summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--MAINTAINERS8
-rw-r--r--arch/riscv/include/asm/pgtable.h17
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/include/asm/topology.h10
-rw-r--r--arch/x86/kernel/cpu/topology.c13
-rw-r--r--include/linux/sched.h2
-rw-r--r--kernel/sched/deadline.c35
-rw-r--r--kernel/sched/fair.c7
-rw-r--r--kernel/sched/sched.h37
9 files changed, 80 insertions, 51 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index cfffa6c3bdf1..35dac69ec0d5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1772,7 +1772,7 @@ F: drivers/staging/iio/*/ad*
X: drivers/iio/*/adjd*
ANALOGBITS PLL LIBRARIES
-M: Paul Walmsley <paul.walmsley@sifive.com>
+M: Paul Walmsley <pjw@kernel.org>
M: Samuel Holland <samuel.holland@sifive.com>
S: Supported
F: drivers/clk/analogbits/*
@@ -19296,7 +19296,7 @@ S: Maintained
F: drivers/pci/controller/dwc/*layerscape*
PCI DRIVER FOR FU740
-M: Paul Walmsley <paul.walmsley@sifive.com>
+M: Paul Walmsley <pjw@kernel.org>
M: Greentime Hu <greentime.hu@sifive.com>
M: Samuel Holland <samuel.holland@sifive.com>
L: linux-pci@vger.kernel.org
@@ -21656,7 +21656,7 @@ F: Documentation/devicetree/bindings/timer/andestech,plmt0.yaml
F: arch/riscv/boot/dts/andes/
RISC-V ARCHITECTURE
-M: Paul Walmsley <paul.walmsley@sifive.com>
+M: Paul Walmsley <pjw@kernel.org>
M: Palmer Dabbelt <palmer@dabbelt.com>
M: Albert Ou <aou@eecs.berkeley.edu>
R: Alexandre Ghiti <alex@ghiti.fr>
@@ -23108,7 +23108,7 @@ S: Maintained
F: drivers/watchdog/simatic-ipc-wdt.c
SIFIVE DRIVERS
-M: Paul Walmsley <paul.walmsley@sifive.com>
+M: Paul Walmsley <pjw@kernel.org>
M: Samuel Holland <samuel.holland@sifive.com>
L: linux-riscv@lists.infradead.org
S: Supported
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 91697fbf1f90..815067742939 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -942,6 +942,23 @@ static inline int pudp_test_and_clear_young(struct vm_area_struct *vma,
return ptep_test_and_clear_young(vma, address, (pte_t *)pudp);
}
+#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR
+static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
+ unsigned long address, pud_t *pudp)
+{
+#ifdef CONFIG_SMP
+ pud_t pud = __pud(xchg(&pudp->pud, 0));
+#else
+ pud_t pud = *pudp;
+
+ pud_clear(pudp);
+#endif
+
+ page_table_check_pud_clear(mm, pud);
+
+ return pud;
+}
+
static inline int pud_young(pud_t pud)
{
return pte_young(pud_pte(pud));
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 52c8910ba2ef..05880301212e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -26,7 +26,6 @@ config X86_64
depends on 64BIT
# Options that are inherently 64-bit kernel only:
select ARCH_HAS_GIGANTIC_PAGE
- select ARCH_HAS_PTDUMP
select ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS
select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
select ARCH_SUPPORTS_PER_VMA_LOCK
@@ -99,6 +98,7 @@ config X86
select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
select ARCH_HAS_PMEM_API if X86_64
select ARCH_HAS_PREEMPT_LAZY
+ select ARCH_HAS_PTDUMP
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_HW_PTE_YOUNG
select ARCH_HAS_NONLEAF_PMD_YOUNG if PGTABLE_LEVELS > 2
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 6c79ee7c0957..21041898157a 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -231,6 +231,16 @@ static inline bool topology_is_primary_thread(unsigned int cpu)
}
#define topology_is_primary_thread topology_is_primary_thread
+int topology_get_primary_thread(unsigned int cpu);
+
+static inline bool topology_is_core_online(unsigned int cpu)
+{
+ int pcpu = topology_get_primary_thread(cpu);
+
+ return pcpu >= 0 ? cpu_online(pcpu) : false;
+}
+#define topology_is_core_online topology_is_core_online
+
#else /* CONFIG_SMP */
static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
static inline int topology_max_smt_threads(void) { return 1; }
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index e35ccdc84910..6073a16628f9 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -372,6 +372,19 @@ unsigned int topology_unit_count(u32 apicid, enum x86_topology_domains which_uni
return topo_unit_count(lvlid, at_level, apic_maps[which_units].map);
}
+#ifdef CONFIG_SMP
+int topology_get_primary_thread(unsigned int cpu)
+{
+ u32 apic_id = cpuid_to_apicid[cpu];
+
+ /*
+ * Get the core domain level APIC id, which is the primary thread
+ * and return the CPU number assigned to it.
