, node);
 
 	if (cpumask_test_cpu(cpu, node_to_cpumask_map[node])) {
-		cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
+		cpumask_clear_cpu(cpu, node_to_cpumask_map[node]);
 	} else {
 		printk(KERN_ERR "WARNING: cpu %lu not found in node %d\n",
 		       cpu, node);
@@ -1289,10 +1289,9 @@ u64 memory_hotplug_max(void)
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
-/* Vrtual Processor Home Node (VPHN) support */
+/* Virtual Processor Home Node (VPHN) support */
 #ifdef CONFIG_PPC_SPLPAR
-#define VPHN_NR_CHANGE_CTRS (8)
-static u8 vphn_cpu_change_counts[NR_CPUS][VPHN_NR_CHANGE_CTRS];
+static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS];
 static cpumask_t cpu_associativity_changes_mask;
 static int vphn_enabled;
 static void set_topology_timer(void);
@@ -1303,16 +1302,18 @@ static void set_topology_timer(void);
  */
 static void setup_cpu_associativity_change_counters(void)
 {
-	int cpu = 0;
+	int cpu;
+
+	/* The VPHN feature supports a maximum of 8 reference points */
+	BUILD_BUG_ON(MAX_DISTANCE_REF_POINTS > 8);
 
 	for_each_possible_cpu(cpu) {
-		int i = 0;
+		int i;
 		u8 *counts = vphn_cpu_change_counts[cpu];
 		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
 
-		for (i = 0; i < VPHN_NR_CHANGE_CTRS; i++) {
+		for (i = 0; i < distance_ref_points_depth; i++)
 			counts[i] = hypervisor_counts[i];
-		}
 	}
 }
 
@@ -1329,7 +1330,7 @@ static void setup_cpu_associativity_change_counters(void)
  */
 static int update_cpu_associativity_changes_mask(void)
 {
-	int cpu = 0, nr_cpus = 0;
+	int cpu, nr_cpus = 0;
 	cpumask_t *changes = &cpu_associativity_changes_mask;
 
 	cpumask_clear(changes);
@@ -1339,8 +1340,8 @@ static int update_cpu_associativity_changes_mask(void)
 		u8 *counts = vphn_cpu_change_counts[cpu];
 		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
 
-		for (i = 0; i < VPHN_NR_CHANGE_CTRS; i++) {
-			if (hypervisor_counts[i] > counts[i]) {
+		for (i = 0; i < distance_ref_points_depth; i++) {
+			if (hypervisor_counts[i] != counts[i]) {
 				counts[i] = hypervisor_counts[i];
 				changed = 1;
 			}
@@ -1354,8 +1355,11 @@ static int update_cpu_associativity_changes_mask(void)
 	return nr_cpus;
 }
 
-/* 6 64-bit registers unpacked into 12 32-bit associativity values */
-#define VPHN_ASSOC_BUFSIZE (6*sizeof(u64)/sizeof(u32))
+/*
+ * 6 64-bit registers unpacked into 12 32-bit associativity values. To form
+ * the complete property we have to add the length in the first cell.
+ */
+#define VPHN_ASSOC_BUFSIZE (6*sizeof(u64)/sizeof(u32) + 1)
 
 /*
  * Convert the associativity domain numbers returned from the hypervisor
@@ -1363,15 +1367,14 @@ static int update_cpu_associativity_changes_mask(void)
  */
 static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked)
 {
-	int i = 0;
-	int nr_assoc_doms = 0;
+	int i, nr_assoc_doms = 0;
 	const u16 *field = (const u16*) packed;
 
 #define VPHN_FIELD_UNUSED	(0xffff)
 #define VPHN_FIELD_MSB		(0x8000)
 #define VPHN_FIELD_MASK		(~VPHN_FIELD_MSB)
 
