From 780b1350d316fda28d85fcae17854c778d89cbbe Mon Sep 17 00:00:00 2001 From: Ramesh Shanmugasundaram Date: Mon, 3 Jul 2017 12:04:21 +0100 Subject: regmap: Avoid namespace collision within macro & tidy up Renamed variable "timeout" to "__timeout" & "pollret" to "__ret" to avoid namespace collision. Tidy up macro arguments with parentheses. Signed-off-by: Ramesh Shanmugasundaram Signed-off-by: Mark Brown --- include/linux/regmap.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index e88649225a60..6e1df5e721a9 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -120,23 +120,24 @@ struct reg_sequence { */ #define regmap_read_poll_timeout(map, addr, val, cond, sleep_us, timeout_us) \ ({ \ - ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \ - int pollret; \ + ktime_t __timeout = ktime_add_us(ktime_get(), timeout_us); \ + int __ret; \ might_sleep_if(sleep_us); \ for (;;) { \ - pollret = regmap_read((map), (addr), &(val)); \ - if (pollret) \ + __ret = regmap_read((map), (addr), &(val)); \ + if (__ret) \ break; \ if (cond) \ break; \ - if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \ - pollret = regmap_read((map), (addr), &(val)); \ + if ((timeout_us) && \ + ktime_compare(ktime_get(), __timeout) > 0) { \ + __ret = regmap_read((map), (addr), &(val)); \ break; \ } \ if (sleep_us) \ - usleep_range((sleep_us >> 2) + 1, sleep_us); \ + usleep_range(((sleep_us) >> 2) + 1, sleep_us); \ } \ - pollret ?: ((cond) ? 0 : -ETIMEDOUT); \ + __ret ?: ((cond) ? 0 : -ETIMEDOUT); \ }) #ifdef CONFIG_REGMAP -- cgit v1.2.3 From 07557ccb8c83f315e409ddee181e9ffbf87c6ad1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Sep 2017 23:29:05 +0200 Subject: genirq/msi: Capture device name for debugfs For debugging the allocation of unused or potentially leaked interrupt descriptor it's helpful to have some information about the site which allocated them. In case of MSI this is simple because the caller hands the device struct pointer into the domain allocation function. Duplicate the device name and show it in the debugfs entry of the interrupt descriptor. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Tested-by: Yu Chen Acked-by: Juergen Gross Cc: Boris Ostrovsky Cc: Tony Luck Cc: Marc Zyngier Cc: Alok Kataria Cc: Joerg Roedel Cc: "Rafael J. Wysocki" Cc: Steven Rostedt Cc: Christoph Hellwig Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Paolo Bonzini Cc: Rui Zhang Cc: "K. Y. Srinivasan" Cc: Arjan van de Ven Cc: Dan Williams Cc: Len Brown Link: https://lkml.kernel.org/r/20170913213152.433038426@linutronix.de --- include/linux/irqdesc.h | 1 + kernel/irq/debugfs.c | 10 ++++++++++ kernel/irq/internals.h | 5 +++++ kernel/irq/msi.c | 6 +++++- 4 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 3e90a094798d..b55b113c049b 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -93,6 +93,7 @@ struct irq_desc { #endif #ifdef CONFIG_GENERIC_IRQ_DEBUGFS struct dentry *debugfs_file; + const char *dev_name; #endif #ifdef CONFIG_SPARSE_IRQ struct rcu_head rcu; diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index c3fdb36dec30..b7d1023b9b22 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -149,6 +149,7 @@ static int irq_debug_show(struct seq_file *m, void *p) raw_spin_lock_irq(&desc->lock); data = irq_desc_get_irq_data(desc); seq_printf(m, "handler: %pf\n", desc->handle_irq); + seq_printf(m, "device: %s\n", desc->dev_name); seq_printf(m, "status: 0x%08x\n", desc->status_use_accessors); irq_debug_show_bits(m, 0, desc->status_use_accessors, irqdesc_states, ARRAY_SIZE(irqdesc_states)); @@ -226,6 +227,15 @@ static const struct file_operations dfs_irq_ops = { .release = single_release, }; +void irq_debugfs_copy_devname(int irq, struct device *dev) +{ + struct irq_desc *desc = irq_to_desc(irq); + const char *name = dev_name(dev); + + if (name) + desc->dev_name = kstrdup(name, GFP_KERNEL); +} + void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc) { char name [10]; diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index a4aa39009f0d..cfaec2669093 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -443,7 +443,9 @@ void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc); static inline void irq_remove_debugfs_entry(struct irq_desc *desc) { debugfs_remove(desc->debugfs_file); + kfree(desc->dev_name); } +void irq_debugfs_copy_devname(int irq, struct device *dev); # ifdef CONFIG_IRQ_DOMAIN void irq_domain_debugfs_init(struct dentry *root); # else @@ -458,4 +460,7 @@ static inline void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *d) static inline void irq_remove_debugfs_entry(struct irq_desc *d) { } +static inline void irq_debugfs_copy_devname(int irq, struct device *dev) +{ +} #endif /* CONFIG_GENERIC_IRQ_DEBUGFS */ diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 3fa4bd59f569..94ecc0293844 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -16,6 +16,8 @@ #include #include +#include "internals.h" + /** * alloc_msi_entry - Allocate an initialize msi_entry * @dev: Pointer to the device for which this is allocated @@ -373,8 +375,10 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, return ret; } - for (i = 0; i < desc->nvec_used; i++) + for (i = 0; i < desc->nvec_used; i++) { irq_set_msi_desc_off(virq, i, desc); + irq_debugfs_copy_devname(virq + i, dev); + } } if (ops->msi_finish) -- cgit v1.2.3 From c3e7239a7f43ce1ff407df5f5944bf0d42dc21bf Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Sep 2017 23:29:06 +0200 Subject: irqdomain/debugfs: Provide domain specific debug callback Some interrupt domains like the X86 vector domain has special requirements for debugging, like showing the vector usage on the CPUs. Add a callback to the irqdomain ops which can be filled in by domains which require it and add conditional invocations to the irqdomain and the per irq debug files. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Tested-by: Yu Chen Acked-by: Juergen Gross Cc: Boris Ostrovsky Cc: Tony Luck Cc: Marc Zyngier Cc: Alok Kataria Cc: Joerg Roedel Cc: "Rafael J. Wysocki" Cc: Steven Rostedt Cc: Christoph Hellwig Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Paolo Bonzini Cc: Rui Zhang Cc: "K. Y. Srinivasan" Cc: Arjan van de Ven Cc: Dan Williams Cc: Len Brown Link: https://lkml.kernel.org/r/20170913213152.512937505@linutronix.de --- include/linux/irqdomain.h | 6 +++++- kernel/irq/debugfs.c | 2 ++ kernel/irq/irqdomain.c | 2 ++ 3 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 81e4889ca6dd..1fb50438a868 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -40,6 +40,7 @@ struct of_device_id; struct irq_chip; struct irq_data; struct cpumask; +struct seq_file; /* Number of irqs reserved for a legacy isa controller */ #define NUM_ISA_INTERRUPTS 16 @@ -104,7 +105,6 @@ struct irq_domain_ops { int (*xlate)(struct irq_domain *d, struct device_node *node, const u32 *intspec, unsigned int intsize, unsigned long *out_hwirq, unsigned int *out_type); - #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY /* extended V2 interfaces to support hierarchy irq_domains */ int (*alloc)(struct irq_domain *d, unsigned int virq, @@ -116,6 +116,10 @@ struct irq_domain_ops { int (*translate)(struct irq_domain *d, struct irq_fwspec *fwspec, unsigned long *out_hwirq, unsigned int *out_type); #endif +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS + void (*debug_show)(struct seq_file *m, struct irq_domain *d, + struct irq_data *irqd, int ind); +#endif }; extern struct irq_domain_ops irq_generic_chip_ops; diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index b7d1023b9b22..7f608ac39653 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -81,6 +81,8 @@ irq_debug_show_data(struct seq_file *m, struct irq_data *data, int ind) data->domain ? data->domain->name : ""); seq_printf(m, "%*shwirq: 0x%lx\n", ind + 1, "", data->hwirq); irq_debug_show_chip(m, data, ind + 1); + if (data->domain && data->domain->ops && data->domain->ops->debug_show) + data->domain->ops->debug_show(m, NULL, data, ind + 1); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY if (!data->parent_data) return; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index e84b7056bb08..1a75a00ee01f 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1810,6 +1810,8 @@ irq_domain_debug_show_one(struct seq_file *m, struct irq_domain *d, int ind) d->revmap_size + d->revmap_direct_max_irq); seq_printf(m, "%*smapped: %u\n", ind + 1, "", d->mapcount); seq_printf(m, "%*sflags: 0x%08x\n", ind +1 , "", d->flags); + if (d->ops && d->ops->debug_show) + d->ops->debug_show(m, d, NULL, ind + 1); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY if (!d->parent) return; -- cgit v1.2.3 From 457f6d35072f395508255ef09fd08f824382cf85 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Sep 2017 23:29:07 +0200 Subject: genirq: Make state consistent for !IRQ_DOMAIN_HIERARCHY In the !IRQ_DOMAIN_HIERARCHY cas the activation stubs are not setting/clearing the activation status bits. This is not a problem at the moment, but upcoming changes require a correct status. Add the set/clear incovations to the stub functions and move them to the core internal header to avoid duplication and visibility outside the core. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Tested-by: Yu Chen Acked-by: Juergen Gross Cc: Boris Ostrovsky Cc: Tony Luck Cc: Marc Zyngier Cc: Alok Kataria Cc: Joerg Roedel Cc: "Rafael J. Wysocki" Cc: Steven Rostedt Cc: Christoph Hellwig Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Paolo Bonzini Cc: Rui Zhang Cc: "K. Y. Srinivasan" Cc: Arjan van de Ven Cc: Dan Williams Cc: Len Brown Link: https://lkml.kernel.org/r/20170913213152.591985591@linutronix.de --- include/linux/irqdomain.h | 4 ---- kernel/irq/internals.h | 11 +++++++++++ 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 1fb50438a868..de06ce992a2d 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -511,8 +511,6 @@ static inline bool irq_domain_is_msi_remap(struct irq_domain *domain) extern bool irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain); #else /* CONFIG_IRQ_DOMAIN_HIERARCHY */ -static inline void irq_domain_activate_irq(struct irq_data *data) { } -static inline void irq_domain_deactivate_irq(struct irq_data *data) { } static inline int irq_domain_alloc_irqs(struct irq_domain *domain, unsigned int nr_irqs, int node, void *arg) { @@ -561,8 +559,6 @@ irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain) #else /* CONFIG_IRQ_DOMAIN */ static inline void irq_dispose_mapping(unsigned int virq) { } -static inline void irq_domain_activate_irq(struct irq_data *data) { } -static inline void irq_domain_deactivate_irq(struct irq_data *data) { } static inline struct irq_domain *irq_find_matching_fwnode( struct fwnode_handle *fwnode, enum irq_domain_bus_token bus_token) { diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index cfaec2669093..72b8da2a7c39 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -436,6 +436,17 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear) } #endif /* !CONFIG_GENERIC_PENDING_IRQ */ +#if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY) +static inline void irq_domain_activate_irq(struct irq_data *data) +{ + irqd_set_activated(data); +} +static inline void irq_domain_deactivate_irq(struct irq_data *data) +{ + irqd_clr_activated(data); +} +#endif + #ifdef CONFIG_GENERIC_IRQ_DEBUGFS #include -- cgit v1.2.3 From 72491643469aab736536ae71dcd199b19dabd891 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Sep 2017 23:29:10 +0200 Subject: genirq/irqdomain: Update irq_domain_ops.activate() signature The irq_domain_ops.activate() callback has no return value and no way to tell the function that the activation is early. The upcoming changes to support a reservation scheme which allows to assign interrupt vectors on x86 only when the interrupt is actually requested requires: - A return value, so activation can fail at request_irq() time - Information that the activate invocation is early, i.e. before request_irq(). Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Tested-by: Yu Chen Acked-by: Juergen Gross Cc: Boris Ostrovsky Cc: Tony Luck Cc: Marc Zyngier Cc: Alok Kataria Cc: Joerg Roedel Cc: "Rafael J. Wysocki" Cc: Steven Rostedt Cc: Christoph Hellwig Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Paolo Bonzini Cc: Rui Zhang Cc: "K. Y. Srinivasan" Cc: Arjan van de Ven Cc: Dan Williams Cc: Len Brown Link: https://lkml.kernel.org/r/20170913213152.848490816@linutronix.de --- arch/x86/include/asm/irqdomain.h | 4 ++-- arch/x86/kernel/apic/htirq.c | 5 +++-- arch/x86/kernel/apic/io_apic.c | 5 +++-- arch/x86/platform/uv/uv_irq.c | 5 +++-- drivers/gpio/gpio-xgene-sb.c | 8 +++++--- drivers/iommu/amd_iommu.c | 5 +++-- drivers/iommu/intel_irq_remapping.c | 5 +++-- drivers/irqchip/irq-gic-v3-its.c | 10 ++++++---- drivers/pinctrl/stm32/pinctrl-stm32.c | 5 +++-- include/linux/irqdomain.h | 2 +- kernel/irq/irqdomain.c | 2 +- kernel/irq/msi.c | 5 +++-- 12 files changed, 36 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h index d26075b52885..1d9091ffa140 100644 --- a/arch/x86/include/asm/irqdomain.h +++ b/arch/x86/include/asm/irqdomain.h @@ -41,8 +41,8 @@ extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg); extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs); -extern void mp_irqdomain_activate(struct irq_domain *domain, - struct irq_data *irq_data); +extern int mp_irqdomain_activate(struct irq_domain *domain, + struct irq_data *irq_data, bool early); extern void mp_irqdomain_deactivate(struct irq_domain *domain, struct irq_data *irq_data); extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain); diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c index 56ccf9346b08..b07075dce8b7 100644 --- a/arch/x86/kernel/apic/htirq.c +++ b/arch/x86/kernel/apic/htirq.c @@ -112,8 +112,8 @@ static void htirq_domain_free(struct irq_domain *domain, unsigned int virq, irq_domain_free_irqs_top(domain, virq, nr_irqs); } -static void htirq_domain_activate(struct irq_domain *domain, - struct irq_data *irq_data) +static int htirq_domain_activate(struct irq_domain *domain, + struct irq_data *irq_data, bool early) { struct ht_irq_msg msg; struct irq_cfg *cfg = irqd_cfg(irq_data); @@ -132,6 +132,7 @@ static void htirq_domain_activate(struct irq_domain *domain, HT_IRQ_LOW_MT_ARBITRATED) | HT_IRQ_LOW_IRQ_MASKED; write_ht_irq_msg(irq_data->irq, &msg); + return 0; } static void htirq_domain_deactivate(struct irq_domain *domain, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 70e48aa6af98..d50e46757f6d 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2977,8 +2977,8 @@ void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, irq_domain_free_irqs_top(domain, virq, nr_irqs); } -void mp_irqdomain_activate(struct irq_domain *domain, - struct irq_data *irq_data) +int mp_irqdomain_activate(struct irq_domain *domain, + struct irq_data *irq_data, bool early) { unsigned long flags; struct irq_pin_list *entry; @@ -2988,6 +2988,7 @@ void mp_irqdomain_activate(struct irq_domain *domain, for_each_irq_pin(entry, data->irq_2_pin) __ioapic_write_entry(entry->apic, entry->pin, data->entry); raw_spin_unlock_irqrestore(&ioapic_lock, flags); + return 0; } void mp_irqdomain_deactivate(struct irq_domain *domain, diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index 03fc397335b7..5f6fd860820a 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -127,10 +127,11 @@ static void uv_domain_free(struct irq_domain *domain, unsigned int virq, * Re-target the irq to the specified CPU and enable the specified MMR located * on the specified blade to allow the sending of MSIs to the specified CPU. */ -static void uv_domain_activate(struct irq_domain *domain, - struct irq_data *irq_data) +static int uv_domain_activate(struct irq_domain *domain, + struct irq_data *irq_data, bool early) { uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data); + return 0; } /* diff --git a/drivers/gpio/gpio-xgene-sb.c b/drivers/gpio/gpio-xgene-sb.c index 033258634b8c..b5843fe6a44d 100644 --- a/drivers/gpio/gpio-xgene-sb.c +++ b/drivers/gpio/gpio-xgene-sb.c @@ -140,8 +140,9 @@ static int xgene_gpio_sb_to_irq(struct gpio_chip *gc, u32 gpio) return irq_create_fwspec_mapping(&fwspec); } -static void xgene_gpio_sb_domain_activate(struct irq_domain *d, - struct irq_data *irq_data) +static int xgene_gpio_sb_domain_activate(struct irq_domain *d, + struct irq_data *irq_data, + bool early) { struct xgene_gpio_sb *priv = d->host_data; u32 gpio = HWIRQ_TO_GPIO(priv, irq_data->hwirq); @@ -150,11 +151,12 @@ static void xgene_gpio_sb_domain_activate(struct irq_domain *d, dev_err(priv->gc.parent, "Unable to configure XGene GPIO standby pin %d as IRQ\n", gpio); - return; + return -ENOSPC; } xgene_gpio_set_bit(&priv->gc, priv->regs + MPA_GPIO_SEL_LO, gpio * 2, 1); + return 0; } static void xgene_gpio_sb_domain_deactivate(struct irq_domain *d, diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 51f8215877f5..ea03f4138f5f 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -4170,8 +4170,8 @@ static void irq_remapping_free(struct irq_domain *domain, unsigned int virq, irq_domain_free_irqs_common(domain, virq, nr_irqs); } -static void irq_remapping_activate(struct irq_domain *domain, - struct irq_data *irq_data) +static int irq_remapping_activate(struct irq_domain *domain, + struct irq_data *irq_data, bool early) { struct amd_ir_data *data = irq_data->chip_data; struct irq_2_irte *irte_info = &data->irq_2_irte; @@ -4180,6 +4180,7 @@ static void irq_remapping_activate(struct irq_domain *domain, if (iommu) iommu->irte_ops->activate(data->entry, irte_info->devid, irte_info->index); + return 0; } static void irq_remapping_deactivate(struct irq_domain *domain, diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index a5b89f6bcdbf..762d84713b7a 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -1389,12 +1389,13 @@ static void intel_irq_remapping_free(struct irq_domain *domain, irq_domain_free_irqs_common(domain, virq, nr_irqs); } -static void intel_irq_remapping_activate(struct irq_domain *domain, - struct irq_data *irq_data) +static int intel_irq_remapping_activate(struct irq_domain *domain, + struct irq_data *irq_data, bool early) { struct intel_ir_data *data = irq_data->chip_data; modify_irte(&data->irq_2_iommu, &data->irte_entry); + return 0; } static void intel_irq_remapping_deactivate(struct irq_domain *domain, diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index e8d89343d613..20e2b5fac7b9 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -2186,8 +2186,8 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, return 0; } -static void its_irq_domain_activate(struct irq_domain *domain, - struct irq_data *d) +static int its_irq_domain_activate(struct irq_domain *domain, + struct irq_data *d, bool early) { struct its_device *its_dev = irq_data_get_irq_chip_data(d); u32 event = its_get_event_id(d); @@ -2205,6 +2205,7 @@ static void its_irq_domain_activate(struct irq_domain *domain, /* Map the GIC IRQ and event to the device */ its_send_mapti(its_dev, d->hwirq, event); + return 0; } static void its_irq_domain_deactivate(struct irq_domain *domain, @@ -2678,8 +2679,8 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq return err; } -static void its_vpe_irq_domain_activate(struct irq_domain *domain, - struct irq_data *d) +static int its_vpe_irq_domain_activate(struct irq_domain *domain, + struct irq_data *d, bool early) { struct its_vpe *vpe = irq_data_get_irq_chip_data(d); @@ -2687,6 +2688,7 @@ static void its_vpe_irq_domain_activate(struct irq_domain *domain, vpe->col_idx = cpumask_first(cpu_online_mask); its_send_vmapp(vpe, true); its_send_vinvall(vpe); + return 0; } static void its_vpe_irq_domain_deactivate(struct irq_domain *domain, diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index 50299ad96659..02b66588cac6 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -289,13 +289,14 @@ static int stm32_gpio_domain_translate(struct irq_domain *d, return 0; } -static void stm32_gpio_domain_activate(struct irq_domain *d, - struct irq_data *irq_data) +static int stm32_gpio_domain_activate(struct irq_domain *d, + struct irq_data *irq_data, bool early) { struct stm32_gpio_bank *bank = d->host_data; struct stm32_pinctrl *pctl = dev_get_drvdata(bank->gpio_chip.parent); regmap_field_write(pctl->irqmux[irq_data->hwirq], bank->bank_nr); + return 0; } static int stm32_gpio_domain_alloc(struct irq_domain *d, diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index de06ce992a2d..9bc07f59b090 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -111,7 +111,7 @@ struct irq_domain_ops { unsigned int nr_irqs, void *arg); void (*free)(struct irq_domain *d, unsigned int virq, unsigned int nr_irqs); - void (*activate)(struct irq_domain *d, struct irq_data *irq_data); + int (*activate)(struct irq_domain *d, struct irq_data *irqd, bool early); void (*deactivate)(struct irq_domain *d, struct irq_data *irq_data); int (*translate)(struct irq_domain *d, struct irq_fwspec *fwspec, unsigned long *out_hwirq, unsigned int *out_type); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 1a75a00ee01f..1423f8a6c75d 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1690,7 +1690,7 @@ static void __irq_domain_activate_irq(struct irq_data *irq_data) if (irq_data->parent_data) __irq_domain_activate_irq(irq_data->parent_data); if (domain->ops->activate) - domain->ops->activate(domain, irq_data); + domain->ops->activate(domain, irq_data, false); } } diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 94ecc0293844..6155fff9f647 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -102,13 +102,14 @@ int msi_domain_set_affinity(struct irq_data *irq_data, return ret; } -static void msi_domain_activate(struct irq_domain *domain, - struct irq_data *irq_data) +static int msi_domain_activate(struct irq_domain *domain, + struct irq_data *irq_data, bool early) { struct msi_msg msg; BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg)); irq_chip_write_msi_msg(irq_data, &msg); + return 0; } static void msi_domain_deactivate(struct irq_domain *domain, -- cgit v1.2.3 From bb9b428a5c832d7abb494fbabac37c515c01c6c4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Sep 2017 23:29:11 +0200 Subject: genirq/irqdomain: Allow irq_domain_activate_irq() to fail Allow irq_domain_activate_irq() to fail. This is required to support a reservation and late vector assignment scheme. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Tested-by: Yu Chen Acked-by: Juergen Gross Cc: Boris Ostrovsky Cc: Tony Luck Cc: Marc Zyngier Cc: Alok Kataria Cc: Joerg Roedel Cc: "Rafael J. Wysocki" Cc: Steven Rostedt Cc: Christoph Hellwig Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Paolo Bonzini Cc: Rui Zhang Cc: "K. Y. Srinivasan" Cc: Arjan van de Ven Cc: Dan Williams Cc: Len Brown Link: https://lkml.kernel.org/r/20170913213152.933882227@linutronix.de --- include/linux/irqdomain.h | 2 +- kernel/irq/chip.c | 9 +++++++-- kernel/irq/internals.h | 3 ++- kernel/irq/irqdomain.c | 40 +++++++++++++++++++++++++--------------- kernel/irq/msi.c | 19 +++++++++++++++++-- 5 files changed, 52 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 9bc07f59b090..8fb877121984 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -441,7 +441,7 @@ extern int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, unsigned int nr_irqs, int node, void *arg, bool realloc, const struct cpumask *affinity); extern void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs); -extern void irq_domain_activate_irq(struct irq_data *irq_data); +extern int irq_domain_activate_irq(struct irq_data *irq_data); extern void irq_domain_deactivate_irq(struct irq_data *irq_data); static inline int irq_domain_alloc_irqs(struct irq_domain *domain, diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 37dd34d922f4..cd5b3eb38082 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -219,7 +219,12 @@ __irq_startup_managed(struct irq_desc *desc, struct cpumask *aff, bool force) */ return IRQ_STARTUP_ABORT; } - irq_domain_activate_irq(d); + /* + * Managed interrupts have reserved resources, so this should not + * happen. + */ + if (WARN_ON(irq_domain_activate_irq(d))) + return IRQ_STARTUP_ABORT; return IRQ_STARTUP_MANAGED; } #else @@ -285,7 +290,7 @@ int irq_activate(struct irq_desc *desc) struct irq_data *d = irq_desc_get_irq_data(desc); if (!irqd_affinity_is_managed(d)) - irq_domain_activate_irq(d); + return irq_domain_activate_irq(d); return 0; } diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 8bd131e4c944..e84d0e3899f6 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -439,9 +439,10 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear) #endif /* !CONFIG_GENERIC_PENDING_IRQ */ #if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY) -static inline void irq_domain_activate_irq(struct irq_data *data) +static inline int irq_domain_activate_irq(struct irq_data *data) { irqd_set_activated(data); + return 0; } static inline void irq_domain_deactivate_irq(struct irq_data *data) { diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 1423f8a6c75d..47e8ddd9e8cf 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1682,28 +1682,35 @@ void irq_domain_free_irqs_parent(struct irq_domain *domain, } EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent); -static void __irq_domain_activate_irq(struct irq_data *irq_data) +static void __irq_domain_deactivate_irq(struct irq_data *irq_data) { if (irq_data && irq_data->domain) { struct irq_domain *domain = irq_data->domain; + if (domain->ops->deactivate) + domain->ops->deactivate(domain, irq_data); if (irq_data->parent_data) - __irq_domain_activate_irq(irq_data->parent_data); - if (domain->ops->activate) - domain->ops->activate(domain, irq_data, false); + __irq_domain_deactivate_irq(irq_data->parent_data); } } -static void __irq_domain_deactivate_irq(struct irq_data *irq_data) +static int __irq_domain_activate_irq(struct irq_data *irqd) { - if (irq_data && irq_data->domain) { - struct irq_domain *domain = irq_data->domain; + int ret = 0; - if (domain->ops->deactivate) - domain->ops->deactivate(domain, irq_data); - if (irq_data->parent_data) - __irq_domain_deactivate_irq(irq_data->parent_data); + if (irqd && irqd->domain) { + struct irq_domain *domain = irqd->domain; + + if (irqd->parent_data) + ret = __irq_domain_activate_irq(irqd->parent_data); + if (!ret && domain->ops->activate) { + ret = domain->ops->activate(domain, irqd, false); + /* Rollback in case of error */ + if (ret && irqd->parent_data) + __irq_domain_deactivate_irq(irqd->parent_data); + } } + return ret; } /** @@ -1714,12 +1721,15 @@ static void __irq_domain_deactivate_irq(struct irq_data *irq_data) * This is the second step to call domain_ops->activate to program interrupt * controllers, so the interrupt could actually get delivered. */ -void irq_domain_activate_irq(struct irq_data *irq_data) +int irq_domain_activate_irq(struct irq_data *irq_data) { - if (!irqd_is_activated(irq_data)) { - __irq_domain_activate_irq(irq_data); + int ret = 0; + + if (!irqd_is_activated(irq_data)) + ret = __irq_domain_activate_irq(irq_data); + if (!ret) irqd_set_activated(irq_data); - } + return ret; } /** diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 6155fff9f647..5ece369950ec 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -401,11 +401,26 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, struct irq_data *irq_data; irq_data = irq_domain_get_irq_data(domain, desc->irq); - irq_domain_activate_irq(irq_data); + ret = irq_domain_activate_irq(irq_data); + if (ret) + goto cleanup; } } - return 0; + +cleanup: + for_each_msi_entry(desc, dev) { + struct irq_data *irqd; + + if (desc->irq == virq) + break; + + irqd = irq_domain_get_irq_data(domain, desc->irq); + if (irqd_is_activated(irqd)) + irq_domain_deactivate_irq(irqd); + } + msi_domain_free_irqs(domain, dev); + return ret; } /** -- cgit v1.2.3 From 42e1cc2dc5b698181ab1ffb7972bd880230c506e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Sep 2017 23:29:12 +0200 Subject: genirq/irqdomain: Propagate early activation Propagate the early activation mode to the irqdomain activate() callbacks. This is required for the upcoming reservation, late vector assignment scheme, so that the early activation call can act accordingly. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Tested-by: Yu Chen Acked-by: Juergen Gross Cc: Boris Ostrovsky Cc: Tony Luck Cc: Marc Zyngier Cc: Alok Kataria Cc: Joerg Roedel Cc: "Rafael J. Wysocki" Cc: Steven Rostedt Cc: Christoph Hellwig Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Paolo Bonzini Cc: Rui Zhang Cc: "K. Y. Srinivasan" Cc: Arjan van de Ven Cc: Dan Williams Cc: Len Brown Link: https://lkml.kernel.org/r/20170913213153.028353660@linutronix.de --- arch/x86/kernel/apic/io_apic.c | 4 ++-- include/linux/irqdomain.h | 2 +- kernel/irq/chip.c | 4 ++-- kernel/irq/internals.h | 2 +- kernel/irq/irqdomain.c | 11 ++++++----- kernel/irq/msi.c | 2 +- 6 files changed, 13 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index d50e46757f6d..6f1007fd9783 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2096,7 +2096,7 @@ static inline void __init check_timer(void) unmask_ioapic_irq(irq_get_irq_data(0)); } irq_domain_deactivate_irq(irq_data); - irq_domain_activate_irq(irq_data); + irq_domain_activate_irq(irq_data, false); if (timer_irq_works()) { if (disable_timer_pin_1 > 0) clear_IO_APIC_pin(0, pin1); @@ -2118,7 +2118,7 @@ static inline void __init check_timer(void) */ replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2); irq_domain_deactivate_irq(irq_data); - irq_domain_activate_irq(irq_data); + irq_domain_activate_irq(irq_data, false); legacy_pic->unmask(0); if (timer_irq_works()) { apic_printk(APIC_QUIET, KERN_INFO "....... works.\n"); diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 8fb877121984..7d0c6c144708 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -441,7 +441,7 @@ extern int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, unsigned int nr_irqs, int node, void *arg, bool realloc, const struct cpumask *affinity); extern void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs); -extern int irq_domain_activate_irq(struct irq_data *irq_data); +extern int irq_domain_activate_irq(struct irq_data *irq_data, bool early); extern void irq_domain_deactivate_irq(struct irq_data *irq_data); static inline int irq_domain_alloc_irqs(struct irq_domain *domain, diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index cd5b3eb38082..82333835ac66 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -223,7 +223,7 @@ __irq_startup_managed(struct irq_desc *desc, struct cpumask *aff, bool force) * Managed interrupts have reserved resources, so this should not * happen. */ - if (WARN_ON(irq_domain_activate_irq(d))) + if (WARN_ON(irq_domain_activate_irq(d, false))) return IRQ_STARTUP_ABORT; return IRQ_STARTUP_MANAGED; } @@ -290,7 +290,7 @@ int irq_activate(struct irq_desc *desc) struct irq_data *d = irq_desc_get_irq_data(desc); if (!irqd_affinity_is_managed(d)) - return irq_domain_activate_irq(d); + return irq_domain_activate_irq(d, false); return 0; } diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index e84d0e3899f6..a0327136e469 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -439,7 +439,7 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear) #endif /* !CONFIG_GENERIC_PENDING_IRQ */ #if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY) -static inline int irq_domain_activate_irq(struct irq_data *data) +static inline int irq_domain_activate_irq(struct irq_data *data, bool early) { irqd_set_activated(data); return 0; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 47e8ddd9e8cf..b50f737574ae 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1694,7 +1694,7 @@ static void __irq_domain_deactivate_irq(struct irq_data *irq_data) } } -static int __irq_domain_activate_irq(struct irq_data *irqd) +static int __irq_domain_activate_irq(struct irq_data *irqd, bool early) { int ret = 0; @@ -1702,9 +1702,10 @@ static int __irq_domain_activate_irq(struct irq_data *irqd) struct irq_domain *domain = irqd->domain; if (irqd->parent_data) - ret = __irq_domain_activate_irq(irqd->parent_data); + ret = __irq_domain_activate_irq(irqd->parent_data, + early); if (!ret && domain->ops->activate) { - ret = domain->ops->activate(domain, irqd, false); + ret = domain->ops->activate(domain, irqd, early); /* Rollback in case of error */ if (ret && irqd->parent_data) __irq_domain_deactivate_irq(irqd->parent_data); @@ -1721,12 +1722,12 @@ static int __irq_domain_activate_irq(struct irq_data *irqd) * This is the second step to call domain_ops->activate to program interrupt * controllers, so the interrupt could actually get delivered. */ -int irq_domain_activate_irq(struct irq_data *irq_data) +int irq_domain_activate_irq(struct irq_data *irq_data, bool early) { int ret = 0; if (!irqd_is_activated(irq_data)) - ret = __irq_domain_activate_irq(irq_data); + ret = __irq_domain_activate_irq(irq_data, early); if (!ret) irqd_set_activated(irq_data); return ret; diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 5ece369950ec..d7553d015175 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -401,7 +401,7 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, struct irq_data *irq_data; irq_data = irq_domain_get_irq_data(domain, desc->irq); - ret = irq_domain_activate_irq(irq_data); + ret = irq_domain_activate_irq(irq_data, true); if (ret) goto cleanup; } -- cgit v1.2.3 From 22d0b12f3560d3b3264ee79faa1c05a5060fb916 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Sep 2017 23:29:13 +0200 Subject: genirq/irqdomain: Add force reactivation flag to irq domains Allow irqdomains to tell the core code, that after early activation the interrupt needs to be reactivated at request_irq() time. This allows reservation of vectors at early activation time and actual vector assignment at request_irq() time. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Tested-by: Yu Chen Acked-by: Juergen Gross Cc: Boris Ostrovsky Cc: Tony Luck Cc: Marc Zyngier Cc: Alok Kataria Cc: Joerg Roedel Cc: "Rafael J. Wysocki" Cc: Steven Rostedt Cc: Christoph Hellwig Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Paolo Bonzini Cc: Rui Zhang Cc: "K. Y. Srinivasan" Cc: Arjan van de Ven Cc: Dan Williams Cc: Len Brown Link: https://lkml.kernel.org/r/20170913213153.106242536@linutronix.de --- include/linux/msi.h | 5 +++++ kernel/irq/msi.c | 2 ++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 80e3b562bef6..eff16ef81f43 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -283,6 +283,11 @@ enum { MSI_FLAG_PCI_MSIX = (1 << 3), /* Needs early activate, required for PCI */ MSI_FLAG_ACTIVATE_EARLY = (1 << 4), + /* + * Must reactivate when irq is started even when + * MSI_FLAG_ACTIVATE_EARLY has been set. + */ + MSI_FLAG_MUST_REACTIVATE = (1 << 5), }; int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index d7553d015175..edb987b2c58d 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -404,6 +404,8 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, ret = irq_domain_activate_irq(irq_data, true); if (ret) goto cleanup; + if (info->flags & MSI_FLAG_MUST_REACTIVATE) + irqd_clr_activated(irq_data); } } return 0; -- cgit v1.2.3 From 2f75d9e1c90511bff6d1ce4de94503cc28fec032 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Sep 2017 23:29:14 +0200 Subject: genirq: Implement bitmap matrix allocator Implement the infrastructure for a simple bitmap based allocator, which will replace the x86 vector allocator. It's in the core code as other architectures might be able to reuse/extend it. For now it only implements allocations for single CPUs, but it's simple to add multi CPU allocation support if required. The concept is rather simple: Global information: system_vector bitmap global accounting PerCPU information: allocation bitmap managed allocation bitmap local accounting The system vector bitmap is used to exclude vectors system wide from the allocation space. The allocation bitmap is used to keep track of per cpu used vectors. The managed allocation bitmap is used to reserve vectors for managed interrupts. When a regular (non managed) interrupt allocation happens then the following rule applies: tmpmap = system_map | alloc_map | managed_map find_zero_bit(tmpmap) Oring the bitmaps together gives the real available space. The same rule applies for reserving a managed interrupt vector. But contrary to the regular interrupts the reservation only marks the bit in the managed map and therefor excludes it from the regular allocations. The managed map is only cleaned out when the a managed interrupt is completely released and it stays alive accross CPU offline/online operations. For managed interrupt allocations the rule is: tmpmap = managed_map & ~alloc_map find_first_bit(tmpmap) This returns the first bit which is in the managed map, but not yet allocated in the allocation map. The allocation marks it in the allocation map and hands it back to the caller for use. The rest of the code are helper functions to handle the various requirements and the accounting which are necessary to replace the x86 vector allocation code. The result is a single patch as the evolution of this infrastructure cannot be represented in bits and pieces. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Tested-by: Yu Chen Acked-by: Juergen Gross Cc: Boris Ostrovsky Cc: Tony Luck Cc: Marc Zyngier Cc: Alok Kataria Cc: Joerg Roedel Cc: "Rafael J. Wysocki" Cc: Steven Rostedt Cc: Christoph Hellwig Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Paolo Bonzini Cc: Rui Zhang Cc: "K. Y. Srinivasan" Cc: Arjan van de Ven Cc: Dan Williams Cc: Chris Metcalf Cc: Len Brown Link: https://lkml.kernel.org/r/20170913213153.185437174@linutronix.de --- include/linux/irq.h | 22 +++ kernel/irq/Kconfig | 3 + kernel/irq/Makefile | 1 + kernel/irq/matrix.c | 428 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 454 insertions(+) create mode 100644 kernel/irq/matrix.c (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index d4728bf6a537..fda8da7c45e7 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -1113,6 +1113,28 @@ static inline u32 irq_reg_readl(struct irq_chip_generic *gc, return readl(gc->reg_base + reg_offset); } +struct irq_matrix; +struct irq_matrix *irq_alloc_matrix(unsigned int matrix_bits, + unsigned int alloc_start, + unsigned int alloc_end); +void irq_matrix_online(struct irq_matrix *m); +void irq_matrix_offline(struct irq_matrix *m); +void irq_matrix_assign_system(struct irq_matrix *m, unsigned int bit, bool replace); +int irq_matrix_reserve_managed(struct irq_matrix *m, const struct cpumask *msk); +void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk); +int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu); +void irq_matrix_reserve(struct irq_matrix *m); +void irq_matrix_remove_reserved(struct irq_matrix *m); +int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk, + bool reserved, unsigned int *mapped_cpu); +void irq_matrix_free(struct irq_matrix *m, unsigned int cpu, + unsigned int bit, bool managed); +void irq_matrix_assign(struct irq_matrix *m, unsigned int bit); +unsigned int irq_matrix_available(struct irq_matrix *m, bool cpudown); +unsigned int irq_matrix_allocated(struct irq_matrix *m); +unsigned int irq_matrix_reserved(struct irq_matrix *m); +void irq_matrix_debug_show(struct seq_file *sf, struct irq_matrix *m, int ind); + /* Contrary to Linux irqs, for hardware irqs the irq number 0 is valid */ #define INVALID_HWIRQ (~0UL) irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu); diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index a117adf7084b..ac1a3e29d3b9 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -97,6 +97,9 @@ config HANDLE_DOMAIN_IRQ config IRQ_TIMINGS bool +config GENERIC_IRQ_MATRIX_ALLOCATOR + bool + config IRQ_DOMAIN_DEBUG bool "Expose hardware/virtual IRQ mapping via debugfs" depends on IRQ_DOMAIN && DEBUG_FS diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index 1970cafe8f2a..329c9193b4bf 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -13,3 +13,4 @@ obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o obj-$(CONFIG_SMP) += affinity.o obj-$(CONFIG_GENERIC_IRQ_DEBUGFS) += debugfs.o +obj-$(CONFIG_GENERIC_IRQ_MATRIX_ALLOCATOR) += matrix.o diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c new file mode 100644 index 000000000000..7b2b4fbde1e2 --- /dev/null +++ b/kernel/irq/matrix.c @@ -0,0 +1,428 @@ +/* + * Copyright (C) 2017 Thomas Gleixner + * + * SPDX-License-Identifier: GPL-2.0 + */ +#include +#include +#include +#include +#include +#include + +#define IRQ_MATRIX_SIZE (BITS_TO_LONGS(IRQ_MATRIX_BITS) * sizeof(unsigned long)) + +struct cpumap { + unsigned int available; + unsigned int allocated; + unsigned int managed; + bool online; + unsigned long alloc_map[IRQ_MATRIX_SIZE]; + unsigned long managed_map[IRQ_MATRIX_SIZE]; +}; + +struct irq_matrix { + unsigned int matrix_bits; + unsigned int alloc_start; + unsigned int alloc_end; + unsigned int alloc_size; + unsigned int global_available; + unsigned int global_reserved; + unsigned int systembits_inalloc; + unsigned