+ */
+ return topo_lookup_cpuid(topo_apicid(apic_id, TOPO_CORE_DOMAIN));
+}
+#endif
+
#ifdef CONFIG_ACPI_HOTPLUG_CPU
/**
* topology_hotplug_apic - Handle a physical hotplugged APIC after boot
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f8188b833350..e4ce0a76831e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -706,7 +706,6 @@ struct sched_dl_entity {
unsigned int dl_defer : 1;
unsigned int dl_defer_armed : 1;
unsigned int dl_defer_running : 1;
- unsigned int dl_server_idle : 1;
/*
* Bandwidth enforcement timer. Each -deadline task has its
@@ -733,7 +732,6 @@ struct sched_dl_entity {
* runnable task.
*/
struct rq *rq;
- dl_server_has_tasks_f server_has_tasks;
dl_server_pick_f server_pick_task;
#ifdef CONFIG_RT_MUTEXES
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index f25301267e47..72c1f72463c7 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -875,7 +875,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
*/
if (dl_se->dl_defer && !dl_se->dl_defer_running &&
dl_time_before(rq_clock(dl_se->rq), dl_se->deadline - dl_se->runtime)) {
- if (!is_dl_boosted(dl_se) && dl_se->server_has_tasks(dl_se)) {
+ if (!is_dl_boosted(dl_se)) {
/*
* Set dl_se->dl_defer_armed and dl_throttled variables to
@@ -1152,8 +1152,6 @@ static void __push_dl_task(struct rq *rq, struct rq_flags *rf)
/* a defer timer will not be reset if the runtime consumed was < dl_server_min_res */
static const u64 dl_server_min_res = 1 * NSEC_PER_MSEC;
-static bool dl_server_stopped(struct sched_dl_entity *dl_se);
-
static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_dl_entity *dl_se)
{
struct rq *rq = rq_of_dl_se(dl_se);
@@ -1171,12 +1169,6 @@ static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_
if (!dl_se->dl_runtime)
return HRTIMER_NORESTART;
- if (!dl_se->server_has_tasks(dl_se)) {
- replenish_dl_entity(dl_se);
- dl_server_stopped(dl_se);
- return HRTIMER_NORESTART;
- }
-
if (dl_se->dl_defer_armed) {
/*
* First check if the server could consume runtime in background.
