Linus,

please pull the latest irq/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq-urgent-2024-08-04

up to:  6be6cba9c437: irqchip/mbigen: Fix mbigen node address layout

A couple of fixes for interrupt chip drivers:

  - Ensure to skip the clear register space in the MBIGEN driver when
    calculating the node register index. Otherwise the clear register is
    clobbered and the wrong node registers are accessed.

  - Fix a signed/unsigned confusion in the loongarch CPU driver which
    converts an error code to a huge "valid" interrupt number.

  - Convert the mesion GPIO interrupt controller lock to a raw spinlock so
    it works on RT.

  - Add a missing static to a internal function in the pic32 EVIC driver.

Thanks,

	tglx

------------------>
Arseniy Krasnov (1):
      irqchip/meson-gpio: Convert meson_gpio_irq_controller::lock to 'raw_spinlock_t'

Huacai Chen (1):
      irqchip/loongarch-cpu: Fix return value of lpic_gsi_to_irq()

Luca Ceresoli (1):
      irqchip/irq-pic32-evic: Add missing 'static' to internal function

Yipeng Zou (1):
      irqchip/mbigen: Fix mbigen node address layout


 drivers/irqchip/irq-loongarch-cpu.c |  6 ++++--
 drivers/irqchip/irq-mbigen.c        | 20 ++++++++++++++++----
 drivers/irqchip/irq-meson-gpio.c    | 14 +++++++-------
 drivers/irqchip/irq-pic32-evic.c    |  6 +++---
 4 files changed, 30 insertions(+), 16 deletions(-)

diff --git a/drivers/irqchip/irq-loongarch-cpu.c b/drivers/irqchip/irq-loongarch-cpu.c
index 9d8f2c406043..b35903a06902 100644
--- a/drivers/irqchip/irq-loongarch-cpu.c
+++ b/drivers/irqchip/irq-loongarch-cpu.c
@@ -18,11 +18,13 @@ struct fwnode_handle *cpuintc_handle;
 
 static u32 lpic_gsi_to_irq(u32 gsi)
 {
+	int irq = 0;
+
 	/* Only pch irqdomain transferring is required for LoongArch. */
 	if (gsi >= GSI_MIN_PCH_IRQ && gsi <= GSI_MAX_PCH_IRQ)
-		return acpi_register_gsi(NULL, gsi, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_HIGH);
+		irq = acpi_register_gsi(NULL, gsi, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_HIGH);
 
-	return 0;
+	return (irq > 0) ? irq : 0;
 }
 
 static struct fwnode_handle *lpic_get_gsi_domain_id(u32 gsi)
diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c
index 093fd42893a7..53cc08387588 100644
--- a/drivers/irqchip/irq-mbigen.c
+++ b/drivers/irqchip/irq-mbigen.c
@@ -64,6 +64,20 @@ struct mbigen_device {
 	void __iomem		*base;
 };
 
+static inline unsigned int get_mbigen_node_offset(unsigned int nid)
+{
+	unsigned int offset = nid * MBIGEN_NODE_OFFSET;
+
+	/*
+	 * To avoid touched clear register in unexpected way, we need to directly
+	 * skip clear register when access to more than 10 mbigen nodes.
+	 */
+	if (nid >= (REG_MBIGEN_CLEAR_OFFSET / MBIGEN_NODE_OFFSET))
+		offset += MBIGEN_NODE_OFFSET;
+
+	return offset;
+}
+
 static inline unsigned int get_mbigen_vec_reg(irq_hw_number_t hwirq)
 {
 	unsigned int nid, pin;
@@ -72,8 +86,7 @@ static inline unsigned int get_mbigen_vec_reg(irq_hw_number_t hwirq)
 	nid = hwirq / IRQS_PER_MBIGEN_NODE + 1;
 	pin = hwirq % IRQS_PER_MBIGEN_NODE;
 