int total_allocated; + unsigned int online_maps; + struct cpumap __percpu *maps; + unsigned long scratch_map[IRQ_MATRIX_SIZE]; + unsigned long system_map[IRQ_MATRIX_SIZE]; +}; + +/** + * irq_alloc_matrix - Allocate a irq_matrix structure and initialize it + * @matrix_bits: Number of matrix bits must be <= IRQ_MATRIX_BITS + * @alloc_start: From which bit the allocation search starts + * @alloc_end: At which bit the allocation search ends, i.e first + * invalid bit + */ +__init struct irq_matrix *irq_alloc_matrix(unsigned int matrix_bits, + unsigned int alloc_start, + unsigned int alloc_end) +{ + struct irq_matrix *m; + + if (matrix_bits > IRQ_MATRIX_BITS) + return NULL; + + m = kzalloc(sizeof(*m), GFP_KERNEL); + if (!m) + return NULL; + + m->matrix_bits = matrix_bits; + m->alloc_start = alloc_start; + m->alloc_end = alloc_end; + m->alloc_size = alloc_end - alloc_start; + m->maps = alloc_percpu(*m->maps); + if (!m->maps) { + kfree(m); + return NULL; + } + return m; +} + +/** + * irq_matrix_online - Bring the local CPU matrix online + * @m: Matrix pointer + */ +void irq_matrix_online(struct irq_matrix *m) +{ + struct cpumap *cm = this_cpu_ptr(m->maps); + + BUG_ON(cm->online); + + bitmap_zero(cm->alloc_map, m->matrix_bits); + cm->available = m->alloc_size - (cm->managed + m->systembits_inalloc); + cm->allocated = 0; + m->global_available += cm->available; + cm->online = true; + m->online_maps++; +} + +/** + * irq_matrix_offline - Bring the local CPU matrix offline + * @m: Matrix pointer + */ +void irq_matrix_offline(struct irq_matrix *m) +{ + struct cpumap *cm = this_cpu_ptr(m->maps); + + /* Update the global available size */ + m->global_available -= cm->available; + cm->online = false; + m->online_maps--; +} + +static unsigned int matrix_alloc_area(struct irq_matrix *m, struct cpumap *cm, + unsigned int num, bool managed) +{ + unsigned int area, start = m->alloc_start; + unsigned int end = m->alloc_end; + + bitmap_or(m->scratch_map, cm->managed_map, m->system_map, end); + bitmap_or(m->scratch_map, m->scratch_map, cm->alloc_map, end); + area = bitmap_find_next_zero_area(m->scratch_map, end, start, num, 0); + if (area >= end) + return area; + if (managed) + bitmap_set(cm->managed_map, area, num); + else + bitmap_set(cm->alloc_map, area, num); + return area; +} + +/** + * irq_matrix_assign_system - Assign system wide entry in the matrix + * @m: Matrix pointer + * @bit: Which bit to reserve + * @replace: Replace an already allocated vector with a system + * vector at the same bit position. + * + * The BUG_ON()s below are on purpose. If this goes wrong in the + * early boot process, then the chance to survive is about zero. + * If this happens when the system is life, it's not much better. + */ +void irq_matrix_assign_system(struct irq_matrix *m, unsigned int bit, + bool replace) +{ + struct cpumap *cm = this_cpu_ptr(m->maps); + + BUG_ON(bit > m->matrix_bits); + BUG_ON(m->online_maps > 1 || (m->online_maps && !replace)); + + set_bit(bit, m->system_map); + if (replace) { + BUG_ON(!test_and_clear_bit(bit, cm->alloc_map)); + cm->allocated--; + m->total_allocated--; + } + if (bit >= m->alloc_start && bit < m->alloc_end) + m->systembits_inalloc++; +} + +/** + * irq_matrix_reserve_managed - Reserve a managed interrupt in a CPU map + * @m: Matrix pointer + * @msk: On which CPUs the bits should be reserved. + * + * Can be called for offline CPUs. Note, this will only reserve one bit + * on all CPUs in @msk, but it's not guaranteed that the bits are at the + * same offset on all CPUs + */ +int irq_matrix_reserve_managed(struct irq_matrix *m, const struct cpumask *msk) +{ + unsigned int cpu, failed_cpu; + + for_each_cpu(cpu, msk) { + struct cpumap *cm = per_cpu_ptr(m->maps, cpu); + unsigned int bit; + + bit = matrix_alloc_area(m, cm, 1, true); + if (bit >= m->alloc_end) + goto cleanup; + cm->managed++; + if (cm->online) { + cm->available--; + m->global_available--; + } + } + return 0; +cleanup: + failed_cpu = cpu; + for_each_cpu(cpu, msk) { + if (cpu == failed_cpu) + break; + irq_matrix_remove_managed(m, cpumask_of(cpu)); + } + return -ENOSPC; +} + +/** + * irq_matrix_remove_managed - Remove managed interrupts in a CPU map + * @m: Matrix pointer + * @msk: On which CPUs the bits should be removed + * + * Can be called for offline CPUs + * + * This removes not allocated managed interrupts from the map. It does + * not matter which one because the managed interrupts free their + * allocation when they shut down. If not, the accounting is screwed, + * but all what can be done at this point is warn about it. + */ +void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk) +{ + unsigned int cpu; + + for_each_cpu(cpu, msk) { + struct cpumap *cm = per_cpu_ptr(m->maps, cpu); + unsigned int bit, end = m->alloc_end; + + if (WARN_ON_ONCE(!cm->managed)) + continue; + + /* Get managed bit which are not allocated */ + bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end); + + bit = find_first_bit(m->scratch_map, end); + if (WARN_ON_ONCE(bit >= end)) + continue; + + clear_bit(bit, cm->managed_map); + + cm->managed--; + if (cm->online) { + cm->available++; + m->global_available++; + } + } +} + +/** + * irq_matrix_alloc_managed - Allocate a managed interrupt in a CPU map + * @m: Matrix pointer + * @cpu: On which CPU the interrupt should be allocated + */ +int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu) +{ + struct cpumap *cm = per_cpu_ptr(m->maps, cpu); + unsigned int bit, end = m->alloc_end; + + /* Get managed bit which are not allocated */ + bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end); + bit = find_first_bit(m->scratch_map, end); + if (bit >= end) + return -ENOSPC; + set_bit(bit, cm->alloc_map); + cm->allocated++; + m->total_allocated++; + return bit; +} + +/** + * irq_matrix_assign - Assign a preallocated interrupt in the local CPU map + * @m: Matrix pointer + * @bit: Which bit to mark + * + * This should only be used to mark preallocated vectors + */ +void irq_matrix_assign(struct irq_matrix *m, unsigned int bit) +{ + struct cpumap *cm = this_cpu_ptr(m->maps); + + if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end)) + return; + if (WARN_ON_ONCE(test_and_set_bit(bit, cm->alloc_map))) + return; + cm->allocated++; + m->total_allocated++; + cm->available--; + m->global_available--; +} + +/** + * irq_matrix_reserve - Reserve interrupts + * @m: Matrix pointer + * + * This is merily a book keeping call. It increments the number of globally + * reserved interrupt bits w/o actually allocating them. This allows to + * setup interrupt descriptors w/o assigning low level resources to it. + * The actual allocation happens when the interrupt gets activated. + */ +void irq_matrix_reserve(struct irq_matrix *m) +{ + if (m->global_reserved <= m->global_available && + m->global_reserved + 1 > m->global_available) + pr_warn("Interrupt reservation exceeds available resources\n"); + + m->global_reserved++; +} + +/** + * irq_matrix_remove_reserved - Remove interrupt reservation + * @m: Matrix pointer + * + * This is merily a book keeping call. It decrements the number of globally + * reserved interrupt bits. This is used to undo irq_matrix_reserve() when the + * interrupt was never in use and a real vector allocated, which undid the + * reservation. + */ +void irq_matrix_remove_reserved(struct irq_matrix *m) +{ + m->global_reserved--; +} + +/** + * irq_matrix_alloc - Allocate a regular interrupt in a CPU map + * @m: Matrix pointer + * @msk: Which CPUs to search in + * @reserved: Allocate previously reserved interrupts + * @mapped_cpu: Pointer to store the CPU for which the irq was allocated + */ +int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk, + bool reserved, unsigned int *mapped_cpu) +{ + unsigned int cpu; + + for_each_cpu(cpu, msk) { + struct cpumap *cm = per_cpu_ptr(m->maps, cpu); + unsigned int bit; + + if (!cm->online) + continue; + + bit = matrix_alloc_area(m, cm, 1, false); + if (bit < m->alloc_end) { + cm->allocated++; + cm->available--; + m->total_allocated++; + m->global_available--; + if (reserved) + m->global_reserved--; + *mapped_cpu = cpu; + return bit; + } + } + return -ENOSPC; +} + +/** + * irq_matrix_free - Free allocated interrupt in the matrix + * @m: Matrix pointer + * @cpu: Which CPU map needs be updated + * @bit: The bit to remove + * @managed: If true, the interrupt is managed and not accounted + * as available. + */ +void irq_matrix_free(struct irq_matrix *m, unsigned int cpu, + unsigned int bit, bool managed) +{ + struct cpumap *cm = per_cpu_ptr(m->maps, cpu); + + if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end)) + return; + + if (cm->online) { + clear_bit(bit, cm->alloc_map); + cm->allocated--; + m->total_allocated--; + if (!managed) { + cm->available++; + m->global_available++; + } + } +} + +/** + * irq_matrix_available - Get the number of globally available irqs + * @m: Pointer to the matrix to query + * @cpudown: If true, the local CPU is about to go down, adjust + * the number of available irqs accordingly + */ +unsigned int irq_matrix_available(struct irq_matrix *m, bool cpudown) +{ + struct cpumap *cm = this_cpu_ptr(m->maps); + + return m->global_available - cpudown ? cm->available : 0; +} + +/** + * irq_matrix_reserved - Get the number of globally reserved irqs + * @m: Pointer to the matrix to query + */ +unsigned int irq_matrix_reserved(struct irq_matrix *m) +{ + return m->global_reserved; +} + +/** + * irq_matrix_allocated - Get the number of allocated irqs on the local cpu + * @m: Pointer to the matrix to search + * + * This returns number of allocated irqs + */ +unsigned int irq_matrix_allocated(struct irq_matrix *m) +{ + struct cpumap *cm = this_cpu_ptr(m->maps); + + return cm->allocated; +} + +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS +/** + * irq_matrix_debug_show - Show detailed allocation information + * @sf: Pointer to the seq_file to print to + * @m: Pointer to the matrix allocator + * @ind: Indentation for the print format + * + * Note, this is a lockless snapshot. + */ +void irq_matrix_debug_show(struct seq_file *sf, struct irq_matrix *m, int ind) +{ + unsigned int nsys = bitmap_weight(m->system_map, m->matrix_bits); + int cpu; + + seq_printf(sf, "Online bitmaps: %6u\n", m->online_maps); + seq_printf(sf, "Global available: %6u\n", m->global_available); + seq_printf(sf, "Global reserved: %6u\n", m->global_reserved); + seq_printf(sf, "Total allocated: %6u\n", m->total_allocated); + seq_printf(sf, "System: %u: %*pbl\n", nsys, m->matrix_bits, + m->system_map); + seq_printf(sf, "%*s| CPU | avl | man | act | vectors\n", ind, " "); + cpus_read_lock(); + for_each_online_cpu(cpu) { + struct cpumap *cm = per_cpu_ptr(m->maps, cpu); + + seq_printf(sf, "%*s %4d %4u %4u %4u %*pbl\n", ind, " ", + cpu, cm->available, cm->managed, cm->allocated, + m->matrix_bits, cm->alloc_map); + } + cpus_read_unlock(); +} +#endif -- cgit v1.2.3 From 4c3711d7fb4763c63b2654f2d07cbe21ca5aadd4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 31 Aug 2017 17:12:48 +0200 Subject: timekeeping: Provide NMI safe access to clock realtime The configurable printk timestamping wants access to clock realtime. Right now there is no ktime_get_real_fast_ns() accessor because reading the monotonic base and the realtime offset cannot be done atomically. Contrary to boot time this offset can change during runtime and cause half updated readouts. struct tk_read_base was fully packed when the fast timekeeper access was implemented. commit ceea5e3771ed ("time: Fix clock->read(clock) race around clocksource changes") removed the 'read' function pointer from the structure, but of course left the comment stale. So now the structure can fit a new 64bit member w/o violating the cache line constraints. Add real_base to tk_read_base and update it in the fast timekeeper update sequence. Implement an accessor which follows the same scheme as the accessor to clock monotonic, but uses the new real_base to access clock real time. The runtime overhead for updating real_base is minimal as it just adds two cache hot values and stores them into an already dirtied cache line along with the other fast timekeeper updates. Signed-off-by: Thomas Gleixner Cc: Prarit Bhargava Cc: John Stultz Cc: Peter Zijlstra Link: https://lkml.kernel.org/r/1505757060-2004-3-git-send-email-prarit@redhat.com --- include/linux/timekeeper_internal.h | 6 +++++- include/linux/timekeeping.h | 1 + kernel/time/timekeeping.c | 35 +++++++++++++++++++++++++++++++++++ 3 files changed, 41 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 0a0a53daf2a2..98f645ee8409 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -13,19 +13,22 @@ /** * struct tk_read_base - base structure for timekeeping readout * @clock: Current clocksource used for timekeeping. - * @read: Read function of @clock * @mask: Bitmask for two's complement subtraction of non 64bit clocks * @cycle_last: @clock cycle value at last update * @mult: (NTP adjusted) multiplier for scaled math conversion * @shift: Shift value for scaled math conversion * @xtime_nsec: Shifted (fractional) nano seconds offset for readout * @base: ktime_t (nanoseconds) base time for readout + * @base_real: Nanoseconds base value for clock REALTIME readout * * This struct has size 56 byte on 64 bit. Together with a seqcount it * occupies a single 64byte cache line. * * The struct is separate from struct timekeeper as it is also used * for a fast NMI safe accessors. + * + * @base_real is for the fast NMI safe accessor to allow reading clock + * realtime from any context. */ struct tk_read_base { struct clocksource *clock; @@ -35,6 +38,7 @@ struct tk_read_base { u32 shift; u64 xtime_nsec; ktime_t base; + u64 base_real; }; /** diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index ddc229ff6d1e..eb98cbdbb323 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -239,6 +239,7 @@ static inline u64 ktime_get_raw_ns(void) extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); +extern u64 ktime_get_real_fast_ns(void); /* * Timespec interfaces utilizing the ktime based ones diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 6a92794427c9..8af77006e937 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -496,6 +496,39 @@ u64 notrace ktime_get_boot_fast_ns(void) } EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); + +/* + * See comment for __ktime_get_fast_ns() vs. timestamp ordering + */ +static __always_inline u64 __ktime_get_real_fast_ns(struct tk_fast *tkf) +{ + struct tk_read_base *tkr; + unsigned int seq; + u64 now; + + do { + seq = raw_read_seqcount_latch(&tkf->seq); + tkr = tkf->base + (seq & 0x01); + now = ktime_to_ns(tkr->base_real); + + now += timekeeping_delta_to_ns(tkr, + clocksource_delta( + tk_clock_read(tkr), + tkr->cycle_last, + tkr->mask)); + } while (read_seqcount_retry(&tkf->seq, seq)); + + return now; +} + +/** + * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. + */ +u64 ktime_get_real_fast_ns(void) +{ + return __ktime_get_real_fast_ns(&tk_fast_mono); +} + /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. @@ -514,6 +547,7 @@ static void halt_fast_timekeeper(struct timekeeper *tk) memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); tkr_dummy.clock = &dummy_clock; + tkr_dummy.base_real = tkr->base + tk->offs_real; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; @@ -661,6 +695,7 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); + tk->tkr_mono.base_real = tk->tkr_mono.base + tk->offs_real; update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); -- cgit v1.2.3 From 404376af788a76cca760efdc05f26fd73bd94b17 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 17 Sep 2017 19:07:10 -0700 Subject: Documentation: kernel-api: add bitmap operations from linux/bitmap.h Add to kernel-api Bitmap Operations section. Fix kernel-doc nitpicks in . Signed-off-by: Randy Dunlap Acked-by: Yury Norov Signed-off-by: Jonathan Corbet --- Documentation/core-api/kernel-api.rst | 3 +++ include/linux/bitmap.h | 9 +++++---- 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index e557509574a0..f37c73faa5b7 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -59,6 +59,9 @@ Bitmap Operations .. kernel-doc:: lib/bitmap.c :internal: +.. kernel-doc:: include/linux/bitmap.h + :internal: + Command-line Parsing -------------------- diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 700cf5f67118..5c4178016b1e 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -360,8 +360,9 @@ static inline int bitmap_parse(const char *buf, unsigned int buflen, return __bitmap_parse(buf, buflen, 0, maskp, nmaskbits); } -/* +/** * BITMAP_FROM_U64() - Represent u64 value in the format suitable for bitmap. + * @n: u64 value * * Linux bitmaps are internally arrays of unsigned longs, i.e. 32-bit * integers in 32-bit environment, and 64-bit integers in 64-bit one. @@ -392,14 +393,14 @@ static inline int bitmap_parse(const char *buf, unsigned int buflen, ((unsigned long) ((u64)(n) >> 32)) #endif -/* +/** * bitmap_from_u64 - Check and swap words within u64. * @mask: source bitmap * @dst: destination bitmap * - * In 32-bit Big Endian kernel, when using (u32 *)(&val)[*] + * In 32-bit Big Endian kernel, when using ``(u32 *)(&val)[*]`` * to read u64 mask, we will get the wrong word. - * That is "(u32 *)(&val)[0]" gets the upper 32 bits, + * That is ``(u32 *)(&val)[0]`` gets the upper 32 bits, * but we expect the lower 32-bits of u64. */ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) -- cgit v1.2.3 From 1ea6c46a23f1213d1972bfae220db5c165e27bba Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sat, 6 May 2017 15:59:54 +0200 Subject: sched/fair: Propagate an effective runnable_load_avg The load balancer uses runnable_load_avg as load indicator. For !cgroup this is: runnable_load_avg = \Sum se->avg.load_avg ; where se->on_rq That is, a direct sum of all runnable tasks on that runqueue. As opposed to load_avg, which is a sum of all tasks on the runqueue, which includes a blocked component. However, in the cgroup case, this comes apart since the group entities are always runnable, even if most of their constituent entities are blocked. Therefore introduce a runnable_weight which for task entities is the same as the regular weight, but for group entities is a fraction of the entity weight and represents the runnable part of the group runqueue. Then propagate this load through the PELT hierarchy to arrive at an effective runnable load avgerage -- which we should not confuse with the canonical runnable load average. Suggested-by: Tejun Heo Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 + kernel/sched/debug.c | 8 ++- kernel/sched/fair.c | 172 +++++++++++++++++++++++++++++++++----------------- kernel/sched/sched.h | 3 +- 4 files changed, 124 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 26a7df4e558c..bdd6ad6fcce1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -331,9 +331,11 @@ struct load_weight { struct sched_avg { u64 last_update_time; u64 load_sum; + u64 runnable_load_sum; u32 util_sum; u32 period_contrib; unsigned long load_avg; + unsigned long runnable_load_avg; unsigned long util_avg; }; @@ -376,6 +378,7 @@ struct sched_statistics { struct sched_entity { /* For load-balancing: */ struct load_weight load; + unsigned long runnable_weight; struct rb_node run_node; struct list_head group_node; unsigned int on_rq; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 2e039a81864c..1ca0130ed4f9 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -441,9 +441,11 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group P_SCHEDSTAT(se->statistics.wait_count); } P(se->load.weight); + P(se->runnable_weight); #ifdef CONFIG_SMP P(se->avg.load_avg); P(se->avg.util_avg); + P(se->avg.runnable_load_avg); #endif #undef PN_SCHEDSTAT @@ -558,10 +560,11 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running); SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight); #ifdef CONFIG_SMP + SEQ_printf(m, " .%-30s: %ld\n", "runnable_weight", cfs_rq->runnable_weight); SEQ_printf(m, " .%-30s: %lu\n", "load_avg", cfs_rq->avg.load_avg); SEQ_printf(m, " .%-30s: %lu\n", "runnable_load_avg", - cfs_rq->runnable_load_avg); + cfs_rq->avg.runnable_load_avg); SEQ_printf(m, " .%-30s: %lu\n", "util_avg", cfs_rq->avg.util_avg); SEQ_printf(m, " .