linux_dsm_epyc7002/arch/x86/platform/uv/uv_time.c

417 lines
10 KiB
C
Raw Normal View History

/*
* SGI RTC clock/timer routines.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Copyright (c) 2009-2013 Silicon Graphics, Inc. All Rights Reserved.
* Copyright (c) Dimitri Sivanich
*/
#include <linux/clockchips.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/slab.h>
#include <asm/uv/uv_mmrs.h>
#include <asm/uv/uv_hub.h>
#include <asm/uv/bios.h>
#include <asm/uv/uv.h>
#include <asm/apic.h>
#include <asm/cpu.h>
#define RTC_NAME "sgi_rtc"
static u64 uv_read_rtc(struct clocksource *cs);
static int uv_rtc_next_event(unsigned long, struct clock_event_device *);
static int uv_rtc_shutdown(struct clock_event_device *evt);
static struct clocksource clocksource_uv = {
.name = RTC_NAME,
.rating = 299,
.read = uv_read_rtc,
.mask = (u64)UVH_RTC_REAL_TIME_CLOCK_MASK,
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
static struct clock_event_device clock_event_device_uv = {
.name = RTC_NAME,
.features = CLOCK_EVT_FEAT_ONESHOT,
.shift = 20,
.rating = 400,
.irq = -1,
.set_next_event = uv_rtc_next_event,
.set_state_shutdown = uv_rtc_shutdown,
.event_handler = NULL,
};
static DEFINE_PER_CPU(struct clock_event_device, cpu_ced);
/* There is one of these allocated per node */
struct uv_rtc_timer_head {
spinlock_t lock;
/* next cpu waiting for timer, local node relative: */
int next_cpu;
/* number of cpus on this node: */
int ncpus;
struct {
int lcpu; /* systemwide logical cpu number */
u64 expires; /* next timer expiration for this cpu */
} cpu[1];
};
/*
* Access to uv_rtc_timer_head via blade id.
*/
static struct uv_rtc_timer_head **blade_info __read_mostly;
static int uv_rtc_evt_enable;
/*
* Hardware interface routines
*/
/* Send IPIs to another node */
static void uv_rtc_send_IPI(int cpu)
{
unsigned long apicid, val;
int pnode;
apicid = cpu_physical_id(cpu);
pnode = uv_apicid_to_pnode(apicid);
apicid |= uv_apicid_hibits;
val = (1UL << UVH_IPI_INT_SEND_SHFT) |
(apicid << UVH_IPI_INT_APIC_ID_SHFT) |
(X86_PLATFORM_IPI_VECTOR << UVH_IPI_INT_VECTOR_SHFT);
uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
}
/* Check for an RTC interrupt pending */
static int uv_intr_pending(int pnode)
{
if (is_uv1_hub())
return uv_read_global_mmr64(pnode, UVH_EVENT_OCCURRED0) &
UV1H_EVENT_OCCURRED0_RTC1_MASK;
else if (is_uvx_hub())
return uv_read_global_mmr64(pnode, UVXH_EVENT_OCCURRED2) &
UVXH_EVENT_OCCURRED2_RTC_1_MASK;
return 0;
}
/* Setup interrupt and return non-zero if early expiration occurred. */
static int uv_setup_intr(int cpu, u64 expires)
{
u64 val;
unsigned long apicid = cpu_physical_id(cpu) | uv_apicid_hibits;
int pnode = uv_cpu_to_pnode(cpu);
uv_write_global_mmr64(pnode, UVH_RTC1_INT_CONFIG,
UVH_RTC1_INT_CONFIG_M_MASK);
uv_write_global_mmr64(pnode, UVH_INT_CMPB, -1L);
if (is_uv1_hub())
uv_write_global_mmr64(pnode, UVH_EVENT_OCCURRED0_ALIAS,
UV1H_EVENT_OCCURRED0_RTC1_MASK);
else
uv_write_global_mmr64(pnode, UVXH_EVENT_OCCURRED2_ALIAS,
UVXH_EVENT_OCCURRED2_RTC_1_MASK);
val = (X86_PLATFORM_IPI_VECTOR << UVH_RTC1_INT_CONFIG_VECTOR_SHFT) |
((u64)apicid << UVH_RTC1_INT_CONFIG_APIC_ID_SHFT);
/* Set configuration */
uv_write_global_mmr64(pnode, UVH_RTC1_INT_CONFIG, val);
/* Initialize comparator value */