-	return pin * 4 + nid * MBIGEN_NODE_OFFSET
-			+ REG_MBIGEN_VEC_OFFSET;
+	return pin * 4 + get_mbigen_node_offset(nid) + REG_MBIGEN_VEC_OFFSET;
 }
 
 static inline void get_mbigen_type_reg(irq_hw_number_t hwirq,
@@ -88,8 +101,7 @@ static inline void get_mbigen_type_reg(irq_hw_number_t hwirq,
 	*mask = 1 << (irq_ofst % 32);
 	ofst = irq_ofst / 32 * 4;
 
-	*addr = ofst + nid * MBIGEN_NODE_OFFSET
-		+ REG_MBIGEN_TYPE_OFFSET;
+	*addr = ofst + get_mbigen_node_offset(nid) + REG_MBIGEN_TYPE_OFFSET;
 }
 
 static inline void get_mbigen_clear_reg(irq_hw_number_t hwirq,
diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c
index 27e30ce41db3..cd789fa51519 100644
--- a/drivers/irqchip/irq-meson-gpio.c
+++ b/drivers/irqchip/irq-meson-gpio.c
@@ -178,7 +178,7 @@ struct meson_gpio_irq_controller {
 	void __iomem *base;
 	u32 channel_irqs[MAX_NUM_CHANNEL];
 	DECLARE_BITMAP(channel_map, MAX_NUM_CHANNEL);
-	spinlock_t lock;
+	raw_spinlock_t lock;
 };
 
 static void meson_gpio_irq_update_bits(struct meson_gpio_irq_controller *ctl,
@@ -187,14 +187,14 @@ static void meson_gpio_irq_update_bits(struct meson_gpio_irq_controller *ctl,
 	unsigned long flags;
 	u32 tmp;
 
-	spin_lock_irqsave(&ctl->lock, flags);
+	raw_spin_lock_irqsave(&ctl->lock, flags);
 
 	tmp = readl_relaxed(ctl->base + reg);
 	tmp &= ~mask;
 	tmp |= val;
 	writel_relaxed(tmp, ctl->base + reg);
 
-	spin_unlock_irqrestore(&ctl->lock, flags);
+	raw_spin_unlock_irqrestore(&ctl->lock, flags);
 }
 
 static void meson_gpio_irq_init_dummy(struct meson_gpio_irq_controller *ctl)
@@ -244,12 +244,12 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl,
 	unsigned long flags;
 	unsigned int idx;
 
-	spin_lock_irqsave(&ctl->lock, flags);
+	raw_spin_lock_irqsave(&ctl->lock, flags);
 
 	/* Find a free channel */
 	idx = find_first_zero_bit(ctl->channel_map, ctl->params->nr_channels);
 	if (idx >= ctl->params->nr_channels) {
-		spin_unlock_irqrestore(&ctl->lock, flags);
+		raw_spin_unlock_irqrestore(&ctl->lock, flags);
 		pr_err("No channel available\n");
 		return -ENOSPC;
 	}
@@ -257,7 +257,7 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl,
 	/* Mark the channel as used */
 	set_bit(idx, ctl->channel_map);
 
-	spin_unlock_irqrestore(&ctl->lock, flags);
+	raw_spin_unlock_irqrestore(&ctl->lock, flags);
 
 	/*
 	 * Setup the mux of the channel to route the signal of the pad
@@ -567,7 +567,7 @@ static int meson_gpio_irq_of_init(struct device_node *node, struct device_node *
 	if (!ctl)
 		return -ENOMEM;
 
-	spin_lock_init(&ctl->lock);
+	raw_spin_lock_init(&ctl->lock);
 
 	ctl->base = of_iomap(node, 0);
 	if (!ctl->base) {
diff --git a/drivers/irqchip/irq-pic32-evic.c b/drivers/irqchip/irq-pic32-evic.c
index 1d9bb28d13e5..277240325cbc 100644
--- a/drivers/irqchip/irq-pic32-evic.c
+++ b/drivers/irqchip/irq-pic32-evic.c
@@ -161,9 +161,9 @@ static int pic32_irq_domain_map(struct irq_domain *d, unsigned int virq,
 	return ret;
 }
 
-int pic32_irq_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
-			   const u32 *intspec, unsigned int intsize,
-			   irq_hw_number_t *out_hwirq, unsigned int *out_type)
+static int pic32_irq_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
+				  const u32 *intspec, unsigned int intsize,
+				  irq_hw_number_t *out_hwirq, unsigned int *out_type)
 {
 	struct evic_chip_data *priv = d->host_data;
 