%-30s: %ld\n", "removed.load_avg", @@ -1006,10 +1009,13 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, "nr_involuntary_switches", (long long)p->nivcsw); P(se.load.weight); + P(se.runnable_weight); #ifdef CONFIG_SMP P(se.avg.load_sum); + P(se.avg.runnable_load_sum); P(se.avg.util_sum); P(se.avg.load_avg); + P(se.avg.runnable_load_avg); P(se.avg.util_avg); P(se.avg.last_update_time); #endif diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 086a5d979720..10d2000fca2d 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -730,8 +730,9 @@ void init_entity_runnable_average(struct sched_entity *se) * nothing has been attached to the task group yet. */ if (entity_is_task(se)) - sa->load_avg = scale_load_down(se->load.weight); - sa->load_sum = LOAD_AVG_MAX; + sa->runnable_load_avg = sa->load_avg = scale_load_down(se->load.weight); + sa->runnable_load_sum = sa->load_sum = LOAD_AVG_MAX; + /* * At this point, util_avg won't be used in select_task_rq_fair anyway */ @@ -2731,25 +2732,35 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) #ifdef CONFIG_SMP /* - * XXX we want to get rid of this helper and use the full load resolution. + * XXX we want to get rid of these helpers and use the full load resolution. */ static inline long se_weight(struct sched_entity *se) { return scale_load_down(se->load.weight); } +static inline long se_runnable(struct sched_entity *se) +{ + return scale_load_down(se->runnable_weight); +} + static inline void enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - cfs_rq->runnable_load_avg += se->avg.load_avg; - cfs_rq->runnable_load_sum += se_weight(se) * se->avg.load_sum; + cfs_rq->runnable_weight += se->runnable_weight; + + cfs_rq->avg.runnable_load_avg += se->avg.runnable_load_avg; + cfs_rq->avg.runnable_load_sum += se_runnable(se) * se->avg.runnable_load_sum; } static inline void dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - sub_positive(&cfs_rq->runnable_load_avg, se->avg.load_avg); - sub_positive(&cfs_rq->runnable_load_sum, se_weight(se) * se->avg.load_sum); + cfs_rq->runnable_weight -= se->runnable_weight; + + sub_positive(&cfs_rq->avg.runnable_load_avg, se->avg.runnable_load_avg); + sub_positive(&cfs_rq->avg.runnable_load_sum, + se_runnable(se) * se->avg.runnable_load_sum); } static inline void @@ -2777,7 +2788,7 @@ dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { } #endif static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, - unsigned long weight) + unsigned long weight, unsigned long runnable) { if (se->on_rq) { /* commit outstanding execution time */ @@ -2788,11 +2799,17 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, } dequeue_load_avg(cfs_rq, se); + se->runnable_weight = runnable; update_load_set(&se->load, weight); #ifdef CONFIG_SMP - se->avg.load_avg = div_u64(se_weight(se) * se->avg.load_sum, - LOAD_AVG_MAX - 1024 + se->avg.period_contrib); + do { + u32 divider = LOAD_AVG_MAX - 1024 + se->avg.period_contrib; + + se->avg.load_avg = div_u64(se_weight(se) * se->avg.load_sum, divider); + se->avg.runnable_load_avg = + div_u64(se_runnable(se) * se->avg.runnable_load_sum, divider); + } while (0); #endif enqueue_load_avg(cfs_rq, se); @@ -2809,7 +2826,7 @@ void reweight_task(struct task_struct *p, int prio) struct load_weight *load = &se->load; unsigned long weight = scale_load(sched_prio_to_weight[prio]); - reweight_entity(cfs_rq, se, weight); + reweight_entity(cfs_rq, se, weight, weight); load->inv_weight = sched_prio_to_wmult[prio]; } @@ -2917,31 +2934,45 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq) static inline int throttled_hierarchy(struct cfs_rq *cfs_rq); -static void update_cfs_shares(struct sched_entity *se) +/* + * Recomputes the group entity based on the current state of its group + * runqueue. + */ +static void update_cfs_group(struct sched_entity *se) { - struct cfs_rq *cfs_rq = group_cfs_rq(se); - long shares; + struct cfs_rq *gcfs_rq = group_cfs_rq(se); + long shares, runnable; - if (!cfs_rq) + if (!gcfs_rq) return; - if (throttled_hierarchy(cfs_rq)) + if (throttled_hierarchy(gcfs_rq)) return; #ifndef CONFIG_SMP - shares = READ_ONCE(cfs_rq->tg->shares); + runnable = shares = READ_ONCE(gcfs_rq->tg->shares); if (likely(se->load.weight == shares)) return; #else - shares = calc_cfs_shares(cfs_rq); + shares = calc_cfs_shares(gcfs_rq); + /* + * The hierarchical runnable load metric is the proportional part + * of this group's runnable_load_avg / load_avg. + * + * Note: we need to deal with very sporadic 'runnable > load' cases + * due to numerical instability. + */ + runnable = shares * gcfs_rq->avg.runnable_load_avg; + if (runnable) + runnable /= max(gcfs_rq->avg.load_avg, gcfs_rq->avg.runnable_load_avg); #endif - reweight_entity(cfs_rq_of(se), se, shares); + reweight_entity(cfs_rq_of(se), se, shares, runnable); } #else /* CONFIG_FAIR_GROUP_SCHED */ -static inline void update_cfs_shares(struct sched_entity *se) +static inline void update_cfs_group(struct sched_entity *se) { } #endif /* CONFIG_FAIR_GROUP_SCHED */ @@ -3050,7 +3081,7 @@ static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3) */ static __always_inline u32 accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, - unsigned long weight, int running, struct cfs_rq *cfs_rq) + unsigned long load, unsigned long runnable, int running) { unsigned long scale_freq, scale_cpu; u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */ @@ -3067,10 +3098,8 @@ accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, */ if (periods) { sa->load_sum = decay_load(sa->load_sum, periods); - if (cfs_rq) { - cfs_rq->runnable_load_sum = - decay_load(cfs_rq->runnable_load_sum, periods); - } + sa->runnable_load_sum = + decay_load(sa->runnable_load_sum, periods); sa->util_sum = decay_load((u64)(sa->util_sum), periods); /* @@ -3083,11 +3112,10 @@ accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, sa->period_contrib = delta; contrib = cap_scale(contrib, scale_freq); - if (weight) { - sa->load_sum += weight * contrib; - if (cfs_rq) - cfs_rq->runnable_load_sum += weight * contrib; - } + if (load) + sa->load_sum += load * contrib; + if (runnable) + sa->runnable_load_sum += runnable * contrib; if (running) sa->util_sum += contrib * scale_cpu; @@ -3124,7 +3152,7 @@ accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, */ static __always_inline int ___update_load_sum(u64 now, int cpu, struct sched_avg *sa, - unsigned long weight, int running, struct cfs_rq *cfs_rq) + unsigned long load, unsigned long runnable, int running) { u64 delta; @@ -3157,8 +3185,8 @@ ___update_load_sum(u64 now, int cpu, struct sched_avg *sa, * this happens during idle_balance() which calls * update_blocked_averages() */ - if (!weight) - running = 0; + if (!load) + runnable = running = 0; /* * Now we know we crossed measurement unit boundaries. The *_avg @@ -3167,45 +3195,60 @@ ___update_load_sum(u64 now, int cpu, struct sched_avg *sa, * Step 1: accumulate *_sum since last_update_time. If we haven't * crossed period boundaries, finish. */ - if (!accumulate_sum(delta, cpu, sa, weight, running, cfs_rq)) + if (!accumulate_sum(delta, cpu, sa, load, runnable, running)) return 0; return 1; } static __always_inline void -___update_load_avg(struct sched_avg *sa, unsigned long weight, struct cfs_rq *cfs_rq) +___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable) { u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib; /* * Step 2: update *_avg. */ - sa->load_avg = div_u64(weight * sa->load_sum, divider); - if (cfs_rq) { - cfs_rq->runnable_load_avg = - div_u64(cfs_rq->runnable_load_sum, divider); - } + sa->load_avg = div_u64(load * sa->load_sum, divider); + sa->runnable_load_avg = div_u64(runnable * sa->runnable_load_sum, divider); sa->util_avg = sa->util_sum / divider; } /* * sched_entity: * + * task: + * se_runnable() == se_weight() + * + * group: [ see update_cfs_group() ] + * se_weight() = tg->weight * grq->load_avg / tg->load_avg + * se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg + * * load_sum := runnable_sum * load_avg = se_weight(se) * runnable_avg * + * runnable_load_sum := runnable_sum + * runnable_load_avg = se_runnable(se) * runnable_avg + * + * XXX collapse load_sum and runnable_load_sum + * * cfq_rs: * * load_sum = \Sum se_weight(se) * se->avg.load_sum * load_avg = \Sum se->avg.load_avg + * + * runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum + * runnable_load_avg = \Sum se->avg.runable_load_avg */ static int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se) { - if (___update_load_sum(now, cpu, &se->avg, 0, 0, NULL)) { - ___update_load_avg(&se->avg, se_weight(se), NULL); + if (entity_is_task(se)) + se->runnable_weight = se->load.weight; + + if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) { + ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); return 1; } @@ -3215,10 +3258,13 @@ __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se) static int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se) { - if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, - cfs_rq->curr == se, NULL)) { + if (entity_is_task(se)) + se->runnable_weight = se->load.weight; + + if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq, + cfs_rq->curr == se)) { - ___update_load_avg(&se->avg, se_weight(se), NULL); + ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); return 1; } @@ -3230,8 +3276,10 @@ __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq) { if (___update_load_sum(now, cpu, &cfs_rq->avg, scale_load_down(cfs_rq->load.weight), - cfs_rq->curr != NULL, cfs_rq)) { - ___update_load_avg(&cfs_rq->avg, 1, cfs_rq); + scale_load_down(cfs_rq->runnable_weight), + cfs_rq->curr != NULL)) { + + ___update_load_avg(&cfs_rq->avg, 1, 1); return 1; } @@ -3409,8 +3457,8 @@ static inline void update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { long runnable_sum = gcfs_rq->prop_runnable_sum; - long load_avg; - s64 load_sum; + long runnable_load_avg, load_avg; + s64 runnable_load_sum, load_sum; if (!runnable_sum) return; @@ -3426,9 +3474,15 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf add_positive(&cfs_rq->avg.load_avg, load_avg); add_positive(&cfs_rq->avg.load_sum, load_sum); + runnable_load_sum = (s64)se_runnable(se) * runnable_sum; + runnable_load_avg = div_s64(runnable_load_sum, LOAD_AVG_MAX); + + add_positive(&se->avg.runnable_load_sum, runnable_sum); + add_positive(&se->avg.runnable_load_avg, runnable_load_avg); + if (se->on_rq) { - add_positive(&cfs_rq->runnable_load_avg, load_avg); - add_positive(&cfs_rq->runnable_load_sum, load_sum); + add_positive(&cfs_rq->avg.runnable_load_avg, runnable_load_avg); + add_positive(&cfs_rq->avg.runnable_load_sum, runnable_load_sum); } } @@ -3710,7 +3764,7 @@ void remove_entity_load_avg(struct sched_entity *se) static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq) { - return cfs_rq->runnable_load_avg; + return cfs_rq->avg.runnable_load_avg; } static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq) @@ -3882,8 +3936,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * - Add its new weight to cfs_rq->load.weight */ update_load_avg(cfs_rq, se, UPDATE_TG | DO_ATTACH); + update_cfs_group(se); enqueue_runnable_load_avg(cfs_rq, se); - update_cfs_shares(se); account_entity_enqueue(cfs_rq, se); if (flags & ENQUEUE_WAKEUP) @@ -3989,7 +4043,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) /* return excess runtime on last dequeue */ return_cfs_rq_runtime(cfs_rq); - update_cfs_shares(se); + update_cfs_group(se); /* * Now advance min_vruntime if @se was the entity holding it back, @@ -4172,7 +4226,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) * Ensure that runnable average is periodically updated. */ update_load_avg(cfs_rq, curr, UPDATE_TG); - update_cfs_shares(curr); + update_cfs_group(curr); #ifdef CONFIG_SCHED_HRTICK /* @@ -5090,7 +5144,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) break; update_load_avg(cfs_rq, se, UPDATE_TG); - update_cfs_shares(se); + update_cfs_group(se); } if (!se) @@ -5149,7 +5203,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) break; update_load_avg(cfs_rq, se, UPDATE_TG); - update_cfs_shares(se); + update_cfs_group(se); } if (!se) @@ -7174,7 +7228,7 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) if (cfs_rq->avg.util_sum) return false; - if (cfs_rq->runnable_load_sum) + if (cfs_rq->avg.runnable_load_sum) return false; return true; @@ -9692,7 +9746,7 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) update_rq_clock(rq); for_each_sched_entity(se) { update_load_avg(cfs_rq_of(se), se, UPDATE_TG); - update_cfs_shares(se); + update_cfs_group(se); } rq_unlock_irqrestore(rq, &rf); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 5bcb86eb026b..e83d1b8be611 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -418,6 +418,7 @@ struct cfs_bandwidth { }; /* CFS-related fields in a runqueue */ struct cfs_rq { struct load_weight load; + unsigned long runnable_weight; unsigned int nr_running, h_nr_running; u64 exec_clock; @@ -443,8 +444,6 @@ struct cfs_rq { * CFS load tracking */ struct sched_avg avg; - u64 runnable_load_sum; - unsigned long runnable_load_avg; #ifndef CONFIG_64BIT u64 load_last_update_time_copy; #endif -- cgit v1.2.3 From 667063acb81931e2f8fd0cb91df9fcccad131d9a Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Fri, 29 Sep 2017 16:23:01 +0800 Subject: regmap: add iopoll-like polling macro for regmap_field This patch adds a macro regmap_field_read_poll_timeout that works similar to the readx_poll_timeout defined in linux/iopoll.h, except that this can also return the error value returned by a failed regmap_field_read. Signed-off-by: Chen-Yu Tsai Signed-off-by: Mark Brown --- include/linux/regmap.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 978abfbac617..93a4663d7acb 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -139,6 +139,45 @@ struct reg_sequence { pollret ?: ((cond) ? 0 : -ETIMEDOUT); \ }) +/** + * regmap_field_read_poll_timeout - Poll until a condition is met or timeout + * + * @field: Regmap field to read from + * @val: Unsigned integer variable to read the value into + * @cond: Break condition (usually involving @val) + * @sleep_us: Maximum time to sleep between reads in us (0 + * tight-loops). Should be less than ~20ms since usleep_range + * is used (see Documentation/timers/timers-howto.txt). + * @timeout_us: Timeout in us, 0 means never timeout + * + * Returns 0 on success and -ETIMEDOUT upon a timeout or the regmap_field_read + * error return value in case of a error read. In the two former cases, + * the last read value at @addr is stored in @val. Must not be called + * from atomic context if sleep_us or timeout_us are used. + * + * This is modelled after the readx_poll_timeout macros in linux/iopoll.h. + */ +#define regmap_field_read_poll_timeout(field, val, cond, sleep_us, timeout_us) \ +({ \ + ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \ + int pollret; \ + might_sleep_if(sleep_us); \ + for (;;) { \ + pollret = regmap_field_read((field), &(val)); \ + if (pollret) \ + break; \ + if (cond) \ + break; \ + if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \ + pollret = regmap_field_read((field), &(val)); \ + break; \ + } \ + if (sleep_us) \ + usleep_range((sleep_us >> 2) + 1, sleep_us); \ + } \ + pollret ?: ((cond) ? 0 : -ETIMEDOUT); \ +}) + #ifdef CONFIG_REGMAP enum regmap_endian { -- cgit v1.2.3 From d81851c1764b26b46670c0b3bd6701308ddaab98 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Fri, 29 Sep 2017 11:25:09 +0800 Subject: regulator: axp20x: Add support for AXP813 regulators The AXP813 PMIC has 7 DC-DC buck regulators, 16 LDOs (including the fixed RTC LDO and 2 GPIO LDOs), and 1 switchable. The drive-vbus feature is also supported. All the hardware details are very similar to the AXP803, with the following exceptions: - Extra DCDC7 buck regulator, with the same range as DCDC6 - SWitch now has a separate supply pin, instead of being chained internaly from DCDC1 - RTC LDO output voltage is now 1.8V - FLDO3 is an LDO with switchable supplies, but unconfigurable output voltage. The voltage is always half that of its supply. Support for FLDO3 is currently unimplemented, as it requires runtime switching of its supplies, something the regulator subsystem does not support. It is not used in either the reference designs nor actually produced boards available. Signed-off-by: Chen-Yu Tsai Tested-by: Maxime Ripard Acked-by: Maxime Ripard Signed-off-by: Mark Brown --- drivers/regulator/axp20x-regulator.c | 102 +++++++++++++++++++++++++++++++++-- include/linux/mfd/axp20x.h | 3 ++ 2 files changed, 101 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index 376a99b7cf5d..e1761df4cbfd 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -244,6 +244,7 @@ static const struct regulator_desc axp22x_drivevbus_regulator = { .ops = &axp20x_ops_sw, }; +/* DCDC ranges shared with AXP813 */ static const struct regulator_linear_range axp803_dcdc234_ranges[] = { REGULATOR_LINEAR_RANGE(500000, 0x0, 0x46, 10000), REGULATOR_LINEAR_RANGE(1220000, 0x47, 0x4b, 20000), @@ -426,6 +427,69 @@ static const struct regulator_desc axp809_regulators[] = { AXP_DESC_SW(AXP809, SW, "sw", "swin", AXP22X_PWR_OUT_CTRL2, BIT(6)), }; +static const struct regulator_desc axp813_regulators[] = { + AXP_DESC(AXP813, DCDC1, "dcdc1", "vin1", 1600, 3400, 100, + AXP803_DCDC1_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL1, BIT(0)), + AXP_DESC_RANGES(AXP813, DCDC2, "dcdc2", "vin2", axp803_dcdc234_ranges, + 76, AXP803_DCDC2_V_OUT, 0x7f, AXP22X_PWR_OUT_CTRL1, + BIT(1)), + AXP_DESC_RANGES(AXP813, DCDC3, "dcdc3", "vin3", axp803_dcdc234_ranges, + 76, AXP803_DCDC3_V_OUT, 0x7f, AXP22X_PWR_OUT_CTRL1, + BIT(2)), + AXP_DESC_RANGES(AXP813, DCDC4, "dcdc4", "vin4", axp803_dcdc234_ranges, + 76, AXP803_DCDC4_V_OUT, 0x7f, AXP22X_PWR_OUT_CTRL1, + BIT(3)), + AXP_DESC_RANGES(AXP813, DCDC5, "dcdc5", "vin5", axp803_dcdc5_ranges, + 68, AXP803_DCDC5_V_OUT, 0x7f, AXP22X_PWR_OUT_CTRL1, + BIT(4)), + AXP_DESC_RANGES(AXP813, DCDC6, "dcdc6", "vin6", axp803_dcdc6_ranges, + 72, AXP803_DCDC6_V_OUT, 0x7f, AXP22X_PWR_OUT_CTRL1, + BIT(5)), + AXP_DESC_RANGES(AXP813, DCDC7, "dcdc7", "vin7", axp803_dcdc6_ranges, + 72, AXP813_DCDC7_V_OUT, 0x7f, AXP22X_PWR_OUT_CTRL1, + BIT(6)), + AXP_DESC(AXP813, ALDO1, "aldo1", "aldoin", 700, 3300, 100, + AXP22X_ALDO1_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL3, BIT(5)), + AXP_DESC(AXP813, ALDO2, "aldo2", "aldoin", 700, 3300, 100, + AXP22X_ALDO2_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL3, BIT(6)), + AXP_DESC(AXP813, ALDO3, "aldo3", "aldoin", 700, 3300, 100, + AXP22X_ALDO3_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL3, BIT(7)), + AXP_DESC(AXP813, DLDO1, "dldo1", "dldoin", 700, 3300, 100, + AXP22X_DLDO1_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(3)), + AXP_DESC_RANGES(AXP813, DLDO2, "dldo2", "dldoin", axp803_dldo2_ranges, + 32, AXP22X_DLDO2_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, + BIT(4)), + AXP_DESC(AXP813, DLDO3, "dldo3", "dldoin", 700, 3300, 100, + AXP22X_DLDO3_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(5)), + AXP_DESC(AXP813, DLDO4, "dldo4", "dldoin", 700, 3300, 100, + AXP22X_DLDO4_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(6)), + AXP_DESC(AXP813, ELDO1, "eldo1", "eldoin", 700, 1900, 50, + AXP22X_ELDO1_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(0)), + AXP_DESC(AXP813, ELDO2, "eldo2", "eldoin", 700, 1900, 50, + AXP22X_ELDO2_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(1)), + AXP_DESC(AXP813, ELDO3, "eldo3", "eldoin", 700, 1900, 50, + AXP22X_ELDO3_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(2)), + /* to do / check ... */ + AXP_DESC(AXP813, FLDO1, "fldo1", "fldoin", 700, 1450, 50, + AXP803_FLDO1_V_OUT, 0x0f, AXP22X_PWR_OUT_CTRL3, BIT(2)), + AXP_DESC(AXP813, FLDO2, "fldo2", "fldoin", 700, 1450, 50, + AXP803_FLDO2_V_OUT, 0x0f, AXP22X_PWR_OUT_CTRL3, BIT(3)), + /* + * TODO: FLDO3 = {DCDC5, FLDOIN} / 2 + * + * This means FLDO3 effectively switches supplies at runtime, + * something the regulator subsystem does not support. + */ + AXP_DESC_FIXED(AXP813, RTC_LDO, "rtc-ldo", "ips", 1800), + AXP_DESC_IO(AXP813, LDO_IO0, "ldo-io0", "ips", 700, 3300, 100, + AXP22X_LDO_IO0_V_OUT, 0x1f, AXP20X_GPIO0_CTRL, 0x07, + AXP22X_IO_ENABLED, AXP22X_IO_DISABLED), + AXP_DESC_IO(AXP813, LDO_IO1, "ldo-io1", "ips", 700, 3300, 100, + AXP22X_LDO_IO1_V_OUT, 0x1f, AXP20X_GPIO1_CTRL, 0x07, + AXP22X_IO_ENABLED, AXP22X_IO_DISABLED), + AXP_DESC_SW(AXP813, SW, "sw", "swin", AXP22X_PWR_OUT_CTRL2, BIT(7)), +}; + static int axp20x_set_dcdc_freq(struct platform_device *pdev, u32 dcdcfreq) { struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent); @@ -441,9 +505,10 @@ static int axp20x_set_dcdc_freq(struct platform_device *pdev, u32 dcdcfreq) step = 75; break; case AXP803_ID: + case AXP813_ID: /* - * AXP803 DCDC work frequency setting has the same range and - * step as AXP22X, but at a different register. + * AXP803/AXP813 DCDC work frequency setting has the same + * range and step as AXP22X, but at a different register. * Fall through to the check below. * (See include/linux/mfd/axp20x.h) */ @@ -561,6 +626,14 @@ static int axp20x_set_dcdc_workmode(struct regulator_dev *rdev, int id, u32 work workmode <<= id - AXP803_DCDC1; break; + case AXP813_ID: + if (id < AXP813_DCDC1 || id > AXP813_DCDC7) + return -EINVAL; + + mask = AXP22X_WORKMODE_DCDCX_MASK(id - AXP813_DCDC1); + workmode <<= id - AXP813_DCDC1; + break; + default: /* should not happen */ WARN_ON(1); @@ -579,8 +652,8 @@ static bool axp20x_is_polyphase_slave(struct axp20x_dev *axp20x, int id) u32 reg = 0; /* - * Currently in our supported AXP variants, only AXP803 and AXP806 - * have polyphase regulators. + * Currently in our supported AXP variants, only AXP803, AXP806, + * and AXP813 have polyphase regulators. */ switch (axp20x->variant) { case AXP803_ID: @@ -608,6 +681,17 @@ static bool axp20x_is_polyphase_slave(struct axp20x_dev *axp20x, int id) } break; + case AXP813_ID: + regmap_read(axp20x->regmap, AXP803_POLYPHASE_CTRL, ®); + + switch (id) { + case AXP803_DCDC3: + return !!