-	for (i = 0; i < VPHN_ASSOC_BUFSIZE; i++) {
+	for (i = 1; i < VPHN_ASSOC_BUFSIZE; i++) {
 		if (*field == VPHN_FIELD_UNUSED) {
 			/* All significant fields processed, and remaining
 			 * fields contain the reserved value of all 1's.
@@ -1379,14 +1382,12 @@ static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked)
 			 */
 			unpacked[i] = *((u32*)field);
 			field += 2;
-		}
-		else if (*field & VPHN_FIELD_MSB) {
+		} else if (*field & VPHN_FIELD_MSB) {
 			/* Data is in the lower 15 bits of this field */
 			unpacked[i] = *field & VPHN_FIELD_MASK;
 			field++;
 			nr_assoc_doms++;
-		}
-		else {
+		} else {
 			/* Data is in the lower 15 bits of this field
 			 * concatenated with the next 16 bit field
 			 */
@@ -1396,6 +1397,9 @@ static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked)
 		}
 	}
 
+	/* The first cell contains the length of the property */
+	unpacked[0] = nr_assoc_doms;
+
 	return nr_assoc_doms;
 }
 
@@ -1405,7 +1409,7 @@ static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked)
  */
 static long hcall_vphn(unsigned long cpu, unsigned int *associativity)
 {
-	long rc = 0;
+	long rc;
 	long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
 	u64 flags = 1;
 	int hwcpu = get_hard_smp_processor_id(cpu);
@@ -1419,7 +1423,7 @@ static long hcall_vphn(unsigned long cpu, unsigned int *associativity)
 static long vphn_get_associativity(unsigned long cpu,
 					unsigned int *associativity)
 {
-	long rc = 0;
+	long rc;
 
 	rc = hcall_vphn(cpu, associativity);
 
@@ -1445,9 +1449,9 @@ static long vphn_get_associativity(unsigned long cpu,
  */
 int arch_update_cpu_topology(void)
 {
-	int cpu = 0, nid = 0, old_nid = 0;
+	int cpu, nid, old_nid;
 	unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
-	struct sys_device *sysdev = NULL;
+	struct sys_device *sysdev;
 
 	for_each_cpu_mask(cpu, cpu_associativity_changes_mask) {
 		vphn_get_associativity(cpu, associativity);
@@ -1512,7 +1516,8 @@ int start_topology_update(void)
 {
 	int rc = 0;
 
-	if (firmware_has_feature(FW_FEATURE_VPHN)) {
+	if (firmware_has_feature(FW_FEATURE_VPHN) &&
+	    get_lppaca()->shared_proc) {
 		vphn_enabled = 1;
 		setup_cpu_associativity_change_counters();
 		init_timer_deferrable(&topology_timer);

+ 37 - 0
arch/powerpc/platforms/pseries/lpar.c

@@ -713,6 +713,13 @@ EXPORT_SYMBOL(arch_free_page);
 /* NB: reg/unreg are called while guarded with the tracepoints_mutex */
 extern long hcall_tracepoint_refcount;
 
+/* 
+ * Since the tracing code might execute hcalls we need to guard against
+ * recursion. One example of this are spinlocks calling H_YIELD on
+ * shared processor partitions.
+ */
+static DEFINE_PER_CPU(unsigned int, hcall_trace_depth);
+
 void hcall_tracepoint_regfunc(void)
 {
 	hcall_tracepoint_refcount++;
@@ -725,12 +732,42 @@ void hcall_tracepoint_unregfunc(void)
 
 void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
 {
+	unsigned long flags;
+	unsigned int *depth;
+
+	local_irq_save(flags);
+
+	depth = &__get_cpu_var(hcall_trace_depth);
+
+	if (*depth)
+		goto out;
+
+	(*depth)++;
 	trace_hcall_entry(opcode, args);
+	(*depth)--;
+
+out:
+	local_irq_restore(flags);
 }
 
 void __trace_hcall_exit(long opcode, unsigned long retval,
 			unsigned long *retbuf)
 {
+	unsigned long flags;
+	unsigned int *depth;
+
+	local_irq_save(flags);
+
+	depth = &__get_cpu_var(hcall_trace_depth);
+
+	if (*depth)
+		goto out;
+
+	(*depth)++;
 	trace_hcall_exit(opcode, retval, retbuf);
+	(*depth)--;
+
+out:
+	local_irq_restore(flags);
 }
 #endif