The pull request you sent on Sun,  4 Aug 2024 15:02:51 +0200 (CEST):

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq-urgent-2024-08-04

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/953f776459a83f00ac940dd67c96d226d7041550

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

Linus,

please pull the latest locking/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking-urgent-2024-08-04

up to:  224fa3552029: jump_label: Fix the fix, brown paper bags galore


Two fixes for locking and jump labels:

   - Ensure that the atomic_cmpxchg() conditions are correct and evaluating
     to true on any non-zero value except 1. The missing check of the
     return value leads to inconsisted state of the jump label counter.

   - Add a missing type conversion in the paravirt spinlock code which
     makes loongson build again.


Thanks,

	tglx

------------------>
Peter Zijlstra (1):
      jump_label: Fix the fix, brown paper bags galore

Uros Bizjak (1):
      locking/pvqspinlock: Correct the type of "old" variable in pv_kick_node()


 kernel/jump_label.c                 | 4 ++--
 kernel/locking/qspinlock_paravirt.h | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 4ad5ed8adf96..6dc76b590703 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -236,7 +236,7 @@ void static_key_disable_cpuslocked(struct static_key *key)
 	}
 
 	jump_label_lock();
-	if (atomic_cmpxchg(&key->enabled, 1, 0))
+	if (atomic_cmpxchg(&key->enabled, 1, 0) == 1)
 		jump_label_update(key);
 	jump_label_unlock();
 }
@@ -289,7 +289,7 @@ static void __static_key_slow_dec_cpuslocked(struct static_key *key)
 		return;
 
 	guard(mutex)(&jump_label_mutex);
-	if (atomic_cmpxchg(&key->enabled, 1, 0))
+	if (atomic_cmpxchg(&key->enabled, 1, 0) == 1)
 		jump_label_update(key);
 	else
 		WARN_ON_ONCE(!static_key_slow_try_dec(key));
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index f5a36e67b593..ac2e22502741 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -357,7 +357,7 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
 static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
 {
 	struct pv_node *pn = (struct pv_node *)node;
-	enum vcpu_state old = vcpu_halted;
+	u8 old = vcpu_halted;
 	/*
 	 * If the vCPU is indeed halted, advance its state to match that of
 	 * pv_wait_node(). If OTOH this fails, the vCPU was running and will

The pull request you sent on Sun,  4 Aug 2024 15:02:53 +0200 (CEST):

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking-urgent-2024-08-04

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/3bc70ad12097c19cd6c687bc5b12c31da14b63f7

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

Linus,

please pull the latest perf/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2024-08-04

up to:  f73cefa3b72e: perf/x86: Fix smp_processor_id()-in-preemptible warnings


perf/x86 subsystem fixes:

     - Move the smp_processor_id() invocation back into the non-preemtible
       region, so that the result is valid to use.

     - Add the missing package C2 residency counters for Sierra Forest CPUs
       to make the newly added support actually useful

Thanks,

	tglx

------------------>
Li Huafei (1):
      perf/x86: Fix smp_processor_id()-in-preemptible warnings

Zhenyu Wang (1):
      perf/x86/intel/cstate: Add pkg C2 residency counter for Sierra Forest


 arch/x86/events/core.c         | 22 ++++++++++++----------
 arch/x86/events/intel/cstate.c |  5 +++--
 2 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 12f2a0c14d33..be01823b1bb4 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1520,20 +1520,23 @@ static void x86_pmu_start(struct perf_event *event, int flags)
 void perf_event_print_debug(void)
 {
 	u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed;
+	unsigned long *cntr_mask, *fixed_cntr_mask;
+	struct event_constraint *pebs_constraints;
+	struct cpu_hw_events *cpuc;
 	u64 pebs, debugctl;
-	int cpu = smp_processor_id();
-	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
-	unsigned long *cntr_mask = hybrid(cpuc->pmu, cntr_mask);
-	unsigned long *fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask);
-	struct event_constraint *pebs_constraints = hybrid(cpuc->pmu, pebs_constraints);
-	unsigned long flags;
-	int idx;
+	int cpu, idx;
+
+	guard(irqsave)();
+
+	cpu = smp_processor_id();
+	cpuc = &per_cpu(cpu_hw_events, cpu);
+	cntr_mask = hybrid(cpuc->pmu, cntr_mask);
+	fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask);
+	pebs_constraints = hybrid(cpuc->pmu, pebs_constraints);
 
 	if (!*(u64 *)cntr_mask)
 		return;
 
