Commit d34696c2 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux 

Pull s390 fixes from Martin Schwidefsky:
 "Two patches to save some memory if CONFIG_NR_CPUS is large, a changed
  default for the use of compare-and-delay, and a couple of bug fixes"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
  s390/spinlock: disabled compare-and-delay by default
  s390/mm: align 64-bit PIE binaries to 4GB
  s390/cacheinfo: coding style changes
  s390/cacheinfo: fix shared cpu masks
  s390/smp: reduce size of struct pcpu
  s390/topology: convert cpu_topology array to per cpu variable
  s390/topology: delay initialization of topology cpu masks
  s390/vdso: fix clock_gettime for CLOCK_THREAD_CPUTIME_ID, -2 and -3
parents f9677375 61b0b016

arch/s390/include/asm/topology.h

+8 −16
Original line number Diff line number Diff line
@@ -18,15 +18,15 @@ struct cpu_topology_s390 { 
	cpumask_t book_mask;

};



extern struct cpu_topology_s390 cpu_topology[NR_CPUS];

DECLARE_PER_CPU(struct cpu_topology_s390, cpu_topology);



#define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)

#define topology_thread_id(cpu)			(cpu_topology[cpu].thread_id)

#define topology_thread_cpumask(cpu)		(&cpu_topology[cpu].thread_mask)

#define topology_core_id(cpu)			(cpu_topology[cpu].core_id)

#define topology_core_cpumask(cpu)		(&cpu_topology[cpu].core_mask)

#define topology_book_id(cpu)			(cpu_topology[cpu].book_id)

#define topology_book_cpumask(cpu)		(&cpu_topology[cpu].book_mask)

#define topology_physical_package_id(cpu) (per_cpu(cpu_topology, cpu).socket_id)

#define topology_thread_id(cpu)		  (per_cpu(cpu_topology, cpu).thread_id)

#define topology_thread_cpumask(cpu)	  (&per_cpu(cpu_topology, cpu).thread_mask)

#define topology_core_id(cpu)		  (per_cpu(cpu_topology, cpu).core_id)

#define topology_core_cpumask(cpu)	  (&per_cpu(cpu_topology, cpu).core_mask)

#define topology_book_id(cpu)		  (per_cpu(cpu_topology, cpu).book_id)

#define topology_book_cpumask(cpu)	  (&per_cpu(cpu_topology, cpu).book_mask)



#define mc_capable() 1
@@ -51,14 +51,6 @@ static inline void topology_expect_change(void) { } 
#define POLARIZATION_VM		(2)

#define POLARIZATION_VH		(3)



#ifdef CONFIG_SCHED_BOOK

void s390_init_cpu_topology(void);

#else

static inline void s390_init_cpu_topology(void)

{

};

#endif



#include <asm-generic/topology.h>



#endif /* _ASM_S390_TOPOLOGY_H */

arch/s390/kernel/cache.c

+7 −18
Original line number Diff line number Diff line
@@ -91,12 +91,9 @@ static inline enum cache_type get_cache_type(struct cache_info *ci, int level) 
{

	if (level >= CACHE_MAX_LEVEL)

		return CACHE_TYPE_NOCACHE;



	ci += level;



	if (ci->scope != CACHE_SCOPE_SHARED && ci->scope != CACHE_SCOPE_PRIVATE)

		return CACHE_TYPE_NOCACHE;



	return cache_type_map[ci->type];

}
@@ -111,23 +108,19 @@ static inline unsigned long ecag(int ai, int li, int ti) 
}



static void ci_leaf_init(struct cacheinfo *this_leaf, int private,

			 enum cache_type type, unsigned int level)

			 enum cache_type type, unsigned int level, int cpu)

{

	int ti, num_sets;

	int cpu = smp_processor_id();



	if (type == CACHE_TYPE_INST)

		ti = CACHE_TI_INSTRUCTION;

	else

		ti = CACHE_TI_UNIFIED;



	this_leaf->level = level + 1;

	this_leaf->type = type;

	this_leaf->coherency_line_size = ecag(EXTRACT_LINE_SIZE, level, ti);

	this_leaf->ways_of_associativity = ecag(EXTRACT_ASSOCIATIVITY,

						level, ti);

	this_leaf->ways_of_associativity = ecag(EXTRACT_ASSOCIATIVITY, level, ti);

	this_leaf->size = ecag(EXTRACT_SIZE, level, ti);



	num_sets = this_leaf->size / this_leaf->coherency_line_size;

	num_sets /= this_leaf->ways_of_associativity;

	this_leaf->number_of_sets = num_sets;
@@ -145,7 +138,6 @@ int init_cache_level(unsigned int cpu) 


	if (!this_cpu_ci)

		return -EINVAL;



	ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0);

	do {

		ctype = get_cache_type(&ct.ci[0], level);
@@ -154,34 +146,31 @@ int init_cache_level(unsigned int cpu) 
		/* Separate instruction and data caches */

		leaves += (ctype == CACHE_TYPE_SEPARATE) ? 2 : 1;

	} while (++level < CACHE_MAX_LEVEL);



	this_cpu_ci->num_levels = level;

	this_cpu_ci->num_leaves = leaves;



	return 0;

}



int populate_cache_leaves(unsigned int cpu)

{

	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);

	struct cacheinfo *this_leaf = this_cpu_ci->info_list;

	unsigned int level, idx, pvt;

	union cache_topology ct;

	enum cache_type ctype;

	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);

	struct cacheinfo *this_leaf = this_cpu_ci->info_list;



	ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0);

	for (idx = 0, level = 0; level < this_cpu_ci->num_levels &&

	     idx < this_cpu_ci->num_leaves; idx++, level++) {

		if (!this_leaf)

			return -EINVAL;



		pvt = (ct.ci[level].scope == CACHE_SCOPE_PRIVATE) ? 1 : 0;

		ctype = get_cache_type(&ct.ci[0], level);

		if (ctype == CACHE_TYPE_SEPARATE) {

			ci_leaf_init(this_leaf++, pvt, CACHE_TYPE_DATA, level);

			ci_leaf_init(this_leaf++, pvt, CACHE_TYPE_INST, level);

			ci_leaf_init(this_leaf++, pvt, CACHE_TYPE_DATA, level, cpu);

			ci_leaf_init(this_leaf++, pvt, CACHE_TYPE_INST, level, cpu);

		} else {

			ci_leaf_init(this_leaf++, pvt, ctype, level);

			ci_leaf_init(this_leaf++, pvt, ctype, level, cpu);

		}

	}

	return 0;

arch/s390/kernel/early.c

+7 −5
Original line number Diff line number Diff line
@@ -393,17 +393,19 @@ static __init void detect_machine_facilities(void) 
		S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_LC;

	if (test_facility(129))

		S390_lowcore.machine_flags |= MACHINE_FLAG_VX;

	if (test_facility(128))

		S390_lowcore.machine_flags |= MACHINE_FLAG_CAD;

#endif

}



static int __init nocad_setup(char *str)

static int __init cad_setup(char *str)

{

	S390_lowcore.machine_flags &= ~MACHINE_FLAG_CAD;

	int val;



	get_option(&str, &val);

	if (val && test_facility(128))

		S390_lowcore.machine_flags |= MACHINE_FLAG_CAD;

	return 0;

}

early_param("nocad", nocad_setup);

early_param("cad", cad_setup);



static int __init cad_init(void)

{

arch/s390/kernel/setup.c

+0 −1
Original line number Diff line number Diff line
@@ -909,7 +909,6 @@ void __init setup_arch(char **cmdline_p) 
	setup_lowcore();

	smp_fill_possible_mask();

        cpu_init();

	s390_init_cpu_topology();



	/*

	 * Setup capabilities (ELF_HWCAP & ELF_PLATFORM).

arch/s390/kernel/smp.c

+27 −27
Original line number Diff line number Diff line
@@ -59,14 +59,13 @@ enum { 
	CPU_STATE_CONFIGURED,

};



static DEFINE_PER_CPU(struct cpu *, cpu_device);



struct pcpu {

	struct cpu *cpu;

	struct _lowcore *lowcore;	/* lowcore page(s) for the cpu */

	unsigned long async_stack;	/* async stack for the cpu */

	unsigned long panic_stack;	/* panic stack for the cpu */

	unsigned long ec_mask;		/* bit mask for ec_xxx functions */

	int state;			/* physical cpu state */

	int polarization;		/* physical polarization */

	signed char state;		/* physical cpu state */

	signed char polarization;	/* physical polarization */

	u16 address;			/* physical cpu address */

};
@@ -173,25 +172,30 @@ static void pcpu_ec_call(struct pcpu *pcpu, int ec_bit) 
	pcpu_sigp_retry(pcpu, order, 0);

}



#define ASYNC_FRAME_OFFSET (ASYNC_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE)

#define PANIC_FRAME_OFFSET (PAGE_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE)



static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)

{

	unsigned long async_stack, panic_stack;

	struct _lowcore *lc;



	if (pcpu != &pcpu_devices[0]) {

		pcpu->lowcore =	(struct _lowcore *)