(reg & BIT(6)); + case AXP803_DCDC6: + return !!(reg & BIT(5)); + } + break; + default: return false; } @@ -656,6 +740,12 @@ static int axp20x_regulator_probe(struct platform_device *pdev) regulators = axp809_regulators; nregulators = AXP809_REG_ID_MAX; break; + case AXP813_ID: + regulators = axp813_regulators; + nregulators = AXP813_REG_ID_MAX; + drivevbus = of_property_read_bool(pdev->dev.parent->of_node, + "x-powers,drive-vbus-en"); + break; default: dev_err(&pdev->dev, "Unsupported AXP variant: %ld\n", axp20x->variant); @@ -677,6 +767,10 @@ static int axp20x_regulator_probe(struct platform_device *pdev) if (axp20x_is_polyphase_slave(axp20x, i)) continue; + /* Support for AXP813's FLDO3 is not implemented */ + if (axp20x->variant == AXP813_ID && i == AXP813_FLDO3) + continue; + /* * Regulators DC1SW and DC5LDO are connected internally, * so we have to handle their supply names separately. diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index e9c908c4fba8..78dc85365c4f 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -131,6 +131,9 @@ enum axp20x_variants { #define AXP803_DCDC6_V_OUT 0x25 #define AXP803_DCDC_FREQ_CTRL 0x3b +/* Other DCDC regulator control registers are the same as AXP803 */ +#define AXP813_DCDC7_V_OUT 0x26 + /* Interrupt */ #define AXP152_IRQ1_EN 0x40 #define AXP152_IRQ2_EN 0x41 -- cgit v1.2.3 From 58e1177b4cd10b0d358faf7d7ebb3779f98bc3ea Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 4 Oct 2017 16:26:55 -0700 Subject: timer: Convert schedule_timeout() to use from_timer() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new from_timer() helper and passing the timer pointer explicitly. Since this special timer is on the stack, it needs to have a wrapper structure to carry state once .data is eliminated. Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Cc: linux-mips@linux-mips.org Cc: Petr Mladek Cc: Benjamin Herrenschmidt Cc: Lai Jiangshan Cc: Sebastian Reichel Cc: Kalle Valo Cc: Paul Mackerras Cc: Pavel Machek Cc: linux1394-devel@lists.sourceforge.net Cc: Chris Metcalf Cc: linux-s390@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: "James E.J. Bottomley" Cc: Wim Van Sebroeck Cc: Michael Ellerman Cc: Ursula Braun Cc: Geert Uytterhoeven Cc: Viresh Kumar Cc: Harish Patil Cc: Guenter Roeck Cc: Manish Chopra Cc: Len Brown Cc: Arnd Bergmann Cc: linux-pm@vger.kernel.org Cc: Heiko Carstens Cc: Tejun Heo Cc: Julian Wiedmann Cc: John Stultz Cc: Mark Gross Cc: "Rafael J. Wysocki" Cc: linux-watchdog@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" Cc: Greg Kroah-Hartman Cc: Stephen Boyd Cc: Oleg Nesterov Cc: Ralf Baechle Cc: Stefan Richter Cc: Michael Reed Cc: netdev@vger.kernel.org Cc: Martin Schwidefsky Cc: Andrew Morton Cc: linuxppc-dev@lists.ozlabs.org Cc: Sudip Mukherjee Link: https://lkml.kernel.org/r/1507159627-127660-2-git-send-email-keescook@chromium.org --- include/linux/timer.h | 8 ++++++++ kernel/time/timer.c | 26 +++++++++++++++++++------- 2 files changed, 27 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index 6383c528b148..5ef5c9e41a09 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -179,6 +179,14 @@ static inline void timer_setup(struct timer_list *timer, (TIMER_DATA_TYPE)timer, flags); } +static inline void timer_setup_on_stack(struct timer_list *timer, + void (*callback)(struct timer_list *), + unsigned int flags) +{ + __setup_timer_on_stack(timer, (TIMER_FUNC_TYPE)callback, + (TIMER_DATA_TYPE)timer, flags); +} + #define from_timer(var, callback_timer, timer_fieldname) \ container_of(callback_timer, typeof(*var), timer_fieldname) diff --git a/kernel/time/timer.c b/kernel/time/timer.c index f2674a056c26..38613ced2324 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1668,9 +1668,20 @@ void run_local_timers(void) raise_softirq(TIMER_SOFTIRQ); } -static void process_timeout(unsigned long __data) +/* + * Since schedule_timeout()'s timer is defined on the stack, it must store + * the target task on the stack as well. + */ +struct process_timer { + struct timer_list timer; + struct task_struct *task; +}; + +static void process_timeout(struct timer_list *t) { - wake_up_process((struct task_struct *)__data); + struct process_timer *timeout = from_timer(timeout, t, timer); + + wake_up_process(timeout->task); } /** @@ -1704,7 +1715,7 @@ static void process_timeout(unsigned long __data) */ signed long __sched schedule_timeout(signed long timeout) { - struct timer_list timer; + struct process_timer timer; unsigned long expire; switch (timeout) @@ -1738,13 +1749,14 @@ signed long __sched schedule_timeout(signed long timeout) expire = timeout + jiffies; - setup_timer_on_stack(&timer, process_timeout, (unsigned long)current); - __mod_timer(&timer, expire, false); + timer.task = current; + timer_setup_on_stack(&timer.timer, process_timeout, 0); + __mod_timer(&timer.timer, expire, false); schedule(); - del_singleshot_timer_sync(&timer); + del_singleshot_timer_sync(&timer.timer); /* Remove the timer from the object tracker */ - destroy_timer_on_stack(&timer); + destroy_timer_on_stack(&timer.timer); timeout = expire - jiffies; -- cgit v1.2.3 From 1d1fe902afb380571105d05d0be3de61b81bc9a8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 4 Oct 2017 16:26:56 -0700 Subject: timer: Remove init_timer_pinned_deferrable() in favor of timer_setup() This refactors the only user of init_timer_pinned_deferrable() to use the new timer_setup() and from_timer(). Adds a pointer back to the policy, and drops the definition of init_timer_pinned_deferrable(). Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Cc: linux-mips@linux-mips.org Cc: Petr Mladek Cc: Benjamin Herrenschmidt Cc: Lai Jiangshan Cc: Sebastian Reichel Cc: Kalle Valo Cc: Paul Mackerras Cc: Pavel Machek Cc: linux1394-devel@lists.sourceforge.net Cc: Chris Metcalf Cc: linux-s390@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: "James E.J. Bottomley" Cc: Wim Van Sebroeck Cc: Michael Ellerman Cc: Ursula Braun Cc: Geert Uytterhoeven Cc: Viresh Kumar Cc: Harish Patil Cc: Stephen Boyd Cc: Guenter Roeck Cc: Manish Chopra Cc: Len Brown Cc: Arnd Bergmann Cc: linux-pm@vger.kernel.org Cc: Heiko Carstens Cc: Tejun Heo Cc: Julian Wiedmann Cc: John Stultz Cc: Mark Gross Cc: linux-watchdog@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Oleg Nesterov Cc: Ralf Baechle Cc: Stefan Richter Cc: Michael Reed Cc: netdev@vger.kernel.org Cc: Martin Schwidefsky Cc: Andrew Morton Cc: linuxppc-dev@lists.ozlabs.org Cc: Sudip Mukherjee Link: https://lkml.kernel.org/r/1507159627-127660-3-git-send-email-keescook@chromium.org --- drivers/cpufreq/powernv-cpufreq.c | 13 +++++++------ include/linux/timer.h | 2 -- 2 files changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 3ff5160451b4..b6d7c4c98d0a 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -90,6 +90,7 @@ struct global_pstate_info { int last_gpstate_idx; spinlock_t gpstate_lock; struct timer_list timer; + struct cpufreq_policy *policy; }; static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1]; @@ -625,10 +626,10 @@ static inline void queue_gpstate_timer(struct global_pstate_info *gpstates) * according quadratic equation. Queues a new timer if it is still not equal * to local pstate */ -void gpstate_timer_handler(unsigned long data) +void gpstate_timer_handler(struct timer_list *t) { - struct cpufreq_policy *policy = (struct cpufreq_policy *)data; - struct global_pstate_info *gpstates = policy->driver_data; + struct global_pstate_info *gpstates = from_timer(gpstates, t, timer); + struct cpufreq_policy *policy = gpstates->policy; int gpstate_idx, lpstate_idx; unsigned long val; unsigned int time_diff = jiffies_to_msecs(jiffies) @@ -800,9 +801,9 @@ static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy) policy->driver_data = gpstates; /* initialize timer */ - init_timer_pinned_deferrable(&gpstates->timer); - gpstates->timer.data = (unsigned long)policy; - gpstates->timer.function = gpstate_timer_handler; + gpstates->policy = policy; + timer_setup(&gpstates->timer, gpstate_timer_handler, + TIMER_PINNED | TIMER_DEFERRABLE); gpstates->timer.expires = jiffies + msecs_to_jiffies(GPSTATE_TIMER_INTERVAL); spin_lock_init(&gpstates->gpstate_lock); diff --git a/include/linux/timer.h b/include/linux/timer.h index 5ef5c9e41a09..d11e819a86e2 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -132,8 +132,6 @@ static inline void init_timer_on_stack_key(struct timer_list *timer, __init_timer((timer), TIMER_PINNED) #define init_timer_deferrable(timer) \ __init_timer((timer), TIMER_DEFERRABLE) -#define init_timer_pinned_deferrable(timer) \ - __init_timer((timer), TIMER_DEFERRABLE | TIMER_PINNED) #define init_timer_on_stack(timer) \ __init_timer_on_stack((timer), 0) -- cgit v1.2.3 From 9c6c273aa4248c60569de6ef7e7e9c7bed3cd32e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 4 Oct 2017 16:26:57 -0700 Subject: timer: Remove init_timer_on_stack() in favor of timer_setup_on_stack() Remove uses of init_timer_on_stack() with open-coded function and data assignments that could be expressed using timer_setup_on_stack(). Several were removed from the stack entirely since there was a one-to-one mapping of parent structure to timer, those are switched to using timer_setup() instead. All related callbacks were adjusted to use from_timer(). Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Cc: linux-mips@linux-mips.org Cc: Petr Mladek Cc: Benjamin Herrenschmidt Cc: Heiko Carstens Cc: Sebastian Reichel Cc: Kalle Valo Cc: Paul Mackerras Cc: Pavel Machek Cc: Wim Van Sebroeck Cc: linux1394-devel@lists.sourceforge.net Cc: Chris Metcalf Cc: linux-s390@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: "James E.J. Bottomley" Cc: linux-scsi@vger.kernel.org Cc: Michael Ellerman Cc: Ursula Braun Cc: Geert Uytterhoeven Cc: Viresh Kumar Cc: Harish Patil Cc: Stephen Boyd Cc: Michael Reed Cc: Manish Chopra Cc: Len Brown Cc: Arnd Bergmann Cc: linux-pm@vger.kernel.org Cc: Lai Jiangshan Cc: Tejun Heo Cc: Julian Wiedmann Cc: John Stultz Cc: Mark Gross Cc: linux-watchdog@vger.kernel.org Cc: "Martin K. Petersen" Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Oleg Nesterov Cc: Ralf Baechle Cc: Stefan Richter Cc: Guenter Roeck Cc: netdev@vger.kernel.org Cc: Martin Schwidefsky Cc: Andrew Morton Cc: linuxppc-dev@lists.ozlabs.org Cc: Sudip Mukherjee Link: https://lkml.kernel.org/r/1507159627-127660-4-git-send-email-keescook@chromium.org --- drivers/base/power/main.c | 8 +++----- drivers/firewire/core-transaction.c | 10 +++++----- drivers/parport/ieee1284.c | 21 +++++++-------------- drivers/s390/char/tape.h | 1 + drivers/s390/char/tape_std.c | 18 ++++++------------ drivers/s390/net/lcs.c | 16 ++++++---------- drivers/s390/net/lcs.h | 1 + drivers/scsi/qla1280.c | 14 +++++--------- drivers/scsi/qla1280.h | 1 + include/linux/parport.h | 1 + include/linux/timer.h | 2 -- 11 files changed, 36 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 770b1539a083..ae47b2ec84b4 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -478,9 +478,9 @@ struct dpm_watchdog { * There's not much we can do here to recover so panic() to * capture a crash-dump in pstore. */ -static void dpm_watchdog_handler(unsigned long data) +static void dpm_watchdog_handler(struct timer_list *t) { - struct dpm_watchdog *wd = (void *)data; + struct dpm_watchdog *wd = from_timer(wd, t, timer); dev_emerg(wd->dev, "**** DPM device timeout ****\n"); show_stack(wd->tsk, NULL); @@ -500,11 +500,9 @@ static void dpm_watchdog_set(struct dpm_watchdog *wd, struct device *dev) wd->dev = dev; wd->tsk = current; - init_timer_on_stack(timer); + timer_setup_on_stack(timer, dpm_watchdog_handler, 0); /* use same timeout value for both suspend and resume */ timer->expires = jiffies + HZ * CONFIG_DPM_WATCHDOG_TIMEOUT; - timer->function = dpm_watchdog_handler; - timer->data = (unsigned long)wd; add_timer(timer); } diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index d6a09b9cd8cc..4372f9e4b0da 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -137,9 +137,9 @@ int fw_cancel_transaction(struct fw_card *card, } EXPORT_SYMBOL(fw_cancel_transaction); -static void split_transaction_timeout_callback(unsigned long data) +static void split_transaction_timeout_callback(struct timer_list *timer) { - struct fw_transaction *t = (struct fw_transaction *)data; + struct fw_transaction *t = from_timer(t, timer, split_timeout_timer); struct fw_card *card = t->card; unsigned long flags; @@ -373,8 +373,8 @@ void fw_send_request(struct fw_card *card, struct fw_transaction *t, int tcode, t->tlabel = tlabel; t->card = card; t->is_split_transaction = false; - setup_timer(&t->split_timeout_timer, - split_transaction_timeout_callback, (unsigned long)t); + timer_setup(&t->split_timeout_timer, + split_transaction_timeout_callback, 0); t->callback = callback; t->callback_data = callback_data; @@ -423,7 +423,7 @@ int fw_run_transaction(struct fw_card *card, int tcode, int destination_id, struct transaction_callback_data d; struct fw_transaction t; - init_timer_on_stack(&t.split_timeout_timer); + timer_setup_on_stack(&t.split_timeout_timer, NULL, 0); init_completion(&d.done); d.payload = payload; fw_send_request(card, &t, tcode, destination_id, generation, speed, diff --git a/drivers/parport/ieee1284.c b/drivers/parport/ieee1284.c index 74cc6dd982d2..2d1a5c737c6e 100644 --- a/drivers/parport/ieee1284.c +++ b/drivers/parport/ieee1284.c @@ -44,10 +44,11 @@ static void parport_ieee1284_wakeup (struct parport *port) up (&port->physport->ieee1284.irq); } -static struct parport *port_from_cookie[PARPORT_MAX]; -static void timeout_waiting_on_port (unsigned long cookie) +static void timeout_waiting_on_port (struct timer_list *t) { - parport_ieee1284_wakeup (port_from_cookie[cookie % PARPORT_MAX]); + struct parport *port = from_timer(port, t, timer); + + parport_ieee1284_wakeup (port); } /** @@ -69,27 +70,19 @@ static void timeout_waiting_on_port (unsigned long cookie) int parport_wait_event (struct parport *port, signed long timeout) { int ret; - struct timer_list timer; if (!port->physport->cad->timeout) /* Zero timeout is special, and we can't down() the semaphore. */ return 1; - init_timer_on_stack(&timer); - timer.expires = jiffies + timeout; - timer.function = timeout_waiting_on_port; - port_from_cookie[port->number % PARPORT_MAX] = port; - timer.data = port->number; - - add_timer (&timer); + timer_setup(&port->timer, timeout_waiting_on_port, 0); + mod_timer(&port->timer, jiffies + timeout); ret = down_interruptible (&port->physport->ieee1284.irq); - if (!del_timer_sync(&timer) && !ret) + if (!del_timer_sync(&port->timer) && !ret) /* Timed out. */ ret = 1; - destroy_timer_on_stack(&timer); - return ret; } diff --git a/drivers/s390/char/tape.h b/drivers/s390/char/tape.h index ea664dd4f56d..52fbcd9c3cf8 100644 --- a/drivers/s390/char/tape.h +++ b/drivers/s390/char/tape.h @@ -128,6 +128,7 @@ struct tape_request { int options; /* options for execution. */ int retries; /* retry counter for error recovery. */ int rescnt; /* residual count from devstat. */ + struct timer_list timer; /* timer for std_assign_timeout(). */ /* Callback for delivering final status. */ void (*callback)(struct tape_request *, void *); diff --git a/drivers/s390/char/tape_std.c b/drivers/s390/char/tape_std.c index 3478e19ae194..cd204abdc0bc 100644 --- a/drivers/s390/char/tape_std.c +++ b/drivers/s390/char/tape_std.c @@ -32,14 +32,12 @@ * tape_std_assign */ static void -tape_std_assign_timeout(unsigned long data) +tape_std_assign_timeout(struct timer_list *t) { - struct tape_request * request; - struct tape_device * device; + struct tape_request * request = from_timer(request, t, timer); + struct tape_device * device = request->device; int rc; - request = (struct tape_request *) data; - device = request->device; BUG_ON(!device); DBF_EVENT(3, "%08x: Assignment timeout. Device busy.\n", @@ -70,16 +68,12 @@ tape_std_assign(struct tape_device *device) * to another host (actually this shouldn't happen but it does). * So we set up a timeout for this call. */ - init_timer_on_stack(&timeout); - timeout.function = tape_std_assign_timeout; - timeout.data = (unsigned long) request; - timeout.expires = jiffies + 2 * HZ; - add_timer(&timeout); + timer_setup(&request->timer, tape_std_assign_timeout, 0); + mod_timer(&timeout, jiffies + 2 * HZ); rc = tape_do_io_interruptible(device, request); - del_timer_sync(&timeout); - destroy_timer_on_stack(&timeout); + del_timer_sync(&request->timer); if (rc != 0) { DBF_EVENT(3, "%08x: assign failed - device might be busy\n", diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c index d01b5c2a7760..21bba406d5be 100644 --- a/drivers/s390/net/lcs.c +++ b/drivers/s390/net/lcs.c @@ -834,9 +834,10 @@ lcs_notify_lancmd_waiters(struct lcs_card *card, struct lcs_cmd *cmd) * Emit buffer of a lan command. */ static void -lcs_lancmd_timeout(unsigned long data) +lcs_lancmd_timeout(struct timer_list *t) { - struct lcs_reply *reply, *list_reply, *r; + struct lcs_reply *reply = from_timer(reply, t, timer); + struct lcs_reply *list_reply, *r; unsigned long flags; LCS_DBF_TEXT(4, trace, "timeout"); @@ -864,7 +865,6 @@ lcs_send_lancmd(struct lcs_card *card, struct lcs_buffer *buffer, { struct lcs_reply *reply; struct lcs_cmd *cmd; - struct timer_list timer; unsigned long flags; int rc; @@ -885,14 +885,10 @@ lcs_send_lancmd(struct lcs_card *card, struct lcs_buffer *buffer, rc = lcs_ready_buffer(&card->write, buffer); if (rc) return rc; - init_timer_on_stack(&timer); - timer.function = lcs_lancmd_timeout; - timer.data = (unsigned long) reply; - timer.expires = jiffies + HZ*card->lancmd_timeout; - add_timer(&timer); + timer_setup(&reply->timer, lcs_lancmd_timeout, 0); + mod_timer(&reply->timer, jiffies + HZ * card->lancmd_timeout); wait_event(reply->wait_q, reply->received); - del_timer_sync(&timer); - destroy_timer_on_stack(&timer); + del_timer_sync(&reply->timer); LCS_DBF_TEXT_(4, trace, "rc:%d",reply->rc); rc = reply->rc; lcs_put_reply(reply); diff --git a/drivers/s390/net/lcs.h b/drivers/s390/net/lcs.h index 150fcb4cebc3..d44fb8d9378f 100644 --- a/drivers/s390/net/lcs.h +++ b/drivers/s390/net/lcs.h @@ -275,6 +275,7 @@ struct lcs_reply { void (*callback)(struct lcs_card *, struct lcs_cmd *); wait_queue_head_t wait_q; struct lcs_card *card; + struct timer_list timer; int received; int rc; }; diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c index 8a29fb09db14..390775d5c918 100644 --- a/drivers/scsi/qla1280.c +++ b/drivers/scsi/qla1280.c @@ -758,9 +758,9 @@ enum action { }; -static void qla1280_mailbox_timeout(unsigned long __data) +static void qla1280_mailbox_timeout(struct timer_list *t) { - struct scsi_qla_host *ha = (struct scsi_qla_host *)__data; + struct scsi_qla_host *ha = from_timer(ha, t, mailbox_timer); struct device_reg __iomem *reg; reg = ha->iobase; @@ -2465,7 +2465,6 @@ qla1280_mailbox_command(struct scsi_qla_host *ha, uint8_t mr, uint16_t *mb) uint16_t __iomem *mptr; uint16_t data; DECLARE_COMPLETION_ONSTACK(wait); - struct timer_list timer; ENTER("qla1280_mailbox_command"); @@ -2494,18 +2493,15 @@ qla1280_mailbox_command(struct scsi_qla_host *ha, uint8_t mr, uint16_t *mb) /* Issue set host interrupt command. */ /* set up a timer just in case we're really jammed */ - init_timer_on_stack(&timer); - timer.expires = jiffies + 20*HZ; - timer.data = (unsigned long)ha; - timer.function = qla1280_mailbox_timeout; - add_timer(&timer); + timer_setup(&ha->mailbox_timer, qla1280_mailbox_timeout, 0); + mod_timer(&ha->mailbox_timer, jiffies + 20 * HZ); spin_unlock_irq(ha->host->host_lock); WRT_REG_WORD(®->host_cmd, HC_SET_HOST_INT); data = qla1280_debounce_register(®->istatus); wait_for_completion(&wait); - del_timer_sync(&timer); + del_timer_sync(&ha->mailbox_timer); spin_lock_irq(ha->host->host_lock); diff --git a/drivers/scsi/qla1280.h b/drivers/scsi/qla1280.h index 834884b9eed5..1522aca2c8c8 100644 --- a/drivers/scsi/qla1280.h +++ b/drivers/scsi/qla1280.h @@ -1055,6 +1055,7 @@ struct scsi_qla_host { struct list_head done_q; /* Done queue */ struct completion *mailbox_wait; + struct timer_list mailbox_timer; volatile struct { uint32_t online:1; /* 0 */ diff --git a/include/linux/parport.h b/include/linux/parport.h index 58e3c64c6b49..397607a0c0eb 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -225,6 +225,7 @@ struct parport { struct pardevice *waittail; struct list_head list; + struct timer_list timer; unsigned int flags; void *sysctl_table; diff --git a/include/linux/timer.h b/include/linux/timer.h index d11e819a86e2..b10c4bdc6fbd 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -132,8 +132,6 @@ static inline void init_timer_on_stack_key(struct timer_list *timer, __init_timer((timer), TIMER_PINNED) #define init_timer_deferrable(timer) \ __init_timer((timer), TIMER_DEFERRABLE) -#define init_timer_on_stack(timer) \ - __init_timer_on_stack((timer), 0) #define __setup_timer(_timer, _fn, _data, _flags) \ do { \ -- cgit v1.2.3 From 185981d54a60ae90942c6ba9006b250f3348cef2 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 4 Oct 2017 16:26:58 -0700 Subject: timer: Remove init_timer_pinned() in favor of timer_setup() This refactors the only users of init_timer_pinned() to use the new timer_setup() and from_timer(). Drops the definition of init_timer_pinned(). Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Acked-by: David S. Miller # for networking parts Cc: linux-mips@linux-mips.org Cc: Petr Mladek Cc: Benjamin Herrenschmidt Cc: Lai Jiangshan Cc: Sebastian Reichel Cc: Kalle Valo Cc: Paul Mackerras Cc: Pavel Machek Cc: linux1394-devel@lists.sourceforge.net Cc: Chris Metcalf Cc: linux-s390@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: "James E.J. Bottomley" Cc: Wim Van Sebroeck Cc: Michael Ellerman Cc: Ursula Braun Cc: Geert Uytterhoeven Cc: Viresh Kumar Cc: Harish Patil Cc: Stephen Boyd Cc: Guenter Roeck Cc: Manish Chopra Cc: Len Brown Cc: Arnd Bergmann Cc: linux-pm@vger.kernel.org Cc: Heiko Carstens Cc: Tejun Heo Cc: Julian Wiedmann Cc: John Stultz Cc: Mark Gross Cc: linux-watchdog@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Oleg Nesterov Cc: Ralf Baechle Cc: Stefan Richter Cc: Michael Reed Cc: netdev@vger.kernel.org Cc: Martin Schwidefsky Cc: Andrew Morton Cc: linuxppc-dev@lists.ozlabs.org Cc: Sudip Mukherjee Link: https://lkml.kernel.org/r/1507159627-127660-5-git-send-email-keescook@chromium.org --- drivers/net/ethernet/tile/tilepro.c | 9 ++++----- include/linux/timer.h | 2 -- 2 files changed, 4 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/tile/tilepro.c b/drivers/net/ethernet/tile/tilepro.c index 49ccee4b9aec..56d06282fbde 100644 --- a/drivers/net/ethernet/tile/tilepro.c +++ b/drivers/net/ethernet/tile/tilepro.c @@ -608,9 +608,9 @@ static void tile_net_schedule_egress_timer(struct tile_net_cpu *info) * ISSUE: Maybe instead track number of expected completions, and free * only that many, resetting to zero if "pending" is ever false. */ -static void tile_net_handle_egress_timer(unsigned long arg) +static void tile_net_handle_egress_timer(struct timer_list *t) { - struct tile_net_cpu *info = (struct tile_net_cpu *)arg; + struct tile_net_cpu *info = from_timer(info, t, egress_timer); struct net_device *dev = info->napi.dev; /* The timer is no longer scheduled. */ @@ -1004,9 +1004,8 @@ static void tile_net_register(void *dev_ptr) BUG(); /* Initialize the egress timer. */ - init_timer_pinned(&info->egress_timer); - info->egress_timer.data = (long)info; - info->egress_timer.function = tile_net_handle_egress_timer; + timer_setup(&info->egress_timer, tile_net_handle_egress_timer, + TIMER_PINNED); u64_stats_init(&info->stats.syncp); diff --git a/include/linux/timer.h b/include/linux/timer.h index b10c4bdc6fbd..9da903562ed4 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -128,8 +128,6 @@ static inline void init_timer_on_stack_key(struct timer_list *timer, #define init_timer(timer) \ __init_timer((timer), 0) -#define init_timer_pinned(timer) \ - __init_timer((timer), TIMER_PINNED) #define init_timer_deferrable(timer) \ __init_timer((timer), TIMER_DEFERRABLE) -- cgit v1.2.3 From df7e828c1b699792b2ff26ebcf0a6d1025b2b790 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 4 Oct 2017 16:26:59 -0700 Subject: timer: Remove init_timer_deferrable() in favor of timer_setup() This refactors the only users of init_timer_deferrable() to use the new timer_setup() and from_timer(). Removes definition of init_timer_deferrable(). Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Acked-by: David S. Miller # for networking parts Acked-by: Sebastian Reichel # for drivers/hsi parts Cc: linux-mips@linux-mips.org Cc: Petr Mladek Cc: Benjamin Herrenschmidt Cc: Lai Jiangshan Cc: Oleg Nesterov Cc: Kalle Valo Cc: Paul Mackerras Cc: Pavel Machek Cc: linux1394-devel@lists.sourceforge.net Cc: Chris Metcalf Cc: linux-s390@vger.kernel.org Cc: "James E.J. Bottomley" Cc: Wim Van Sebroeck Cc: Michael Ellerman Cc: Ursula Braun Cc: Geert Uytterhoeven Cc: Viresh Kumar Cc: Harish Patil Cc: Stephen Boyd Cc: Guenter Roeck Cc: Manish Chopra Cc: Len Brown Cc: Arnd Bergmann Cc: linux-pm@vger.kernel.org Cc: Heiko Carstens Cc: Tejun Heo Cc: Julian Wiedmann Cc: John Stultz Cc: Mark Gross Cc: "Rafael J. Wysocki" Cc: linux-watchdog@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" Cc: Greg Kroah-Hartman Cc: linux-wireless@vger.kernel.org Cc: Sebastian Reichel Cc: Ralf Baechle Cc: Stefan Richter Cc: Michael Reed Cc: netdev@vger.kernel.org Cc: Martin Schwidefsky Cc: Andrew Morton Cc: linuxppc-dev@lists.ozlabs.org Cc: Sudip Mukherjee Link: https://lkml.kernel.org/r/1507159627-127660-6-git-send-email-keescook@chromium.org --- arch/powerpc/mm/numa.c | 12 +++++------ drivers/hsi/clients/ssi_protocol.c | 32 ++++++++++++++++------------ drivers/net/ethernet/qlogic/qlge/qlge_main.c | 11 ++++------ drivers/net/vxlan.c | 8 +++---- drivers/net/wireless/ath/ath6kl/recovery.c | 9 ++++---- include/linux/timer.h | 2 -- 6 files changed, 34 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b95c584ce19d..f9b6107d6854 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1453,7 +1453,7 @@ static void topology_schedule_update(void) schedule_work(&topology_work); } -static void topology_timer_fn(unsigned long ignored) +static void topology_timer_fn(struct timer_list *unused) { if (prrn_enabled && cpumask_weight(&cpu_associativity_changes_mask)) topology_schedule_update(); @@ -1463,14 +1463,11 @@ static void topology_timer_fn(unsigned long ignored) reset_topology_timer(); } } -static struct timer_list topology_timer = - TIMER_INITIALIZER(topology_timer_fn, 0, 0); +static struct timer_list topology_timer; static void reset_topology_timer(void) { - topology_timer.data = 0; - topology_timer.expires = jiffies + 60 * HZ; - mod_timer(&topology_timer, topology_timer.expires); + mod_timer(&topology_timer, jiffies + 60 * HZ); } #ifdef CONFIG_SMP @@ -1530,7 +1527,8 @@ int start_topology_update(void) prrn_enabled = 0; vphn_enabled = 1; setup_cpu_associativity_change_counters(); - init_timer_deferrable(&topology_timer); + timer_setup(&topology_timer, topology_timer_fn, + TIMER_DEFERRABLE); reset_topology_timer(); } } diff --git a/drivers/hsi/clients/ssi_protocol.c b/drivers/hsi/clients/ssi_protocol.c index 93d28c0ec8bf..67af03d3aeb3 100644 --- a/drivers/hsi/clients/ssi_protocol.c +++ b/drivers/hsi/clients/ssi_protocol.c @@ -464,10 +464,10 @@ static void ssip_error(struct hsi_client *cl) hsi_async_read(cl, msg); } -static void ssip_keep_alive(unsigned long data) +static void ssip_keep_alive(struct timer_list *t) { - struct hsi_client *cl = (struct hsi_client *)data; - struct ssi_protocol *ssi = hsi_client_drvdata(cl); + struct ssi_protocol *ssi = from_timer(ssi, t, keep_alive); + struct hsi_client *cl = ssi->cl; dev_dbg(&cl->device, "Keep alive kick in: m(%d) r(%d) s(%d)\n", ssi->main_state, ssi->recv_state, ssi->send_state); @@ -490,9 +490,19 @@ static void ssip_keep_alive(unsigned long data) spin_unlock(&ssi->lock); } -static void ssip_wd(unsigned long data) +static void ssip_rx_wd(struct timer_list *t) +{ + struct ssi_protocol *ssi = from_timer(ssi, t, rx_wd); + struct hsi_client *cl = ssi->cl; + + dev_err(&cl->device, "Watchdog trigerred\n"); + ssip_error(cl); +} + +static void ssip_tx_wd(unsigned long data) { - struct hsi_client *cl = (struct hsi_client *)data; + struct ssi_protocol *ssi = from_timer(ssi, t, tx_wd); + struct hsi_client *cl = ssi->cl; dev_err(&cl->device, "Watchdog trigerred\n"); ssip_error(cl); @@ -1084,15 +1094,9 @@ static int ssi_protocol_probe(struct device *dev) } spin_lock_init(&ssi->lock); - init_timer_deferrable(&ssi->rx_wd); - init_timer_deferrable(&ssi->tx_wd); - init_timer(&ssi->keep_alive); - ssi->rx_wd.data = (unsigned long)cl; - ssi->rx_wd.function = ssip_wd; - ssi->tx_wd.data = (unsigned long)cl; - ssi->tx_wd.function = ssip_wd; - ssi->keep_alive.data = (unsigned long)cl; - ssi->keep_alive.function = ssip_keep_alive; + timer_setup(&ssi->rx_wd, ssip_rx_wd, TIMER_DEFERRABLE); + timer_setup(&ssi->tx_wd, ssip_tx_wd, TIMER_DEFERRABLE); + timer_setup(&ssi->keep_alive, ssip_keep_alive, 0); INIT_LIST_HEAD(&ssi->txqueue); INIT_LIST_HEAD(&ssi->cmdqueue); atomic_set(&ssi->tx_usecnt, 0); diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index 9feec7009443..29fea74bff2e 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -4725,9 +4725,9 @@ static const struct net_device_ops qlge_netdev_ops = { .ndo_vlan_rx_kill_vid = qlge_vlan_rx_kill_vid, }; -static void ql_timer(unsigned long data) +static void ql_timer(struct timer_list *t) { - struct ql_adapter *qdev = (struct ql_adapter *)data; + struct ql_adapter *qdev = from_timer(qdev, t, timer); u32 var = 0; var = ql_read32(qdev, STS); @@ -4806,11 +4806,8 @@ static int qlge_probe(struct pci_dev *pdev, /* Start up the timer to trigger EEH if * the bus goes dead */ - init_timer_deferrable(&qdev->timer); - qdev->timer.data = (unsigned long)qdev; - qdev->timer.function = ql_timer; - qdev->timer.expires = jiffies + (5*HZ); - add_timer(&qdev->timer); + timer_setup(&qdev->timer, ql_timer, TIMER_DEFERRABLE); + mod_timer(&qdev->timer, jiffies + (5*HZ)); ql_link_off(qdev); ql_display_dev_info(ndev); atomic_set(&qdev->lb_count, 0); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index d7c49cf1d5e9..3247d2feda07 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2325,9 +2325,9 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) } /* Walk the forwarding table and purge stale entries */ -static void vxlan_cleanup(unsigned long arg) +static void vxlan_cleanup(struct timer_list *t) { - struct vxlan_dev *vxlan = (struct vxlan_dev *) arg; + struct vxlan_dev *vxlan = from_timer(vxlan, t, age_timer); unsigned long next_timer = jiffies + FDB_AGE_INTERVAL; unsigned int h; @@ -2647,9 +2647,7 @@ static void vxlan_setup(struct net_device *dev) INIT_LIST_HEAD(&vxlan->next); spin_lock_init(&vxlan->hash_lock); - init_timer_deferrable(&vxlan->age_timer); - vxlan->age_timer.function = vxlan_cleanup; - vxlan->age_timer.data = (unsigned long) vxlan; + timer_setup(&vxlan->age_timer, vxlan_cleanup, TIMER_DEFERRABLE); vxlan->dev = dev; diff --git a/drivers/net/wireless/ath/ath6kl/recovery.c b/drivers/net/wireless/ath/ath6kl/recovery.c index 3a8d5e97dc8e..c09e40c9010f 100644 --- a/drivers/net/wireless/ath/ath6kl/recovery.c +++ b/drivers/net/wireless/ath/ath6kl/recovery.c @@ -60,9 +60,9 @@ void ath6kl_recovery_hb_event(struct ath6kl *ar, u32 cookie) ar->fw_recovery.hb_pending = false; } -static void ath6kl_recovery_hb_timer(unsigned long data) +static void ath6kl_recovery_hb_timer(struct timer_list *t) { - struct ath6kl *ar = (struct ath6kl *) data; + struct ath6kl *ar = from_timer(ar, t, fw_recovery.hb_timer); int err; if (test_bit(RECOVERY_CLEANUP, &ar->flag) || @@ -104,9 +104,8 @@ void ath6kl_recovery_init(struct ath6kl *ar) recovery->seq_num = 0; recovery->hb_misscnt = 0; ar->fw_recovery.hb_pending = false; - ar->fw_recovery.hb_timer.function = ath6kl_recovery_hb_timer; - ar->fw_recovery.hb_timer.data = (unsigned long) ar; - init_timer_deferrable(&ar->fw_recovery.hb_timer); + timer_setup(&ar->fw_recovery.hb_timer, ath6kl_recovery_hb_timer, + TIMER_DEFERRABLE); if (ar->fw_recovery.hb_poll) mod_timer(&ar->fw_recovery.hb_timer, jiffies + diff --git a/include/linux/timer.h b/include/linux/timer.h index 9da903562ed4..10cc45ca5803 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -128,8 +128,6 @@ static inline void init_timer_on_stack_key(struct timer_list *timer, #define init_timer(timer) \ __init_timer((timer), 0) -#define init_timer_deferrable(timer) \ - __init_timer((timer), TIMER_DEFERRABLE) #define __setup_timer(_timer, _fn, _data, _flags) \ do { \ -- cgit v1.2.3 From 51487d9ed1e386f9f0863bbf385e5da8a586bff8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 4 Oct 2017 16:27:01 -0700 Subject: timer: Remove last user of TIMER_INITIALIZER Drops the last user of TIMER_INITIALIZER and adapts timer.h to use the internal version. Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Cc: linux-mips@linux-mips.org Cc: Petr Mladek Cc: Benjamin Herrenschmidt Cc: Lai Jiangshan Cc: Sebastian Reichel Cc: Kalle Valo Cc: Paul Mackerras Cc: Pavel Machek Cc: linux1394-devel@lists.sourceforge.net Cc: Chris Metcalf Cc: linux-s390@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: Mark Gross Cc: Wim Van Sebroeck Cc: Michael Ellerman Cc: Ursula Braun Cc: Geert Uytterhoeven Cc: Viresh Kumar Cc: Harish Patil Cc: Stephen Boyd Cc: Michael Reed Cc: Manish Chopra Cc: Len Brown Cc: Arnd Bergmann Cc: linux-pm@vger.kernel.org Cc: Heiko Carstens Cc: Tejun Heo Cc: Julian Wiedmann Cc: John Stultz Cc: "James E.J. Bottomley" Cc: linux-watchdog@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Oleg Nesterov Cc: Ralf Baechle Cc: Stefan Richter Cc: Guenter Roeck Cc: netdev@vger.kernel.org Cc: Martin Schwidefsky Cc: Andrew Morton Cc: linuxppc-dev@lists.ozlabs.org Cc: Sudip Mukherjee Link: https://lkml.kernel.org/r/1507159627-127660-8-git-send-email-keescook@chromium.org --- drivers/char/tlclk.c | 12 +++++------- include/linux/timer.h | 2 +- 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/tlclk.c b/drivers/char/tlclk.c index 6210bff46341..8eeb4190207d 100644 --- a/drivers/char/tlclk.c +++ b/drivers/char/tlclk.c @@ -184,9 +184,8 @@ static unsigned int telclk_interrupt; static int int_events; /* Event that generate a interrupt */ static int got_event; /* if events processing have been done */ -static void switchover_timeout(unsigned long data); -static struct timer_list switchover_timer = - TIMER_INITIALIZER(switchover_timeout , 0, 0); +static void switchover_timeout(struct timer_list *t); +static struct timer_list switchover_timer; static unsigned long tlclk_timer_data; static struct tlclk_alarms *alarm_events; @@ -805,7 +804,7 @@ static int __init tlclk_init(void) goto out3; } - init_timer(&switchover_timer); + timer_setup(&switchover_timer, switchover_timeout, 0); ret = misc_register(&tlclk_miscdev); if (ret < 0) { @@ -855,9 +854,9 @@ static void __exit tlclk_cleanup(void) } -static void switchover_timeout(unsigned long data) +static void switchover_timeout(struct timer_list *unused) { - unsigned long flags = *(unsigned long *) data; + unsigned long flags = tlclk_timer_data; if ((flags & 1)) { if ((inb(TLCLK_REG1) & 0x08) != (flags & 0x08)) @@ -922,7 +921,6 @@ static irqreturn_t tlclk_interrupt(int irq, void *dev_id) /* TIMEOUT in ~10ms */ switchover_timer.expires = jiffies + msecs_to_jiffies(10); tlclk_timer_data = inb(TLCLK_REG1); - switchover_timer.data = (unsigned long) &tlclk_timer_data; mod_timer(&switchover_timer, switchover_timer.expires); } else { got_event = 1; diff --git a/include/linux/timer.h b/include/linux/timer.h index 10cc45ca5803..4f7476e4a727 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -87,7 +87,7 @@ struct timer_list { #define DEFINE_TIMER(_name, _function, _expires, _data) \ struct timer_list _name = \ - TIMER_INITIALIZER(_function, _expires, _data) + __TIMER_INITIALIZER(_function, _expires, _data, 0) void init_timer_key(struct timer_list *timer, unsigned int flags, const char *name, struct lock_class_key *key); -- cgit v1.2.3 From fca7ce5b7c6d3eda8c2e011cff98d22e0fbd5097 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 4 Oct 2017 16:27:02 -0700 Subject: timer: Remove unused static initializer macros This removes the now unused TIMER_*INITIALIZER macros: TIMER_INITIALIZER TIMER_PINNED_INITIALIZER TIMER_DEFERRED_INITIALIZER TIMER_PINNED_DEFERRED_INITIALIZER Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Cc: linux-mips@linux-mips.org Cc: Petr Mladek Cc: Benjamin Herrenschmidt Cc: Lai Jiangshan Cc: Sebastian Reichel Cc: Kalle Valo Cc: Paul Mackerras Cc: Pavel Machek Cc: linux1394-devel@lists.sourceforge.net Cc: Chris Metcalf Cc: linux-s390@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: "James E.J. Bottomley" Cc: Wim Van Sebroeck Cc: Michael Ellerman Cc: Ursula Braun Cc: Geert Uytterhoeven Cc: Viresh Kumar Cc: Harish Patil Cc: Stephen Boyd Cc: Michael Reed Cc: Manish Chopra Cc: Len Brown Cc: Arnd Bergmann Cc: linux-pm@vger.kernel.org Cc: Heiko Carstens Cc: Tejun Heo Cc: Julian Wiedmann Cc: John Stultz Cc: Mark Gross Cc: linux-watchdog@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Oleg Nesterov Cc: Ralf Baechle Cc: Stefan Richter Cc: Guenter Roeck Cc: netdev@vger.kernel.org Cc: Martin Schwidefsky Cc: Andrew Morton Cc: linuxppc-dev@lists.ozlabs.org Cc: Sudip Mukherjee Link: https://lkml.kernel.org/r/1507159627-127660-9-git-send-email-keescook@chromium.org --- include/linux/timer.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index 4f7476e4a727..a33220311361 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -73,18 +73,6 @@ struct timer_list { __FILE__ ":" __stringify(__LINE__)) \ } -#define TIMER_INITIALIZER(_function, _expires, _data) \ - __TIMER_INITIALIZER((_function), (_expires), (_data), 0) - -#define TIMER_PINNED_INITIALIZER(_function, _expires, _data) \ - __TIMER_INITIALIZER((_function), (_expires), (_data), TIMER_PINNED) - -#define TIMER_DEFERRED_INITIALIZER(_function, _expires, _data) \ - __TIMER_INITIALIZER((_function), (_expires), (_data), TIMER_DEFERRABLE) - -#define TIMER_PINNED_DEFERRED_INITIALIZER(_function, _expires, _data) \ - __TIMER_INITIALIZER((_function), (_expires), (_data), TIMER_DEFERRABLE | TIMER_PINNED) - #define DEFINE_TIMER(_name, _function, _expires, _data) \ struct timer_list _name = \ __TIMER_INITIALIZER(_function, _expires, _data, 0) -- cgit v1.2.3 From 1d27e3e2252ba9d949ca82fbdb73cde102cb2067 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 4 Oct 2017 16:27:04 -0700 Subject: timer: Remove expires and data arguments from DEFINE_TIMER Drop the arguments from the macro and adjust all callers with the following script: perl -pi -e 's/DEFINE_TIMER\((.