-	local_irq_save(flags);
-
 	if (x86_pmu.version >= 2) {
 		rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, ctrl);
 		rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
@@ -1577,7 +1580,6 @@ void perf_event_print_debug(void)
 		pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
 			cpu, idx, pmc_count);
 	}
-	local_irq_restore(flags);
 }
 
 void x86_pmu_stop(struct perf_event *event, int flags)
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index be58cfb012dd..9f116dfc4728 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -64,7 +64,7 @@
  *			       perf code: 0x00
  *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
  *						KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL,
- *						RPL,SPR,MTL,ARL,LNL
+ *						RPL,SPR,MTL,ARL,LNL,SRF
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
@@ -693,7 +693,8 @@ static const struct cstate_model srf_cstates __initconst = {
 	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
 				  BIT(PERF_CSTATE_CORE_C6_RES),
 
-	.pkg_events		= BIT(PERF_CSTATE_PKG_C6_RES),
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES),
 
 	.module_events		= BIT(PERF_CSTATE_MODULE_C6_RES),
 };

The pull request you sent on Sun,  4 Aug 2024 15:02:55 +0200 (CEST):

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2024-08-04

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/1ddeb0ef3cb724615d2d3aa8b35e5e241c474b51

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

Linus,

please pull the latest sched/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-2024-08-04

up to:  fe7a11c78d2a: sched/core: Fix unbalance set_rq_online/offline() in sched_cpu_deactivate()


Scheduler fixes:

   - When stime is larger than rtime due to accounting imprecision, then
     utime = rtime - stime becomes negative. As this is unsigned math, the
     result becomes a huge positive number. Cure it by resetting stime to
     rtime in that case, so utime becomes 0.

   - Restore consistent state when sched_cpu_deactivate() fails.

     When offlining a CPU fails in sched_cpu_deactivate() after the SMT
     present counter has been decremented, then the function aborts but
     fails to increment the SMT present counter and leaves it imbalanced.
     Consecutive operations cause it to underflow. Add the missing fixup
     for the error path.

     As SMT accounting the runqueue needs to marked online again in the
     error exit path to restore consistent state.

Thanks,

	tglx

------------------>
Yang Yingliang (4):
      sched/smt: Introduce sched_smt_present_inc/dec() helper
      sched/smt: Fix unbalance sched_smt_present dec/inc
      sched/core: Introduce sched_set_rq_on/offline() helper
      sched/core: Fix unbalance set_rq_online/offline() in sched_cpu_deactivate()

Zheng Zucheng (1):
      sched/cputime: Fix mul_u64_u64_div_u64() precision for cputime


 kernel/sched/core.c    | 68 ++++++++++++++++++++++++++++++++++----------------
 kernel/sched/cputime.c |  6 +++++
 2 files changed, 53 insertions(+), 21 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a9f655025607..f3951e4a55e5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7845,6 +7845,30 @@ void set_rq_offline(struct rq *rq)
 	}
 }
 
+static inline void sched_set_rq_online(struct rq *rq, int cpu)
+{
+	struct rq_flags rf;
+
+	rq_lock_irqsave(rq, &rf);
+	if (rq->rd) {
+		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+		set_rq_online(rq);
+	}
+	rq_unlock_irqrestore(rq, &rf);
+}
+
+static inline void sched_set_rq_offline(struct rq *rq, int cpu)
+{
+	struct rq_flags rf;
+
+	rq_lock_irqsave(rq, &rf);
+	if (rq->rd) {
+		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+		set_rq_offline(rq);
+	}
+	rq_unlock_irqrestore(rq, &rf);
+}
+
 /*
  * used to mark begin/end of suspend/resume:
  */
@@ -7895,10 +7919,25 @@ static int cpuset_cpu_inactive(unsigned int cpu)
 	return 0;
 }
 