uv_write_global_mmr64(pnode, UVH_INT_CMPB, expires);
if (uv_read_rtc(NULL) <= expires)
return 0;
return !uv_intr_pending(pnode);
}
/*
* Per-cpu timer tracking routines
*/
static __init void uv_rtc_deallocate_timers(void)
{
int bid;
for_each_possible_blade(bid) {
kfree(blade_info[bid]);
}
kfree(blade_info);
}
/* Allocate per-node list of cpu timer expiration times. */
static __init int uv_rtc_allocate_timers(void)
{
int cpu;
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 04:03:40 +07:00
blade_info = kcalloc(uv_possible_blades, sizeof(void *), GFP_KERNEL);
if (!blade_info)
return -ENOMEM;
for_each_present_cpu(cpu) {
int nid = cpu_to_node(cpu);
int bid = uv_cpu_to_blade_id(cpu);
int bcpu = uv_cpu_blade_processor_id(cpu);
struct uv_rtc_timer_head *head = blade_info[bid];
if (!head) {
head = kmalloc_node(sizeof(struct uv_rtc_timer_head) +
(uv_blade_nr_possible_cpus(bid) *
2 * sizeof(u64)),
GFP_KERNEL, nid);
if (!head) {
uv_rtc_deallocate_timers();
return -ENOMEM;
}
spin_lock_init(&head->lock);
head->ncpus = uv_blade_nr_possible_cpus(bid);
head->next_cpu = -1;
blade_info[bid] = head;
}
head->cpu[bcpu].lcpu = cpu;
head->cpu[bcpu].expires = ULLONG_MAX;
}
return 0;
}
/* Find and set the next expiring timer. */
static void uv_rtc_find_next_timer(struct uv_rtc_timer_head *head, int pnode)
{
u64 lowest = ULLONG_MAX;
int c, bcpu = -1;
head->next_cpu = -1;
for (c = 0; c < head->ncpus; c++) {
u64 exp = head->cpu[c].expires;
if (exp < lowest) {
bcpu = c;
lowest = exp;
}
}
if (bcpu >= 0) {
head->next_cpu = bcpu;
c = head->cpu[bcpu].lcpu;
if (uv_setup_intr(c, lowest))
/* If we didn't set it up in time, trigger */
uv_rtc_send_IPI(c);
} else {
uv_write_global_mmr64(pnode, UVH_RTC1_INT_CONFIG,
UVH_RTC1_INT_CONFIG_M_MASK);
}
}
/*
* Set expiration time for current cpu.
*
* Returns 1 if we missed the expiration time.
*/
static int uv_rtc_set_timer(int cpu, u64 expires)
{
int pnode = uv_cpu_to_pnode(cpu);
int bid = uv_cpu_to_blade_id(cpu);
struct uv_rtc_timer_head *head = blade_info[bid];
int bcpu = uv_cpu_blade_processor_id(cpu);
u64 *t = &head->cpu[bcpu].expires;
unsigned long flags;
int next_cpu;
spin_lock_irqsave(&head->lock, flags);
next_cpu = head->next_cpu;
*t = expires;
/* Will this one be next to go off? */
if (next_cpu < 0 || bcpu == next_cpu ||
expires < head->cpu[next_cpu].expires) {
head->next_cpu = bcpu;
if (uv_setup_intr(cpu, expires)) {
*t = ULLONG_MAX;
uv_rtc_find_next_timer(head, pnode);
spin_unlock_irqrestore(&head->lock, flags);
return -ETIME;
}
}
spin_unlock_irqrestore(&head->lock, flags);
return 0;
}
/*
* Unset expiration time for current cpu.
*
* Returns 1 if this timer was pending.
*/
static int uv_rtc_unset_timer(int cpu, int force)
{
int pnode = uv_cpu_to_pnode(cpu);
int bid = uv_cpu_to_blade_id(cpu);
struct uv_rtc_timer_head *head = blade_info[bid];
int bcpu = uv_cpu_blade_processor_id(cpu);
u64 *t = &head->cpu[bcpu].expires;
unsigned long flags;
int rc = 0;
spin_lock_irqsave(&head->lock, flags);
if ((head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) || force)
rc = 1;
if (rc) {
*t = ULLONG_MAX;
/* Was the hardware setup for this timer? */
if (head->next_cpu == bcpu)
uv_rtc_find_next_timer(head, pnode);
}
spin_unlock_irqrestore(&head->lock, flags);
return rc;
}
/*
* Kernel interface routines.
*/
/*
* Read the RTC.