*), 0, 0\);/DEFINE_TIMER($1);/g;' \ $(git grep DEFINE_TIMER | cut -d: -f1 | sort -u | grep -v timer.h) Signed-off-by: Kees Cook Acked-by: Geert Uytterhoeven # for m68k parts Acked-by: Guenter Roeck # for watchdog parts Acked-by: David S. Miller # for networking parts Acked-by: Greg Kroah-Hartman Acked-by: Kalle Valo # for wireless parts Acked-by: Arnd Bergmann Cc: linux-mips@linux-mips.org Cc: Petr Mladek Cc: Benjamin Herrenschmidt Cc: Lai Jiangshan Cc: Sebastian Reichel Cc: Kalle Valo Cc: Paul Mackerras Cc: Pavel Machek Cc: linux1394-devel@lists.sourceforge.net Cc: Chris Metcalf Cc: linux-s390@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: "James E.J. Bottomley" Cc: Wim Van Sebroeck Cc: Michael Ellerman Cc: Ursula Braun Cc: Viresh Kumar Cc: Harish Patil Cc: Stephen Boyd Cc: Michael Reed Cc: Manish Chopra Cc: Len Brown Cc: Arnd Bergmann Cc: linux-pm@vger.kernel.org Cc: Heiko Carstens Cc: Tejun Heo Cc: Julian Wiedmann Cc: John Stultz Cc: Mark Gross Cc: linux-watchdog@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Oleg Nesterov Cc: Ralf Baechle Cc: Stefan Richter Cc: Guenter Roeck Cc: netdev@vger.kernel.org Cc: Martin Schwidefsky Cc: Andrew Morton Cc: linuxppc-dev@lists.ozlabs.org Cc: Sudip Mukherjee Link: https://lkml.kernel.org/r/1507159627-127660-11-git-send-email-keescook@chromium.org Signed-off-by: Thomas Gleixner --- arch/arm/mach-ixp4xx/dsmg600-setup.c | 2 +- arch/arm/mach-ixp4xx/nas100d-setup.c | 2 +- arch/m68k/amiga/amisound.c | 2 +- arch/m68k/mac/macboing.c | 2 +- arch/mips/mti-malta/malta-display.c | 2 +- arch/parisc/kernel/pdc_cons.c | 2 +- arch/s390/mm/cmm.c | 2 +- drivers/atm/idt77105.c | 4 ++-- drivers/atm/iphase.c | 2 +- drivers/block/ataflop.c | 8 ++++---- drivers/char/dtlk.c | 2 +- drivers/char/hangcheck-timer.c | 2 +- drivers/char/nwbutton.c | 2 +- drivers/char/rtc.c | 2 +- drivers/input/touchscreen/s3c2410_ts.c | 2 +- drivers/net/cris/eth_v10.c | 6 +++--- drivers/net/hamradio/yam.c | 2 +- drivers/net/wireless/atmel/at76c50x-usb.c | 2 +- drivers/staging/speakup/main.c | 2 +- drivers/staging/speakup/synth.c | 2 +- drivers/tty/cyclades.c | 2 +- drivers/tty/isicom.c | 2 +- drivers/tty/moxa.c | 2 +- drivers/tty/rocket.c | 2 +- drivers/tty/vt/keyboard.c | 2 +- drivers/tty/vt/vt.c | 2 +- drivers/watchdog/alim7101_wdt.c | 2 +- drivers/watchdog/machzwd.c | 2 +- drivers/watchdog/mixcomwd.c | 2 +- drivers/watchdog/sbc60xxwdt.c | 2 +- drivers/watchdog/sc520_wdt.c | 2 +- drivers/watchdog/via_wdt.c | 2 +- drivers/watchdog/w83877f_wdt.c | 2 +- drivers/xen/grant-table.c | 2 +- fs/pstore/platform.c | 2 +- include/linux/timer.h | 4 ++-- kernel/irq/spurious.c | 2 +- lib/random32.c | 2 +- net/atm/mpc.c | 2 +- net/decnet/dn_route.c | 2 +- net/ipv6/ip6_flowlabel.c | 2 +- net/netrom/nr_loopback.c | 2 +- security/keys/gc.c | 2 +- sound/oss/midibuf.c | 2 +- sound/oss/soundcard.c | 2 +- sound/oss/sys_timer.c | 2 +- sound/oss/uart6850.c | 2 +- 47 files changed, 54 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-ixp4xx/dsmg600-setup.c b/arch/arm/mach-ixp4xx/dsmg600-setup.c index b3bd0e137f6d..b3689a141ec6 100644 --- a/arch/arm/mach-ixp4xx/dsmg600-setup.c +++ b/arch/arm/mach-ixp4xx/dsmg600-setup.c @@ -174,7 +174,7 @@ static int power_button_countdown; #define PBUTTON_HOLDDOWN_COUNT 4 /* 2 secs */ static void dsmg600_power_handler(unsigned long data); -static DEFINE_TIMER(dsmg600_power_timer, dsmg600_power_handler, 0, 0); +static DEFINE_TIMER(dsmg600_power_timer, dsmg600_power_handler); static void dsmg600_power_handler(unsigned long data) { diff --git a/arch/arm/mach-ixp4xx/nas100d-setup.c b/arch/arm/mach-ixp4xx/nas100d-setup.c index 4e0f762bc651..562d05f9888e 100644 --- a/arch/arm/mach-ixp4xx/nas100d-setup.c +++ b/arch/arm/mach-ixp4xx/nas100d-setup.c @@ -197,7 +197,7 @@ static int power_button_countdown; #define PBUTTON_HOLDDOWN_COUNT 4 /* 2 secs */ static void nas100d_power_handler(unsigned long data); -static DEFINE_TIMER(nas100d_power_timer, nas100d_power_handler, 0, 0); +static DEFINE_TIMER(nas100d_power_timer, nas100d_power_handler); static void nas100d_power_handler(unsigned long data) { diff --git a/arch/m68k/amiga/amisound.c b/arch/m68k/amiga/amisound.c index 90a60d758f8b..a23f48181fd6 100644 --- a/arch/m68k/amiga/amisound.c +++ b/arch/m68k/amiga/amisound.c @@ -66,7 +66,7 @@ void __init amiga_init_sound(void) } static void nosound( unsigned long ignored ); -static DEFINE_TIMER(sound_timer, nosound, 0, 0); +static DEFINE_TIMER(sound_timer, nosound); void amiga_mksound( unsigned int hz, unsigned int ticks ) { diff --git a/arch/m68k/mac/macboing.c b/arch/m68k/mac/macboing.c index ffaa1f6439ae..9a52aff183d0 100644 --- a/arch/m68k/mac/macboing.c +++ b/arch/m68k/mac/macboing.c @@ -56,7 +56,7 @@ static void ( *mac_special_bell )( unsigned int, unsigned int, unsigned int ); /* * our timer to start/continue/stop the bell */ -static DEFINE_TIMER(mac_sound_timer, mac_nosound, 0, 0); +static DEFINE_TIMER(mac_sound_timer, mac_nosound); /* * Sort of initialize the sound chip (called from mac_mksound on the first diff --git a/arch/mips/mti-malta/malta-display.c b/arch/mips/mti-malta/malta-display.c index ac813158b9b8..063de44675ce 100644 --- a/arch/mips/mti-malta/malta-display.c +++ b/arch/mips/mti-malta/malta-display.c @@ -37,7 +37,7 @@ void mips_display_message(const char *str) } static void scroll_display_message(unsigned long unused); -static DEFINE_TIMER(mips_scroll_timer, scroll_display_message, 0, 0); +static DEFINE_TIMER(mips_scroll_timer, scroll_display_message); static void scroll_display_message(unsigned long unused) { diff --git a/arch/parisc/kernel/pdc_cons.c b/arch/parisc/kernel/pdc_cons.c index 10a5ae9553fd..27a2dd616a7d 100644 --- a/arch/parisc/kernel/pdc_cons.c +++ b/arch/parisc/kernel/pdc_cons.c @@ -92,7 +92,7 @@ static int pdc_console_setup(struct console *co, char *options) #define PDC_CONS_POLL_DELAY (30 * HZ / 1000) static void pdc_console_poll(unsigned long unused); -static DEFINE_TIMER(pdc_console_timer, pdc_console_poll, 0, 0); +static DEFINE_TIMER(pdc_console_timer, pdc_console_poll); static struct tty_port tty_port; static int pdc_console_tty_open(struct tty_struct *tty, struct file *filp) diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 829c63dbc81a..2dbdcd85b68f 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -56,7 +56,7 @@ static DEFINE_SPINLOCK(cmm_lock); static struct task_struct *cmm_thread_ptr; static DECLARE_WAIT_QUEUE_HEAD(cmm_thread_wait); -static DEFINE_TIMER(cmm_timer, NULL, 0, 0); +static DEFINE_TIMER(cmm_timer, NULL); static void cmm_timer_fn(unsigned long); static void cmm_set_timer(void); diff --git a/drivers/atm/idt77105.c b/drivers/atm/idt77105.c index 082aa02abc57..57af9fd198e4 100644 --- a/drivers/atm/idt77105.c +++ b/drivers/atm/idt77105.c @@ -49,8 +49,8 @@ static void idt77105_stats_timer_func(unsigned long); static void idt77105_restart_timer_func(unsigned long); -static DEFINE_TIMER(stats_timer, idt77105_stats_timer_func, 0, 0); -static DEFINE_TIMER(restart_timer, idt77105_restart_timer_func, 0, 0); +static DEFINE_TIMER(stats_timer, idt77105_stats_timer_func); +static DEFINE_TIMER(restart_timer, idt77105_restart_timer_func); static int start_timer = 1; static struct idt77105_priv *idt77105_all = NULL; diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c index fc72b763fdd7..ad6b582c268e 100644 --- a/drivers/atm/iphase.c +++ b/drivers/atm/iphase.c @@ -76,7 +76,7 @@ static IADEV *ia_dev[8]; static struct atm_dev *_ia_dev[8]; static int iadev_count; static void ia_led_timer(unsigned long arg); -static DEFINE_TIMER(ia_timer, ia_led_timer, 0, 0); +static DEFINE_TIMER(ia_timer, ia_led_timer); static int IA_TX_BUF = DFL_TX_BUFFERS, IA_TX_BUF_SZ = DFL_TX_BUF_SZ; static int IA_RX_BUF = DFL_RX_BUFFERS, IA_RX_BUF_SZ = DFL_RX_BUF_SZ; static uint IADebugFlag = /* IF_IADBG_ERR | IF_IADBG_CBR| IF_IADBG_INIT_ADAPTER diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index 92da886180aa..ae596e55bcb6 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -373,10 +373,10 @@ static void floppy_release(struct gendisk *disk, fmode_t mode); /************************* End of Prototypes **************************/ -static DEFINE_TIMER(motor_off_timer, fd_motor_off_timer, 0, 0); -static DEFINE_TIMER(readtrack_timer, fd_readtrack_check, 0, 0); -static DEFINE_TIMER(timeout_timer, fd_times_out, 0, 0); -static DEFINE_TIMER(fd_timer, check_change, 0, 0); +static DEFINE_TIMER(motor_off_timer, fd_motor_off_timer); +static DEFINE_TIMER(readtrack_timer, fd_readtrack_check); +static DEFINE_TIMER(timeout_timer, fd_times_out); +static DEFINE_TIMER(fd_timer, check_change); static void fd_end_request_cur(blk_status_t err) { diff --git a/drivers/char/dtlk.c b/drivers/char/dtlk.c index 58471394beb9..1a0385ed6417 100644 --- a/drivers/char/dtlk.c +++ b/drivers/char/dtlk.c @@ -84,7 +84,7 @@ static int dtlk_has_indexing; static unsigned int dtlk_portlist[] = {0x25e, 0x29e, 0x2de, 0x31e, 0x35e, 0x39e, 0}; static wait_queue_head_t dtlk_process_list; -static DEFINE_TIMER(dtlk_timer, dtlk_timer_tick, 0, 0); +static DEFINE_TIMER(dtlk_timer, dtlk_timer_tick); /* prototypes for file_operations struct */ static ssize_t dtlk_read(struct file *, char __user *, diff --git a/drivers/char/hangcheck-timer.c b/drivers/char/hangcheck-timer.c index 5406b90bf626..5b8db2ed844d 100644 --- a/drivers/char/hangcheck-timer.c +++ b/drivers/char/hangcheck-timer.c @@ -124,7 +124,7 @@ static unsigned long long hangcheck_tsc, hangcheck_tsc_margin; static void hangcheck_fire(unsigned long); -static DEFINE_TIMER(hangcheck_ticktock, hangcheck_fire, 0, 0); +static DEFINE_TIMER(hangcheck_ticktock, hangcheck_fire); static void hangcheck_fire(unsigned long data) { diff --git a/drivers/char/nwbutton.c b/drivers/char/nwbutton.c index e6d0d271c58c..44006ed9558f 100644 --- a/drivers/char/nwbutton.c +++ b/drivers/char/nwbutton.c @@ -27,7 +27,7 @@ static void button_sequence_finished (unsigned long parameters); static int button_press_count; /* The count of button presses */ /* Times for the end of a sequence */ -static DEFINE_TIMER(button_timer, button_sequence_finished, 0, 0); +static DEFINE_TIMER(button_timer, button_sequence_finished); static DECLARE_WAIT_QUEUE_HEAD(button_wait_queue); /* Used for blocking read */ static char button_output_buffer[32]; /* Stores data to write out of device */ static int bcount; /* The number of bytes in the buffer */ diff --git a/drivers/char/rtc.c b/drivers/char/rtc.c index 974d48927b07..616871e68e09 100644 --- a/drivers/char/rtc.c +++ b/drivers/char/rtc.c @@ -137,7 +137,7 @@ static DECLARE_WAIT_QUEUE_HEAD(rtc_wait); #ifdef RTC_IRQ static void rtc_dropped_irq(unsigned long data); -static DEFINE_TIMER(rtc_irq_timer, rtc_dropped_irq, 0, 0); +static DEFINE_TIMER(rtc_irq_timer, rtc_dropped_irq); #endif static ssize_t rtc_read(struct file *file, char __user *buf, diff --git a/drivers/input/touchscreen/s3c2410_ts.c b/drivers/input/touchscreen/s3c2410_ts.c index 3b3db8c868e0..d3265b6b58b8 100644 --- a/drivers/input/touchscreen/s3c2410_ts.c +++ b/drivers/input/touchscreen/s3c2410_ts.c @@ -145,7 +145,7 @@ static void touch_timer_fire(unsigned long data) } } -static DEFINE_TIMER(touch_timer, touch_timer_fire, 0, 0); +static DEFINE_TIMER(touch_timer, touch_timer_fire); /** * stylus_irq - touchscreen stylus event interrupt diff --git a/drivers/net/cris/eth_v10.c b/drivers/net/cris/eth_v10.c index 017f48cdcab9..1fcc86fa4e05 100644 --- a/drivers/net/cris/eth_v10.c +++ b/drivers/net/cris/eth_v10.c @@ -165,8 +165,8 @@ static unsigned int network_rec_config_shadow = 0; static unsigned int network_tr_ctrl_shadow = 0; /* Network speed indication. */ -static DEFINE_TIMER(speed_timer, NULL, 0, 0); -static DEFINE_TIMER(clear_led_timer, NULL, 0, 0); +static DEFINE_TIMER(speed_timer, NULL); +static DEFINE_TIMER(clear_led_timer, NULL); static int current_speed; /* Speed read from transceiver */ static int current_speed_selection; /* Speed selected by user */ static unsigned long led_next_time; @@ -174,7 +174,7 @@ static int led_active; static int rx_queue_len; /* Duplex */ -static DEFINE_TIMER(duplex_timer, NULL, 0, 0); +static DEFINE_TIMER(duplex_timer, NULL); static int full_duplex; static enum duplex current_duplex; diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index 7a7c5224a336..104f71fa9c5e 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -157,7 +157,7 @@ static struct net_device *yam_devs[NR_PORTS]; static struct yam_mcs *yam_data; -static DEFINE_TIMER(yam_timer, NULL, 0, 0); +static DEFINE_TIMER(yam_timer, NULL); /* --------------------------------------------------------------------- */ diff --git a/drivers/net/wireless/atmel/at76c50x-usb.c b/drivers/net/wireless/atmel/at76c50x-usb.c index 94bf01f8b2a8..ede89d4ffc88 100644 --- a/drivers/net/wireless/atmel/at76c50x-usb.c +++ b/drivers/net/wireless/atmel/at76c50x-usb.c @@ -519,7 +519,7 @@ exit: /* LED trigger */ static int tx_activity; static void at76_ledtrig_tx_timerfunc(unsigned long data); -static DEFINE_TIMER(ledtrig_tx_timer, at76_ledtrig_tx_timerfunc, 0, 0); +static DEFINE_TIMER(ledtrig_tx_timer, at76_ledtrig_tx_timerfunc); DEFINE_LED_TRIGGER(ledtrig_tx); static void at76_ledtrig_tx_timerfunc(unsigned long data) diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c index 56f7be6af1f6..585925bb49a4 100644 --- a/drivers/staging/speakup/main.c +++ b/drivers/staging/speakup/main.c @@ -1165,7 +1165,7 @@ static const int NUM_CTL_LABELS = (MSG_CTL_END - MSG_CTL_START + 1); static void read_all_doc(struct vc_data *vc); static void cursor_done(u_long data); -static DEFINE_TIMER(cursor_timer, cursor_done, 0, 0); +static DEFINE_TIMER(cursor_timer, cursor_done); static void do_handle_shift(struct vc_data *vc, u_char value, char up_flag) { diff --git a/drivers/staging/speakup/synth.c b/drivers/staging/speakup/synth.c index a1ca68c76579..6ddd3fc3f08d 100644 --- a/drivers/staging/speakup/synth.c +++ b/drivers/staging/speakup/synth.c @@ -158,7 +158,7 @@ static void thread_wake_up(u_long data) wake_up_interruptible_all(&speakup_event); } -static DEFINE_TIMER(thread_timer, thread_wake_up, 0, 0); +static DEFINE_TIMER(thread_timer, thread_wake_up); void synth_start(void) { diff --git a/drivers/tty/cyclades.c b/drivers/tty/cyclades.c index d272bc4e7fb5..dac8a1a8e4ac 100644 --- a/drivers/tty/cyclades.c +++ b/drivers/tty/cyclades.c @@ -283,7 +283,7 @@ static void cyz_poll(unsigned long); /* The Cyclades-Z polling cycle is defined by this variable */ static long cyz_polling_cycle = CZ_DEF_POLL; -static DEFINE_TIMER(cyz_timerlist, cyz_poll, 0, 0); +static DEFINE_TIMER(cyz_timerlist, cyz_poll); #else /* CONFIG_CYZ_INTR */ static void cyz_rx_restart(unsigned long); diff --git a/drivers/tty/isicom.c b/drivers/tty/isicom.c index 61ecdd6b2fc2..40af32108ff5 100644 --- a/drivers/tty/isicom.c +++ b/drivers/tty/isicom.c @@ -177,7 +177,7 @@ static struct tty_driver *isicom_normal; static void isicom_tx(unsigned long _data); static void isicom_start(struct tty_struct *tty); -static DEFINE_TIMER(tx, isicom_tx, 0, 0); +static DEFINE_TIMER(tx, isicom_tx); /* baud index mappings from linux defns to isi */ diff --git a/drivers/tty/moxa.c b/drivers/tty/moxa.c index 7f3d4cb0341b..93d37655d928 100644 --- a/drivers/tty/moxa.c +++ b/drivers/tty/moxa.c @@ -428,7 +428,7 @@ static const struct tty_port_operations moxa_port_ops = { }; static struct tty_driver *moxaDriver; -static DEFINE_TIMER(moxaTimer, moxa_poll, 0, 0); +static DEFINE_TIMER(moxaTimer, moxa_poll); /* * HW init diff --git a/drivers/tty/rocket.c b/drivers/tty/rocket.c index 20d79a6007d5..aa695fda1084 100644 --- a/drivers/tty/rocket.c +++ b/drivers/tty/rocket.c @@ -111,7 +111,7 @@ static struct r_port *rp_table[MAX_RP_PORTS]; /* The main repository of static unsigned int xmit_flags[NUM_BOARDS]; /* Bit significant, indicates port had data to transmit. */ /* eg. Bit 0 indicates port 0 has xmit data, ... */ static atomic_t rp_num_ports_open; /* Number of serial ports open */ -static DEFINE_TIMER(rocket_timer, rp_do_poll, 0, 0); +static DEFINE_TIMER(rocket_timer, rp_do_poll); static unsigned long board1; /* ISA addresses, retrieved from rocketport.conf */ static unsigned long board2; diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c index f4166263bb3a..f974d6340d04 100644 --- a/drivers/tty/vt/keyboard.c +++ b/drivers/tty/vt/keyboard.c @@ -250,7 +250,7 @@ static void kd_nosound(unsigned long ignored) input_handler_for_each_handle(&kbd_handler, &zero, kd_sound_helper); } -static DEFINE_TIMER(kd_mksound_timer, kd_nosound, 0, 0); +static DEFINE_TIMER(kd_mksound_timer, kd_nosound); void kd_mksound(unsigned int hz, unsigned int ticks) { diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 2ebaba16f785..602d71630952 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -228,7 +228,7 @@ static int scrollback_delta; */ int (*console_blank_hook)(int); -static DEFINE_TIMER(console_timer, blank_screen_t, 0, 0); +static DEFINE_TIMER(console_timer, blank_screen_t); static int blank_state; static int blank_timer_expired; enum { diff --git a/drivers/watchdog/alim7101_wdt.c b/drivers/watchdog/alim7101_wdt.c index 3c1f6ac68ea9..18e896eeca62 100644 --- a/drivers/watchdog/alim7101_wdt.c +++ b/drivers/watchdog/alim7101_wdt.c @@ -71,7 +71,7 @@ MODULE_PARM_DESC(use_gpio, "Use the gpio watchdog (required by old cobalt boards)."); static void wdt_timer_ping(unsigned long); -static DEFINE_TIMER(timer, wdt_timer_ping, 0, 0); +static DEFINE_TIMER(timer, wdt_timer_ping); static unsigned long next_heartbeat; static unsigned long wdt_is_open; static char wdt_expect_close; diff --git a/drivers/watchdog/machzwd.c b/drivers/watchdog/machzwd.c index 9826b59ef734..8a616a57bb90 100644 --- a/drivers/watchdog/machzwd.c +++ b/drivers/watchdog/machzwd.c @@ -127,7 +127,7 @@ static int zf_action = GEN_RESET; static unsigned long zf_is_open; static char zf_expect_close; static DEFINE_SPINLOCK(zf_port_lock); -static DEFINE_TIMER(zf_timer, zf_ping, 0, 0); +static DEFINE_TIMER(zf_timer, zf_ping); static unsigned long next_heartbeat; diff --git a/drivers/watchdog/mixcomwd.c b/drivers/watchdog/mixcomwd.c index be86ea359eee..c9e38096ea91 100644 --- a/drivers/watchdog/mixcomwd.c +++ b/drivers/watchdog/mixcomwd.c @@ -105,7 +105,7 @@ static unsigned long mixcomwd_opened; /* long req'd for setbit --RR */ static int watchdog_port; static int mixcomwd_timer_alive; -static DEFINE_TIMER(mixcomwd_timer, mixcomwd_timerfun, 0, 0); +static DEFINE_TIMER(mixcomwd_timer, mixcomwd_timerfun); static char expect_close; static bool nowayout = WATCHDOG_NOWAYOUT; diff --git a/drivers/watchdog/sbc60xxwdt.c b/drivers/watchdog/sbc60xxwdt.c index 2eef58a0cf05..8d589939bc84 100644 --- a/drivers/watchdog/sbc60xxwdt.c +++ b/drivers/watchdog/sbc60xxwdt.c @@ -113,7 +113,7 @@ MODULE_PARM_DESC(nowayout, __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); static void wdt_timer_ping(unsigned long); -static DEFINE_TIMER(timer, wdt_timer_ping, 0, 0); +static DEFINE_TIMER(timer, wdt_timer_ping); static unsigned long next_heartbeat; static unsigned long wdt_is_open; static char wdt_expect_close; diff --git a/drivers/watchdog/sc520_wdt.c b/drivers/watchdog/sc520_wdt.c index 1cfd3f6a13d5..3e9bbaa37bf4 100644 --- a/drivers/watchdog/sc520_wdt.c +++ b/drivers/watchdog/sc520_wdt.c @@ -124,7 +124,7 @@ MODULE_PARM_DESC(nowayout, static __u16 __iomem *wdtmrctl; static void wdt_timer_ping(unsigned long); -static DEFINE_TIMER(timer, wdt_timer_ping, 0, 0); +static DEFINE_TIMER(timer, wdt_timer_ping); static unsigned long next_heartbeat; static unsigned long wdt_is_open; static char wdt_expect_close; diff --git a/drivers/watchdog/via_wdt.c b/drivers/watchdog/via_wdt.c index 5f9cbc37520d..ad3c3be13b40 100644 --- a/drivers/watchdog/via_wdt.c +++ b/drivers/watchdog/via_wdt.c @@ -68,7 +68,7 @@ static struct resource wdt_res; static void __iomem *wdt_mem; static unsigned int mmio; static void wdt_timer_tick(unsigned long data); -static DEFINE_TIMER(timer, wdt_timer_tick, 0, 0); +static DEFINE_TIMER(timer, wdt_timer_tick); /* The timer that pings the watchdog */ static unsigned long next_heartbeat; /* the next_heartbeat for the timer */ diff --git a/drivers/watchdog/w83877f_wdt.c b/drivers/watchdog/w83877f_wdt.c index f0483c75ed32..ba6b680af100 100644 --- a/drivers/watchdog/w83877f_wdt.c +++ b/drivers/watchdog/w83877f_wdt.c @@ -98,7 +98,7 @@ MODULE_PARM_DESC(nowayout, __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); static void wdt_timer_ping(unsigned long); -static DEFINE_TIMER(timer, wdt_timer_ping, 0, 0); +static DEFINE_TIMER(timer, wdt_timer_ping); static unsigned long next_heartbeat; static unsigned long wdt_is_open; static char wdt_expect_close; diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 2c6a9114d332..a8721d718186 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -305,7 +305,7 @@ struct deferred_entry { }; static LIST_HEAD(deferred_list); static void gnttab_handle_deferred(unsigned long); -static DEFINE_TIMER(deferred_timer, gnttab_handle_deferred, 0, 0); +static DEFINE_TIMER(deferred_timer, gnttab_handle_deferred); static void gnttab_handle_deferred(unsigned long unused) { diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 2b21d180157c..ec7199e859d2 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -62,7 +62,7 @@ MODULE_PARM_DESC(update_ms, "milliseconds before pstore updates its content " static int pstore_new_entry; static void pstore_timefunc(unsigned long); -static DEFINE_TIMER(pstore_timer, pstore_timefunc, 0, 0); +static DEFINE_TIMER(pstore_timer, pstore_timefunc); static void pstore_dowork(struct work_struct *); static DECLARE_WORK(pstore_work, pstore_dowork); diff --git a/include/linux/timer.h b/include/linux/timer.h index a33220311361..91e5a2cc81b5 