+static inline void sched_smt_present_inc(int cpu)
+{
+#ifdef CONFIG_SCHED_SMT
+	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+		static_branch_inc_cpuslocked(&sched_smt_present);
+#endif
+}
+
+static inline void sched_smt_present_dec(int cpu)
+{
+#ifdef CONFIG_SCHED_SMT
+	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+		static_branch_dec_cpuslocked(&sched_smt_present);
+#endif
+}
+
 int sched_cpu_activate(unsigned int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	struct rq_flags rf;
 
 	/*
 	 * Clear the balance_push callback and prepare to schedule
@@ -7906,13 +7945,10 @@ int sched_cpu_activate(unsigned int cpu)
 	 */
 	balance_push_set(cpu, false);
 
-#ifdef CONFIG_SCHED_SMT
 	/*
 	 * When going up, increment the number of cores with SMT present.
 	 */
-	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
-		static_branch_inc_cpuslocked(&sched_smt_present);
-#endif
+	sched_smt_present_inc(cpu);
 	set_cpu_active(cpu, true);
 
 	if (sched_smp_initialized) {
@@ -7930,12 +7966,7 @@ int sched_cpu_activate(unsigned int cpu)
 	 * 2) At runtime, if cpuset_cpu_active() fails to rebuild the
 	 *    domains.
 	 */
-	rq_lock_irqsave(rq, &rf);
-	if (rq->rd) {
-		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
-		set_rq_online(rq);
-	}
-	rq_unlock_irqrestore(rq, &rf);
+	sched_set_rq_online(rq, cpu);
 
 	return 0;
 }
@@ -7943,7 +7974,6 @@ int sched_cpu_activate(unsigned int cpu)
 int sched_cpu_deactivate(unsigned int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	struct rq_flags rf;
 	int ret;
 
 	/*
@@ -7974,20 +8004,14 @@ int sched_cpu_deactivate(unsigned int cpu)
 	 */
 	synchronize_rcu();
 
-	rq_lock_irqsave(rq, &rf);
-	if (rq->rd) {
-		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
-		set_rq_offline(rq);
-	}
-	rq_unlock_irqrestore(rq, &rf);
+	sched_set_rq_offline(rq, cpu);
 
-#ifdef CONFIG_SCHED_SMT
 	/*
 	 * When going down, decrement the number of cores with SMT present.
 	 */
-	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
-		static_branch_dec_cpuslocked(&sched_smt_present);
+	sched_smt_present_dec(cpu);
 
+#ifdef CONFIG_SCHED_SMT
 	sched_core_cpu_deactivate(cpu);
 #endif
 
@@ -7997,6 +8021,8 @@ int sched_cpu_deactivate(unsigned int cpu)
 	sched_update_numa(cpu, false);
 	ret = cpuset_cpu_inactive(cpu);
 	if (ret) {
+		sched_smt_present_inc(cpu);
+		sched_set_rq_online(rq, cpu);
 		balance_push_set(cpu, false);
 		set_cpu_active(cpu, true);
 		sched_update_numa(cpu, true);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index a5e00293ae43..0bed0fa1acd9 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -582,6 +582,12 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
 	}
 
 	stime = mul_u64_u64_div_u64(stime, rtime, stime + utime);
+	/*
+	 * Because mul_u64_u64_div_u64() can approximate on some
+	 * achitectures; enforce the constraint that: a*b/(b+c) <= a.
+	 */
+	if (unlikely(stime > rtime))
+		stime = rtime;
 
 update:
 	/*

The pull request you sent on Sun,  4 Aug 2024 15:02:57 +0200 (CEST):

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-2024-08-04

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/6cc82dc2bd1196141ffd5ebc99ecb52f9537443b

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

Linus,

please pull the latest x86/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-urgent-2024-08-04

up to:  dd35a0933269: x86/uaccess: Zero the 8-byte get_range case on failure on 32-bit


X86 fixes:

    - Prevent a deadlock on cpu_hotplug_lock in the aperf/mperf driver.