*
* Starting with HUB rev 2.0, the UV RTC register is replicated across all
* cachelines of it's own page. This allows faster simultaneous reads
* from a given socket.
*/
static u64 uv_read_rtc(struct clocksource *cs)
{
unsigned long offset;
if (uv_get_min_hub_revision_id() == 1)
offset = 0;
else
offset = (uv_blade_processor_id() * L1_CACHE_BYTES) % PAGE_SIZE;
return (u64)uv_read_local_mmr(UVH_RTC | offset);
}
/*
* Program the next event, relative to now
*/
static int uv_rtc_next_event(unsigned long delta,
struct clock_event_device *ced)
{
int ced_cpu = cpumask_first(ced->cpumask);
return uv_rtc_set_timer(ced_cpu, delta + uv_read_rtc(NULL));
}
/*
* Shutdown the RTC timer
*/
static int uv_rtc_shutdown(struct clock_event_device *evt)
{
int ced_cpu = cpumask_first(evt->cpumask);
uv_rtc_unset_timer(ced_cpu, 1);
return 0;
}
static void uv_rtc_interrupt(void)
{
int cpu = smp_processor_id();
struct clock_event_device *ced = &per_cpu(cpu_ced, cpu);
if (!ced || !ced->event_handler)
return;
if (uv_rtc_unset_timer(cpu, 0) != 1)
return;
ced->event_handler(ced);
}
static int __init uv_enable_evt_rtc(char *str)
{
uv_rtc_evt_enable = 1;
return 1;
}
__setup("uvrtcevt", uv_enable_evt_rtc);
static __init void uv_rtc_register_clockevents(struct work_struct *dummy)
{
x86: Replace __get_cpu_var uses __get_cpu_var() is used for multiple purposes in the kernel source. One of them is address calculation via the form &__get_cpu_var(x). This calculates the address for the instance of the percpu variable of the current processor based on an offset. Other use cases are for storing and retrieving data from the current processors percpu area. __get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment. __get_cpu_var() is defined as : #define __get_cpu_var(var) (*this_cpu_ptr(&(var))) __get_cpu_var() always only does an address determination. However, store and retrieve operations could use a segment prefix (or global register on other platforms) to avoid the address calculation. this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use optimized assembly code to read and write per cpu variables. This patch converts __get_cpu_var into either an explicit address calculation using this_cpu_ptr() or into a use of this_cpu operations that use the offset. Thereby address calculations are avoided and less registers are used when code is generated. Transformations done to __get_cpu_var() 1. Determine the address of the percpu instance of the current processor. DEFINE_PER_CPU(int, y); int *x = &__get_cpu_var(y); Converts to int *x = this_cpu_ptr(&y); 2. Same as #1 but this time an array structure is involved. DEFINE_PER_CPU(int, y[20]); int *x = __get_cpu_var(y); Converts to int *x = this_cpu_ptr(y); 3. Retrieve the content of the current processors instance of a per cpu variable. DEFINE_PER_CPU(int, y); int x = __get_cpu_var(y) Converts to int x = __this_cpu_read(y); 4. Retrieve the content of a percpu struct DEFINE_PER_CPU(struct mystruct, y); struct mystruct x = __get_cpu_var(y); Converts to memcpy(&x, this_cpu_ptr(&y), sizeof(x)); 5. Assignment to a per cpu variable DEFINE_PER_CPU(int, y) __get_cpu_var(y) = x; Converts to __this_cpu_write(y, x); 6. Increment/Decrement etc of a per cpu variable DEFINE_PER_CPU(int, y); __get_cpu_var(y)++ Converts to __this_cpu_inc(y) Cc: Thomas Gleixner <tglx@linutronix.de> Cc: x86@kernel.org Acked-by: H. Peter Anvin <hpa@linux.intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2014-08-18 00:30:40 +07:00
struct clock_event_device *ced = this_cpu_ptr(&cpu_ced);
*ced = clock_event_device_uv;
ced->cpumask = cpumask_of(smp_processor_id());
clockevents_register_device(ced);
}
static __init int uv_rtc_setup_clock(void)
{
int rc;
if (!is_uv_system())
return -ENODEV;
rc = clocksource_register_hz(&clocksource_uv, sn_rtc_cycles_per_second);
if (rc)
printk(KERN_INFO "UV RTC clocksource failed rc %d\n", rc);
else
printk(KERN_INFO "UV RTC clocksource registered freq %lu MHz\n",
sn_rtc_cycles_per_second/(unsigned long)1E6);
if (rc || !uv_rtc_evt_enable || x86_platform_ipi_callback)