			__get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER);

		pcpu->async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER);

		pcpu->panic_stack = __get_free_page(GFP_KERNEL);

		if (!pcpu->lowcore || !pcpu->panic_stack || !pcpu->async_stack)

		async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER);

		panic_stack = __get_free_page(GFP_KERNEL);

		if (!pcpu->lowcore || !panic_stack || !async_stack)

			goto out;

	} else {

		async_stack = pcpu->lowcore->async_stack - ASYNC_FRAME_OFFSET;

		panic_stack = pcpu->lowcore->panic_stack - PANIC_FRAME_OFFSET;

	}

	lc = pcpu->lowcore;

	memcpy(lc, &S390_lowcore, 512);

	memset((char *) lc + 512, 0, sizeof(*lc) - 512);

	lc->async_stack = pcpu->async_stack + ASYNC_SIZE

		- STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);

	lc->panic_stack = pcpu->panic_stack + PAGE_SIZE

		- STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);

	lc->async_stack = async_stack + ASYNC_FRAME_OFFSET;

	lc->panic_stack = panic_stack + PANIC_FRAME_OFFSET;

	lc->cpu_nr = cpu;

	lc->spinlock_lockval = arch_spin_lockval(cpu);

#ifndef CONFIG_64BIT
@@ -212,8 +216,8 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) 
	return 0;

out:

	if (pcpu != &pcpu_devices[0]) {

		free_page(pcpu->panic_stack);

		free_pages(pcpu->async_stack, ASYNC_ORDER);

		free_page(panic_stack);

		free_pages(async_stack, ASYNC_ORDER);

		free_pages((unsigned long) pcpu->lowcore, LC_ORDER);

	}

	return -ENOMEM;
@@ -235,12 +239,12 @@ static void pcpu_free_lowcore(struct pcpu *pcpu) 
#else

	vdso_free_per_cpu(pcpu->lowcore);

#endif

	if (pcpu != &pcpu_devices[0]) {

		free_page(pcpu->panic_stack);

		free_pages(pcpu->async_stack, ASYNC_ORDER);

	if (pcpu == &pcpu_devices[0])

		return;

	free_page(pcpu->lowcore->panic_stack-PANIC_FRAME_OFFSET);

	free_pages(pcpu->lowcore->async_stack-ASYNC_FRAME_OFFSET, ASYNC_ORDER);

	free_pages((unsigned long) pcpu->lowcore, LC_ORDER);

}

}



#endif /* CONFIG_HOTPLUG_CPU */
@@ -366,7 +370,8 @@ void smp_call_online_cpu(void (*func)(void *), void *data) 
void smp_call_ipl_cpu(void (*func)(void *), void *data)

{

	pcpu_delegate(&pcpu_devices[0], func, data,

		      pcpu_devices->panic_stack + PAGE_SIZE);

		      pcpu_devices->lowcore->panic_stack -

		      PANIC_FRAME_OFFSET + PAGE_SIZE);

}



int smp_find_processor_id(u16 address)
@@ -935,10 +940,6 @@ void __init smp_prepare_boot_cpu(void) 
	pcpu->state = CPU_STATE_CONFIGURED;

	pcpu->address = stap();

	pcpu->lowcore = (struct _lowcore *)(unsigned long) store_prefix();

	pcpu->async_stack = S390_lowcore.async_stack - ASYNC_SIZE

		+ STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);

	pcpu->panic_stack = S390_lowcore.panic_stack - PAGE_SIZE

		+ STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);

	S390_lowcore.percpu_offset = __per_cpu_offset[0];

	smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN);

	set_cpu_present(0, true);
@@ -1078,8 +1079,7 @@ static int smp_cpu_notify(struct notifier_block *self, unsigned long action, 
			  void *hcpu)

{

	unsigned int cpu = (unsigned int)(long)hcpu;

	struct cpu *c = pcpu_devices[cpu].cpu;

	struct device *s = &c->dev;

	struct device *s = &per_cpu(cpu_device, cpu)->dev;

	int err = 0;



	switch (action & ~CPU_TASKS_FROZEN) {
@@ -1102,7 +1102,7 @@ static int smp_add_present_cpu(int cpu) 
	c = kzalloc(sizeof(*c), GFP_KERNEL);

	if (!c)

		return -ENOMEM;

	pcpu_devices[cpu].cpu = c;

	per_cpu(cpu_device, cpu) = c;

	s = &c->dev;

	c->hotpluggable = 1;

	rc = register_cpu(c, cpu);

CRA Git | Maintained and supported by SUSTech CRA and CCSE