      A recent change in the ACPI code which consolidated code pathes moved
      the invocation of init_freq_invariance_cppc() to be moved to a CPU
      hotplug handler. The first invocation on AMD CPUs ends up enabling a
      static branch which dead locks because the static branch enable tries to
      acquire cpu_hotplug_lock but that lock is already held write by the
      hotplug machinery.

      Use static_branch_enable_cpuslocked() instead and take the hotplug
      lock read for the Intel code path which is invoked from the
      architecture code outside of the CPU hotplug operations.

    - Fix the number of reserved bits in the sev_config structure bit field
      so that the bitfield does not exceed 64 bit.

    - Add missing Zen5 model numbers

    - Fix the alignment assumptions of pti_clone_pgtable() and
      clone_entry_text() on 32-bit:

      The code assumes PMD aligned code sections, but on 32-bit the kernel
      entry text is not PMD aligned. So depending on the code size and
      location, which is configuration and compiler dependent, entry text
      can cross a PMD boundary. As the start is not PMD aligned adding PMD
      size to the start address is larger than the end address which
      results in partially mapped entry code for user space. That causes
      endless recursion on the first entry from userspace (usually #PF).

      Cure this by aligning the start address in the addition so it ends up
      at the next PMD start address.

      clone_entry_text() enforces PMD mapping, but on 32-bit the tail might
      eventually be PTE mapped, which causes a map fail because the PMD for
      the tail is not a large page mapping. Use PTI_LEVEL_KERNEL_IMAGE for
      the clone() invocation which resolves to PTE on 32-bit and PMD on
      64-bit.

    - Zero the 8-byte case for get_user() on range check failure on 32-bit

      The recend consolidation of the 8-byte get_user() case broke the
      zeroing in the failure case again. Establish it by clearing ECX
      before the range check and not afterwards as that obvioulsy can't be
      reached when the range check fails

 
Thanks,

	tglx

------------------>
Borislav Petkov (AMD) (1):
      x86/setup: Parse the builtin command line before merging

David Gow (1):
      x86/uaccess: Zero the 8-byte get_range case on failure on 32-bit

Jonathan Cameron (1):
      x86/aperfmperf: Fix deadlock on cpu_hotplug_lock

Pavan Kumar Paluri (1):
      x86/sev: Fix __reserved field in sev_config

Perry Yuan (1):
      x86/CPU/AMD: Add models 0x60-0x6f to the Zen5 range

Peter Zijlstra (2):
      x86/mm: Fix pti_clone_pgtable() alignment assumption
      x86/mm: Fix pti_clone_entry_text() for i386


 arch/x86/coco/sev/core.c         |  2 +-
 arch/x86/include/asm/cmdline.h   |  4 ++++
 arch/x86/kernel/cpu/amd.c        |  2 +-
 arch/x86/kernel/cpu/aperfmperf.c |  6 ++++--
 arch/x86/kernel/setup.c          |  2 +-
 arch/x86/lib/cmdline.c           | 25 ++++++++++++++++++-------
 arch/x86/lib/getuser.S           |  4 +++-
 arch/x86/mm/pti.c                |  8 ++++----
 8 files changed, 36 insertions(+), 17 deletions(-)

diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index 082d61d85dfc..de1df0cb45da 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -163,7 +163,7 @@ struct sev_config {
 	       */
 	      use_cas		: 1,
 
-	      __reserved	: 62;
+	      __reserved	: 61;
 };
 
 static struct sev_config sev_cfg __read_mostly;
diff --git a/arch/x86/include/asm/cmdline.h b/arch/x86/include/asm/cmdline.h
index 6faaf27e8899..6cbd9ae58b21 100644
--- a/arch/x86/include/asm/cmdline.h
+++ b/arch/x86/include/asm/cmdline.h
@@ -2,6 +2,10 @@
 #ifndef _ASM_X86_CMDLINE_H
 #define _ASM_X86_CMDLINE_H
 