return rc;
/* Setup and register clockevents */
rc = uv_rtc_allocate_timers();
if (rc)
goto error;
x86_platform_ipi_callback = uv_rtc_interrupt;
clock_event_device_uv.mult = div_sc(sn_rtc_cycles_per_second,
NSEC_PER_SEC, clock_event_device_uv.shift);
clock_event_device_uv.min_delta_ns = NSEC_PER_SEC /
sn_rtc_cycles_per_second;
x86/uv/time: Set ->min_delta_ticks and ->max_delta_ticks In preparation for making the clockevents core NTP correction aware, all clockevent device drivers must set ->min_delta_ticks and ->max_delta_ticks rather than ->min_delta_ns and ->max_delta_ns: a clockevent device's rate is going to change dynamically and thus, the ratio of ns to ticks ceases to stay invariant. Currently, the x86's uv rtc clockevent device is initialized as follows: clock_event_device_uv.min_delta_ns = NSEC_PER_SEC / sn_rtc_cycles_per_second; clock_event_device_uv.max_delta_ns = clocksource_uv.mask * (NSEC_PER_SEC / sn_rtc_cycles_per_second); This translates to a ->min_delta_ticks value of 1 and a ->max_delta_ticks value of clocksource_uv.mask. Initialize ->min_delta_ticks and ->max_delta_ticks with these values respectively. This patch alone doesn't introduce any change in functionality as the clockevents core still looks exclusively at the (untouched) ->min_delta_ns and ->max_delta_ns. As soon as this has changed, a followup patch will purge the initialization of ->min_delta_ns and ->max_delta_ns from this driver. Cc: Ingo Molnar <mingo@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Richard Cochran <richardcochran@gmail.com> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Stephen Boyd <sboyd@codeaurora.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Cc: Mike Travis <travis@sgi.com> Cc: Dimitri Sivanich <sivanich@sgi.com> Signed-off-by: Nicolai Stange <nicstange@gmail.com> Signed-off-by: John Stultz <john.stultz@linaro.org>
2017-03-31 03:04:58 +07:00
clock_event_device_uv.min_delta_ticks = 1;
clock_event_device_uv.max_delta_ns = clocksource_uv.mask *
(NSEC_PER_SEC / sn_rtc_cycles_per_second);
x86/uv/time: Set ->min_delta_ticks and ->max_delta_ticks In preparation for making the clockevents core NTP correction aware, all clockevent device drivers must set ->min_delta_ticks and ->max_delta_ticks rather than ->min_delta_ns and ->max_delta_ns: a clockevent device's rate is going to change dynamically and thus, the ratio of ns to ticks ceases to stay invariant. Currently, the x86's uv rtc clockevent device is initialized as follows: clock_event_device_uv.min_delta_ns = NSEC_PER_SEC / sn_rtc_cycles_per_second; clock_event_device_uv.max_delta_ns = clocksource_uv.mask * (NSEC_PER_SEC / sn_rtc_cycles_per_second); This translates to a ->min_delta_ticks value of 1 and a ->max_delta_ticks value of clocksource_uv.mask. Initialize ->min_delta_ticks and ->max_delta_ticks with these values respectively. This patch alone doesn't introduce any change in functionality as the clockevents core still looks exclusively at the (untouched) ->min_delta_ns and ->max_delta_ns. As soon as this has changed, a followup patch will purge the initialization of ->min_delta_ns and ->max_delta_ns from this driver. Cc: Ingo Molnar <mingo@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Richard Cochran <richardcochran@gmail.com> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Stephen Boyd <sboyd@codeaurora.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Cc: Mike Travis <travis@sgi.com> Cc: Dimitri Sivanich <sivanich@sgi.com> Signed-off-by: Nicolai Stange <nicstange@gmail.com> Signed-off-by: John Stultz <john.stultz@linaro.org>
2017-03-31 03:04:58 +07:00
clock_event_device_uv.max_delta_ticks = clocksource_uv.mask;
rc = schedule_on_each_cpu(uv_rtc_register_clockevents);
if (rc) {
x86_platform_ipi_callback = NULL;
uv_rtc_deallocate_timers();
goto error;
}
printk(KERN_INFO "UV RTC clockevents registered\n");
return 0;
error:
clocksource_unregister(&clocksource_uv);
printk(KERN_INFO "UV RTC clockevents failed rc %d\n", rc);
return rc;
}
arch_initcall(uv_rtc_setup_clock);