@@ -1579,10 +1571,8 @@ void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
{
/* 0 runtime = fair server disabled */
- if (dl_se->dl_runtime) {
- dl_se->dl_server_idle = 0;
+ if (dl_se->dl_runtime)
update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
- }
}
void dl_server_start(struct sched_dl_entity *dl_se)
@@ -1610,26 +1600,10 @@ void dl_server_stop(struct sched_dl_entity *dl_se)
dl_se->dl_server_active = 0;
}
-static bool dl_server_stopped(struct sched_dl_entity *dl_se)
-{
- if (!dl_se->dl_server_active)
- return true;
-
- if (dl_se->dl_server_idle) {
- dl_server_stop(dl_se);
- return true;
- }
-
- dl_se->dl_server_idle = 1;
- return false;
-}
-
void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
- dl_server_has_tasks_f has_tasks,
dl_server_pick_f pick_task)
{
dl_se->rq = rq;
- dl_se->server_has_tasks = has_tasks;
dl_se->server_pick_task = pick_task;
}
@@ -2394,10 +2368,7 @@ again:
if (dl_server(dl_se)) {
p = dl_se->server_pick_task(dl_se);
if (!p) {
- if (!dl_server_stopped(dl_se)) {
- dl_se->dl_yielded = 1;
- update_curr_dl_se(rq, dl_se, 0);
- }
+ dl_server_stop(dl_se);
goto again;
}
rq->dl_server = dl_se;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b173a059315c..8ce56a8d507f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8859,11 +8859,6 @@ static struct task_struct *__pick_next_task_fair(struct rq *rq, struct task_stru
return pick_next_task_fair(rq, prev, NULL);
}
-static bool fair_server_has_tasks(struct sched_dl_entity *dl_se)
-{
- return !!dl_se->rq->cfs.nr_queued;
-}
-
static struct task_struct *fair_server_pick_task(struct sched_dl_entity *dl_se)
{
return pick_task_fair(dl_se->rq);
@@ -8875,7 +8870,7 @@ void fair_server_init(struct rq *rq)
init_dl_entity(dl_se);
- dl_server_init(dl_se, rq, fair_server_has_tasks, fair_server_pick_task);
+ dl_server_init(dl_se, rq, fair_server_pick_task);
}
/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index be9745d104f7..cf2109b67f9a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -365,25 +365,50 @@ extern s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s6
*
* dl_se::rq -- runqueue we belong to.
*
- * dl_se::server_has_tasks() -- used on bandwidth enforcement; we 'stop' the
- * server when it runs out of tasks to run.
- *
* dl_se::server_pick() -- nested pick_next_task(); we yield the period if this
* returns NULL.
*
* dl_server_update() -- called from update_curr_common(), propagates runtime
* to the server.
*
- * dl_server_start()
- * dl_server_stop() -- start/stop the server when it has (no) tasks.
+ * dl_server_start() -- start the server when it has tasks; it will stop
+ * automatically when there are no more tasks, per
+ * dl_se::server_pick() returning NULL.
+ *
+ * dl_server_stop() -- (force) stop the server; use when updating
+ * parameters.
*
* dl_server_init() -- initializes the server.
+ *
+ * When started the dl_server will (per dl_defer) schedule a timer for its
+ * zero-laxity point -- that is, unlike regular EDF tasks which run ASAP, a
+ * server will run at the very end of its period.
+ *
+ * This is done such that any runtime from the target class can be accounted
+ * against the server -- through dl_server_update() above -- such that when it
+ * becomes time to run, it might already be out of runtime and get deferred
+ * until the next period. In this case dl_server_timer() will alternate
+ * between defer and replenish but never actually enqueue the server.
+ *
+ * Only when the target class does not manage to exhaust the server's runtime
+ * (there's actualy starvation in the given period), will the dl_server get on
+ * the runqueue. Once queued it will pick tasks from the target class and run
+ * them until either its runtime is exhaused, at which point its back to
+ * dl_server_timer, or until there are no more tasks to run, at which point
+ * the dl_server stops itself.
+ *
+ * By stopping at this point the dl_server retains bandwidth, which, if a new
+ * task wakes up imminently (starting the server again), can be used --
+ * subject to CBS wakeup rules -- without having to wait for the next period.
+ *
+ * Additionally, because of the dl_defer behaviour the start/stop behaviour is
+ * naturally thottled to once per period, avoiding high context switch
+ * workloads from spamming the hrtimer program/cancel paths.
*/
extern void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec);
extern void dl_server_start(struct sched_dl_entity *dl_se);
extern void dl_server_stop(struct sched_dl_entity *dl_se);
extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
- dl_server_has_tasks_f has_tasks,
dl_server_pick_f pick_task);
extern void sched_init_dl_servers(void);
generated by cgit v1.2.3 (git 2.46.0) at 2025-09-27 05:04:08 +0000