+#include <asm/setup.h>
+
+extern char builtin_cmdline[COMMAND_LINE_SIZE];
+
 int cmdline_find_option_bool(const char *cmdline_ptr, const char *option);
 int cmdline_find_option(const char *cmdline_ptr, const char *option,
 			char *buffer, int bufsize);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index be5889bded49..1e0fe5f8ab84 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -462,7 +462,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		switch (c->x86_model) {
 		case 0x00 ... 0x2f:
 		case 0x40 ... 0x4f:
-		case 0x70 ... 0x7f:
+		case 0x60 ... 0x7f:
 			setup_force_cpu_cap(X86_FEATURE_ZEN5);
 			break;
 		default:
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index b3fa61d45352..0b69bfbf345d 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -306,7 +306,7 @@ static void freq_invariance_enable(void)
 		WARN_ON_ONCE(1);
 		return;
 	}
-	static_branch_enable(&arch_scale_freq_key);
+	static_branch_enable_cpuslocked(&arch_scale_freq_key);
 	register_freq_invariance_syscore_ops();
 	pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio);
 }
@@ -323,8 +323,10 @@ static void __init bp_init_freq_invariance(void)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return;
 
-	if (intel_set_max_freq_ratio())
+	if (intel_set_max_freq_ratio()) {
+		guard(cpus_read_lock)();
 		freq_invariance_enable();
+	}
 }
 
 static void disable_freq_invariance_workfn(struct work_struct *work)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 5d34cad9b7b1..6129dc2ba784 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -164,7 +164,7 @@ unsigned long saved_video_mode;
 
 static char __initdata command_line[COMMAND_LINE_SIZE];
 #ifdef CONFIG_CMDLINE_BOOL
-static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
+char builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
 bool builtin_cmdline_added __ro_after_init;
 #endif
 
diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c
index 384da1fdd5c6..c65cd5550454 100644
--- a/arch/x86/lib/cmdline.c
+++ b/arch/x86/lib/cmdline.c
@@ -207,18 +207,29 @@ __cmdline_find_option(const char *cmdline, int max_cmdline_size,
 
 int cmdline_find_option_bool(const char *cmdline, const char *option)
 {
-	if (IS_ENABLED(CONFIG_CMDLINE_BOOL))
-		WARN_ON_ONCE(!builtin_cmdline_added);
+	int ret;
 
-	return __cmdline_find_option_bool(cmdline, COMMAND_LINE_SIZE, option);
+	ret = __cmdline_find_option_bool(cmdline, COMMAND_LINE_SIZE, option);
+	if (ret > 0)
+		return ret;
+
+	if (IS_ENABLED(CONFIG_CMDLINE_BOOL) && !builtin_cmdline_added)
+		return __cmdline_find_option_bool(builtin_cmdline, COMMAND_LINE_SIZE, option);
+
+	return ret;
 }
 
 int cmdline_find_option(const char *cmdline, const char *option, char *buffer,
 			int bufsize)
 {
-	if (IS_ENABLED(CONFIG_CMDLINE_BOOL))
-		WARN_ON_ONCE(!builtin_cmdline_added);
+	int ret;
+
+	ret = __cmdline_find_option(cmdline, COMMAND_LINE_SIZE, option, buffer, bufsize);
+	if (ret > 0)
+		return ret;
+
+	if (IS_ENABLED(CONFIG_CMDLINE_BOOL) && !builtin_cmdline_added)
+		return __cmdline_find_option(builtin_cmdline, COMMAND_LINE_SIZE, option, buffer, bufsize);
 
-	return __cmdline_find_option(cmdline, COMMAND_LINE_SIZE, option,
-				     buffer, bufsize);
+	return ret;
 }
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index a314622aa093..d066aecf8aeb 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -88,12 +88,14 @@ SYM_FUNC_END(__get_user_4)
 EXPORT_SYMBOL(__get_user_4)
 
 SYM_FUNC_START(__get_user_8)
+#ifndef CONFIG_X86_64
+	xor %ecx,%ecx
+#endif
 	check_range size=8
 	ASM_STAC
 #ifdef CONFIG_X86_64
 	UACCESS movq (%_ASM_AX),%rdx
 #else
-	xor %ecx,%ecx
 	UACCESS movl (%_ASM_AX),%edx
 	UACCESS movl 4(%_ASM_AX),%ecx
 #endif
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 2e69abf4f852..bfdf5f45b137 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -374,14 +374,14 @@ pti_clone_pgtable(unsigned long start, unsigned long end,
 			 */
 			*target_pmd = *pmd;
 
-			addr += PMD_SIZE;
+			addr = round_up(addr + 1, PMD_SIZE);
 
 		} else if (level == PTI_CLONE_PTE) {
 
 			/* Walk the page-table down to the pte level */
 			pte = pte_offset_kernel(pmd, addr);
 			if (pte_none(*pte)) {
-				addr += PAGE_SIZE;
+				addr = round_up(addr + 1, PAGE_SIZE);
 				continue;
 			}
 
@@ -401,7 +401,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end,
 			/* Clone the PTE */
 			*target_pte = *pte;
 
-			addr += PAGE_SIZE;
+			addr = round_up(addr + 1, PAGE_SIZE);
 
 		} else {
 			BUG();
@@ -496,7 +496,7 @@ static void pti_clone_entry_text(void)
 {
 	pti_clone_pgtable((unsigned long) __entry_text_start,
 			  (unsigned long) __entry_text_end,
-			  PTI_CLONE_PMD);
+			  PTI_LEVEL_KERNEL_IMAGE);
 }
 
 /*

The pull request you sent on Sun,  4 Aug 2024 15:03:00 +0200 (CEST):

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-urgent-2024-08-04

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/a5dbd76a89423eca9f8de338350f2666aacfb432

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

Linus,

please pull the latest timers/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-urgent-2024-08-04

up to:  f2655ac2c06a: clocksource: Fix brown-bag boolean thinko in cs_watchdog_read()


Two fixes for the timer/clocksource code:

    - The recent fix for making the take over of the broadcast timer more
      reliable retrieves a per CPU pointer in preemptible context.
      This went unnoticed in testing as some compilers hoist the access into
      the non-preemotible section where the pointer is actually used, but
      obviously compilers can rightfully invoke it where the code put it.

      Move it into the non-preemptible section right to the actual usage
      side to cure it.

    - The clocksource watchdog is supposed to emit a warning when the retry
      count is greater than one and the number of retries reaches the
      limit. The condition is backwards and warns always when the count is
      greater than one. Fixup the condition to prevent spamming dmesg.



Thanks,

	tglx

------------------>
Paul E. McKenney (1):
      clocksource: Fix brown-bag boolean thinko in cs_watchdog_read()

Thomas Gleixner (1):
      tick/broadcast: Move per CPU pointer access into the atomic section


 kernel/time/clocksource.c    | 2 +-
 kernel/time/tick-broadcast.c | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index d25ba49e313c..d0538a75f4c6 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -246,7 +246,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow,
 
 		wd_delay = cycles_to_nsec_safe(watchdog, *wdnow, wd_end);
 		if (wd_delay <= WATCHDOG_MAX_SKEW) {
-			if (nretries > 1 || nretries >= max_retries) {
+			if (nretries > 1 && nretries >= max_retries) {
 				pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n",
 					smp_processor_id(), watchdog->name, nretries);
 			}
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index b4843099a8da..ed58eebb4e8f 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -1141,7 +1141,6 @@ void tick_broadcast_switch_to_oneshot(void)
 #ifdef CONFIG_HOTPLUG_CPU
 void hotplug_cpu__broadcast_tick_pull(int deadcpu)
 {
-	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 	struct clock_event_device *bc;
 	unsigned long flags;
 
@@ -1167,6 +1166,8 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu)
 		 * device to avoid the starvation.
 		 */
 		if (tick_check_broadcast_expired()) {
+			struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+
 			cpumask_clear_cpu(smp_processor_id(), tick_broadcast_force_mask);
 			tick_program_event(td->evtdev->next_event, 1);
 		}

The pull request you sent on Sun,  4 Aug 2024 15:02:58 +0200 (CEST):

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-urgent-2024-08-04

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/61ca6c78295e242d4b681003112bfcdc54597489

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html