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -73,9 +73,9 @@ struct timer_list { __FILE__ ":" __stringify(__LINE__)) \ } -#define DEFINE_TIMER(_name, _function, _expires, _data) \ +#define DEFINE_TIMER(_name, _function) \ struct timer_list _name = \ - __TIMER_INITIALIZER(_function, _expires, _data, 0) + __TIMER_INITIALIZER(_function, 0, 0, 0) void init_timer_key(struct timer_list *timer, unsigned int flags, const char *name, struct lock_class_key *key); diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index 061ba7eed4ed..c805e8691c22 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -20,7 +20,7 @@ static int irqfixup __read_mostly; #define POLL_SPURIOUS_IRQ_INTERVAL (HZ/10) static void poll_spurious_irqs(unsigned long dummy); -static DEFINE_TIMER(poll_spurious_irq_timer, poll_spurious_irqs, 0, 0); +static DEFINE_TIMER(poll_spurious_irq_timer, poll_spurious_irqs); static int irq_poll_cpu; static atomic_t irq_poll_active; diff --git a/lib/random32.c b/lib/random32.c index fa594b1140e6..6e91b75c113f 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -214,7 +214,7 @@ core_initcall(prandom_init); static void __prandom_timer(unsigned long dontcare); -static DEFINE_TIMER(seed_timer, __prandom_timer, 0, 0); +static DEFINE_TIMER(seed_timer, __prandom_timer); static void __prandom_timer(unsigned long dontcare) { diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 5677147209e8..63138c8c2269 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -121,7 +121,7 @@ static struct notifier_block mpoa_notifier = { struct mpoa_client *mpcs = NULL; /* FIXME */ static struct atm_mpoa_qos *qos_head = NULL; -static DEFINE_TIMER(mpc_timer, NULL, 0, 0); +static DEFINE_TIMER(mpc_timer, NULL); static struct mpoa_client *find_mpc_by_itfnum(int itf) diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 0bd3afd01dd2..6538632fbd03 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -131,7 +131,7 @@ static struct dn_rt_hash_bucket *dn_rt_hash_table; static unsigned int dn_rt_hash_mask; static struct timer_list dn_route_timer; -static DEFINE_TIMER(dn_rt_flush_timer, dn_run_flush, 0, 0); +static DEFINE_TIMER(dn_rt_flush_timer, dn_run_flush); int decnet_dst_gc_interval = 2; static struct dst_ops dn_dst_ops = { diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 8081bafe441b..b39d0908be2e 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -47,7 +47,7 @@ static atomic_t fl_size = ATOMIC_INIT(0); static struct ip6_flowlabel __rcu *fl_ht[FL_HASH_MASK+1]; static void ip6_fl_gc(unsigned long dummy); -static DEFINE_TIMER(ip6_fl_gc_timer, ip6_fl_gc, 0, 0); +static DEFINE_TIMER(ip6_fl_gc_timer, ip6_fl_gc); /* FL hash table lock: it protects only of GC */ diff --git a/net/netrom/nr_loopback.c b/net/netrom/nr_loopback.c index 94d4e922af53..989ae647825e 100644 --- a/net/netrom/nr_loopback.c +++ b/net/netrom/nr_loopback.c @@ -18,7 +18,7 @@ static void nr_loopback_timer(unsigned long); static struct sk_buff_head loopback_queue; -static DEFINE_TIMER(loopback_timer, nr_loopback_timer, 0, 0); +static DEFINE_TIMER(loopback_timer, nr_loopback_timer); void __init nr_loopback_init(void) { diff --git a/security/keys/gc.c b/security/keys/gc.c index 87cb260e4890..8673f7f58ead 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -30,7 +30,7 @@ DECLARE_WORK(key_gc_work, key_garbage_collector); * Reaper for links from keyrings to dead keys. */ static void key_gc_timer_func(unsigned long); -static DEFINE_TIMER(key_gc_timer, key_gc_timer_func, 0, 0); +static DEFINE_TIMER(key_gc_timer, key_gc_timer_func); static time_t key_gc_next_run = LONG_MAX; static struct key_type *key_gc_dead_keytype; diff --git a/sound/oss/midibuf.c b/sound/oss/midibuf.c index 701c7625c971..1277df815d5b 100644 --- a/sound/oss/midibuf.c +++ b/sound/oss/midibuf.c @@ -52,7 +52,7 @@ static struct midi_parms parms[MAX_MIDI_DEV]; static void midi_poll(unsigned long dummy); -static DEFINE_TIMER(poll_timer, midi_poll, 0, 0); +static DEFINE_TIMER(poll_timer, midi_poll); static volatile int open_devs; static DEFINE_SPINLOCK(lock); diff --git a/sound/oss/soundcard.c b/sound/oss/soundcard.c index b70c7c8f9c5d..4391062e5cfd 100644 --- a/sound/oss/soundcard.c +++ b/sound/oss/soundcard.c @@ -662,7 +662,7 @@ static void do_sequencer_timer(unsigned long dummy) } -static DEFINE_TIMER(seq_timer, do_sequencer_timer, 0, 0); +static DEFINE_TIMER(seq_timer, do_sequencer_timer); void request_sound_timer(int count) { diff --git a/sound/oss/sys_timer.c b/sound/oss/sys_timer.c index d17019d25b99..8a4b5625dba6 100644 --- a/sound/oss/sys_timer.c +++ b/sound/oss/sys_timer.c @@ -28,7 +28,7 @@ static unsigned long prev_event_time; static void poll_def_tmr(unsigned long dummy); static DEFINE_SPINLOCK(lock); -static DEFINE_TIMER(def_tmr, poll_def_tmr, 0, 0); +static DEFINE_TIMER(def_tmr, poll_def_tmr); static unsigned long tmr2ticks(int tmr_value) diff --git a/sound/oss/uart6850.c b/sound/oss/uart6850.c index eda32d7eddbd..a9d3f7568525 100644 --- a/sound/oss/uart6850.c +++ b/sound/oss/uart6850.c @@ -78,7 +78,7 @@ static void (*midi_input_intr) (int dev, unsigned char data); static void poll_uart6850(unsigned long dummy); -static DEFINE_TIMER(uart6850_timer, poll_uart6850, 0, 0); +static DEFINE_TIMER(uart6850_timer, poll_uart6850); static void uart6850_input_loop(void) { -- cgit v1.2.3 From 8ede369b2cccfa585e2969bbed18edc0e2a18c50 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 4 Oct 2017 16:27:05 -0700 Subject: timer: Remove expires argument from __TIMER_INITIALIZER() The expires field is normally initialized during the first mod_timer() call. It was unused by all callers, so remove it from the macro. Signed-off-by: Kees Cook Cc: linux-mips@linux-mips.org Cc: Petr Mladek Cc: Benjamin Herrenschmidt Cc: Lai Jiangshan Cc: Sebastian Reichel Cc: Kalle Valo Cc: Paul Mackerras Cc: Pavel Machek Cc: linux1394-devel@lists.sourceforge.net Cc: Chris Metcalf Cc: linux-s390@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: "James E.J. Bottomley" Cc: Wim Van Sebroeck Cc: Michael Ellerman Cc: Ursula Braun Cc: Geert Uytterhoeven Cc: Viresh Kumar Cc: Harish Patil Cc: Stephen Boyd Cc: Michael Reed Cc: Manish Chopra Cc: Len Brown Cc: Arnd Bergmann Cc: linux-pm@vger.kernel.org Cc: Heiko Carstens Cc: Tejun Heo Cc: Julian Wiedmann Cc: John Stultz Cc: Mark Gross Cc: linux-watchdog@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Oleg Nesterov Cc: Ralf Baechle Cc: Stefan Richter Cc: Guenter Roeck Cc: netdev@vger.kernel.org Cc: Martin Schwidefsky Cc: Andrew Morton Cc: linuxppc-dev@lists.ozlabs.org Cc: Sudip Mukherjee Link: https://lkml.kernel.org/r/1507159627-127660-12-git-send-email-keescook@chromium.org Signed-off-by: Thomas Gleixner --- include/linux/kthread.h | 2 +- include/linux/timer.h | 5 ++--- include/linux/workqueue.h | 2 +- 3 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 82e197eeac91..0d622b350d3f 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -117,7 +117,7 @@ struct kthread_delayed_work { #define KTHREAD_DELAYED_WORK_INIT(dwork, fn) { \ .work = KTHREAD_WORK_INIT((dwork).work, (fn)), \ .timer = __TIMER_INITIALIZER(kthread_delayed_work_timer_fn, \ - 0, (unsigned long)&(dwork), \ + (unsigned long)&(dwork), \ TIMER_IRQSAFE), \ } diff --git a/include/linux/timer.h b/include/linux/timer.h index 91e5a2cc81b5..10685c33e679 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -63,10 +63,9 @@ struct timer_list { #define TIMER_TRACE_FLAGMASK (TIMER_MIGRATING | TIMER_DEFERRABLE | TIMER_PINNED | TIMER_IRQSAFE) -#define __TIMER_INITIALIZER(_function, _expires, _data, _flags) { \ +#define __TIMER_INITIALIZER(_function, _data, _flags) { \ .entry = { .next = TIMER_ENTRY_STATIC }, \ .function = (_function), \ - .expires = (_expires), \ .data = (_data), \ .flags = (_flags), \ __TIMER_LOCKDEP_MAP_INITIALIZER( \ @@ -75,7 +74,7 @@ struct timer_list { #define DEFINE_TIMER(_name, _function) \ struct timer_list _name = \ - __TIMER_INITIALIZER(_function, 0, 0, 0) + __TIMER_INITIALIZER(_function, 0, 0) void init_timer_key(struct timer_list *timer, unsigned int flags, const char *name, struct lock_class_key *key); diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 1c49431f3121..f4960260feaf 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -176,7 +176,7 @@ struct execute_work { #define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \ .work = __WORK_INITIALIZER((n).work, (f)), \ .timer = __TIMER_INITIALIZER(delayed_work_timer_fn, \ - 0, (unsigned long)&(n), \ + (unsigned long)&(n), \ (tflags) | TIMER_IRQSAFE), \ } -- cgit v1.2.3 From fe5c3b69b540e3387223a696f327c1bb8880d1ac Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 4 Oct 2017 16:27:06 -0700 Subject: kthread: Convert callback to use from_timer() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch kthread to use from_timer() and pass the timer pointer explicitly. Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Cc: linux-mips@linux-mips.org Cc: Len Brown Cc: Benjamin Herrenschmidt Cc: Lai Jiangshan Cc: Sebastian Reichel Cc: Kalle Valo Cc: Paul Mackerras Cc: Pavel Machek Cc: linux1394-devel@lists.sourceforge.net Cc: Chris Metcalf Cc: linux-s390@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: "James E.J. Bottomley" Cc: Wim Van Sebroeck Cc: Michael Ellerman Cc: Ursula Braun Cc: Geert Uytterhoeven Cc: Viresh Kumar Cc: Harish Patil Cc: Stephen Boyd Cc: Guenter Roeck Cc: Manish Chopra Cc: Petr Mladek Cc: Arnd Bergmann Cc: linux-pm@vger.kernel.org Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: Julian Wiedmann Cc: John Stultz Cc: Mark Gross Cc: linux-watchdog@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Oleg Nesterov Cc: Ralf Baechle Cc: Stefan Richter Cc: Michael Reed Cc: netdev@vger.kernel.org Cc: Tejun Heo Cc: Andrew Morton Cc: linuxppc-dev@lists.ozlabs.org Cc: Sudip Mukherjee Link: https://lkml.kernel.org/r/1507159627-127660-13-git-send-email-keescook@chromium.org --- include/linux/kthread.h | 10 +++++----- kernel/kthread.c | 10 ++++------ 2 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 0d622b350d3f..35cbe3b0ce5b 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -75,7 +75,7 @@ extern int tsk_fork_get_node(struct task_struct *tsk); */ struct kthread_work; typedef void (*kthread_work_func_t)(struct kthread_work *work); -void kthread_delayed_work_timer_fn(unsigned long __data); +void kthread_delayed_work_timer_fn(struct timer_list *t); enum { KTW_FREEZABLE = 1 << 0, /* freeze during suspend */ @@ -116,8 +116,8 @@ struct kthread_delayed_work { #define KTHREAD_DELAYED_WORK_INIT(dwork, fn) { \ .work = KTHREAD_WORK_INIT((dwork).work, (fn)), \ - .timer = __TIMER_INITIALIZER(kthread_delayed_work_timer_fn, \ - (unsigned long)&(dwork), \ + .timer = __TIMER_INITIALIZER((TIMER_FUNC_TYPE)kthread_delayed_work_timer_fn,\ + (TIMER_DATA_TYPE)&(dwork.timer), \ TIMER_IRQSAFE), \ } @@ -164,8 +164,8 @@ extern void __kthread_init_worker(struct kthread_worker *worker, do { \ kthread_init_work(&(dwork)->work, (fn)); \ __setup_timer(&(dwork)->timer, \ - kthread_delayed_work_timer_fn, \ - (unsigned long)(dwork), \ + (TIMER_FUNC_TYPE)kthread_delayed_work_timer_fn,\ + (TIMER_DATA_TYPE)&(dwork)->timer, \ TIMER_IRQSAFE); \ } while (0) diff --git a/kernel/kthread.c b/kernel/kthread.c index 1c19edf82427..ba3992c8c375 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -798,15 +798,14 @@ EXPORT_SYMBOL_GPL(kthread_queue_work); /** * kthread_delayed_work_timer_fn - callback that queues the associated kthread * delayed work when the timer expires. - * @__data: pointer to the data associated with the timer + * @t: pointer to the expired timer * * The format of the function is defined by struct timer_list. * It should have been called from irqsafe timer with irq already off. */ -void kthread_delayed_work_timer_fn(unsigned long __data) +void kthread_delayed_work_timer_fn(struct timer_list *t) { - struct kthread_delayed_work *dwork = - (struct kthread_delayed_work *)__data; + struct kthread_delayed_work *dwork = from_timer(dwork, t, timer); struct kthread_work *work = &dwork->work; struct kthread_worker *worker = work->worker; @@ -837,8 +836,7 @@ void __kthread_queue_delayed_work(struct kthread_worker *worker, struct timer_list *timer = &dwork->timer; struct kthread_work *work = &dwork->work; - WARN_ON_ONCE(timer->function != kthread_delayed_work_timer_fn || - timer->data != (unsigned long)dwork); + WARN_ON_ONCE(timer->function != (TIMER_FUNC_TYPE)kthread_delayed_work_timer_fn); /* * If @delay is 0, queue @dwork->work immediately. This is for -- cgit v1.2.3 From 8c20feb60604d91a29cd7fef8ac758bd92d9fd2c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 4 Oct 2017 16:27:07 -0700 Subject: workqueue: Convert callback to use from_timer() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch workqueue to use from_timer() and pass the timer pointer explicitly. Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Cc: linux-mips@linux-mips.org Cc: Petr Mladek Cc: Benjamin Herrenschmidt Cc: Lai Jiangshan Cc: Sebastian Reichel Cc: Kalle Valo Cc: Paul Mackerras Cc: Pavel Machek Cc: linux1394-devel@lists.sourceforge.net Cc: Chris Metcalf Cc: linux-s390@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: "James E.J. Bottomley" Cc: Wim Van Sebroeck Cc: Michael Ellerman Cc: Ursula Braun Cc: Geert Uytterhoeven Cc: Viresh Kumar Cc: Harish Patil Cc: Stephen Boyd Cc: Guenter Roeck Cc: Manish Chopra Cc: Len Brown Cc: Arnd Bergmann Cc: linux-pm@vger.kernel.org Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: Julian Wiedmann Cc: John Stultz Cc: Mark Gross Cc: linux-watchdog@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Oleg Nesterov Cc: Ralf Baechle Cc: Stefan Richter Cc: Michael Reed Cc: netdev@vger.kernel.org Cc: Tejun Heo Cc: Andrew Morton Cc: linuxppc-dev@lists.ozlabs.org Cc: Sudip Mukherjee Link: https://lkml.kernel.org/r/1507159627-127660-14-git-send-email-keescook@chromium.org --- include/linux/workqueue.h | 15 ++++++++------- kernel/workqueue.c | 7 +++---- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index f4960260feaf..f3c47a05fd06 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -17,7 +17,7 @@ struct workqueue_struct; struct work_struct; typedef void (*work_func_t)(struct work_struct *work); -void delayed_work_timer_fn(unsigned long __data); +void delayed_work_timer_fn(struct timer_list *t); /* * The first word is the work queue pointer and the flags rolled into @@ -175,8 +175,8 @@ struct execute_work { #define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \ .work = __WORK_INITIALIZER((n).work, (f)), \ - .timer = __TIMER_INITIALIZER(delayed_work_timer_fn, \ - (unsigned long)&(n), \ + .timer = __TIMER_INITIALIZER((TIMER_FUNC_TYPE)delayed_work_timer_fn,\ + (TIMER_DATA_TYPE)&(n.timer), \ (tflags) | TIMER_IRQSAFE), \ } @@ -241,8 +241,9 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } #define __INIT_DELAYED_WORK(_work, _func, _tflags) \ do { \ INIT_WORK(&(_work)->work, (_func)); \ - __setup_timer(&(_work)->timer, delayed_work_timer_fn, \ - (unsigned long)(_work), \ + __setup_timer(&(_work)->timer, \ + (TIMER_FUNC_TYPE)delayed_work_timer_fn, \ + (TIMER_DATA_TYPE)&(_work)->timer, \ (_tflags) | TIMER_IRQSAFE); \ } while (0) @@ -250,8 +251,8 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } do { \ INIT_WORK_ONSTACK(&(_work)->work, (_func)); \ __setup_timer_on_stack(&(_work)->timer, \ - delayed_work_timer_fn, \ - (unsigned long)(_work), \ + (TIMER_FUNC_TYPE)delayed_work_timer_fn,\ + (TIMER_DATA_TYPE)&(_work)->timer,\ (_tflags) | TIMER_IRQSAFE); \ } while (0) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index a5361fc6215d..c77fdf6bf24f 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1492,9 +1492,9 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq, } EXPORT_SYMBOL(queue_work_on); -void delayed_work_timer_fn(unsigned long __data) +void delayed_work_timer_fn(struct timer_list *t) { - struct delayed_work *dwork = (struct delayed_work *)__data; + struct delayed_work *dwork = from_timer(dwork, t, timer); /* should have been called from irqsafe timer with irq already off */ __queue_work(dwork->cpu, dwork->wq, &dwork->work); @@ -1508,8 +1508,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, struct work_struct *work = &dwork->work; WARN_ON_ONCE(!wq); - WARN_ON_ONCE(timer->function != delayed_work_timer_fn || - timer->data != (unsigned long)dwork); + WARN_ON_ONCE(timer->function != (TIMER_FUNC_TYPE)delayed_work_timer_fn); WARN_ON_ONCE(timer_pending(timer)); WARN_ON_ONCE(!list_empty(&work->entry)); -- cgit v1.2.3 From a1c4d24e02d093efd84cbde417051d2e767fa8fa Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 30 Sep 2017 08:43:38 -0700 Subject: linux/log2.h: fix kernel-doc notation Fix kernel-doc: - Add kernel-doc notation to some functions. - Fix kernel-doc notation in function parameters. Signed-off-by: Randy Dunlap Signed-off-by: Jonathan Corbet --- include/linux/log2.h | 42 +++++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/log2.h b/include/linux/log2.h index c373295f359f..41a1ae010993 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -37,19 +37,23 @@ int __ilog2_u64(u64 n) } #endif -/* - * Determine whether some value is a power of two, where zero is +/** + * is_power_of_2() - check if a value is a power of two + * @n: the value to check + * + * Determine whether some value is a power of two, where zero is * *not* considered a power of two. + * Return: true if @n is a power of 2, otherwise false. */ - static inline __attribute__((const)) bool is_power_of_2(unsigned long n) { return (n != 0 && ((n & (n - 1)) == 0)); } -/* - * round up to nearest power of two +/** + * __roundup_pow_of_two() - round up to nearest power of two + * @n: value to round up */ static inline __attribute__((const)) unsigned long __roundup_pow_of_two(unsigned long n) @@ -57,8 +61,9 @@ unsigned long __roundup_pow_of_two(unsigned long n) return 1UL << fls_long(n - 1); } -/* - * round down to nearest power of two +/** + * __rounddown_pow_of_two() - round down to nearest power of two + * @n: value to round down */ static inline __attribute__((const)) unsigned long __rounddown_pow_of_two(unsigned long n) @@ -67,12 +72,12 @@ unsigned long __rounddown_pow_of_two(unsigned long n) } /** - * ilog2 - log of base 2 of 32-bit or a 64-bit unsigned value - * @n - parameter + * ilog2 - log base 2 of 32-bit or a 64-bit unsigned value + * @n: parameter * * constant-capable log of base 2 calculation * - this can be used to initialise global variables from constant data, hence - * the massive ternary operator construction + * the massive ternary operator construction * * selects the appropriately-sized optimised version depending on sizeof(n) */ @@ -150,7 +155,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) /** * roundup_pow_of_two - round the given value up to nearest power of two - * @n - parameter + * @n: parameter * * round the given value up to the nearest power of two * - the result is undefined when n == 0 @@ -167,7 +172,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) /** * rounddown_pow_of_two - round the given value down to nearest power of two - * @n - parameter + * @n: parameter * * round the given value down to the nearest power of two * - the result is undefined when n == 0 @@ -180,6 +185,12 @@ unsigned long __rounddown_pow_of_two(unsigned long n) __rounddown_pow_of_two(n) \ ) +static inline __attribute_const__ +int __order_base_2(unsigned long n) +{ + return n > 1 ? ilog2(n - 1) + 1 : 0; +} + /** * order_base_2 - calculate the (rounded up) base 2 order of the argument * @n: parameter @@ -193,13 +204,6 @@ unsigned long __rounddown_pow_of_two(unsigned long n) * ob2(5) = 3 * ... and so on. */ - -static inline __attribute_const__ -int __order_base_2(unsigned long n) -{ - return n > 1 ? ilog2(n - 1) + 1 : 0; -} - #define order_base_2(n) \ ( \ __builtin_constant_p(n) ? ( \ -- cgit v1.2.3 From 078843f75d234123e654b992d97e8ae8a744ba23 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 30 Sep 2017 08:43:45 -0700 Subject: math64: add missing kernel-doc notation Add missing kernel-doc notation (function parameters) for several div() functions. Signed-off-by: Randy Dunlap Signed-off-by: Jonathan Corbet --- include/linux/math64.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/math64.h b/include/linux/math64.h index 80690c96c734..8dd2488bf289 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -11,6 +11,11 @@ /** * div_u64_rem - unsigned 64bit divide with 32bit divisor with remainder + * @dividend: unsigned 64bit dividend + * @divisor: unsigned 32bit divisor + * @remainder: pointer to unsigned 32bit remainder + * + * Return: sets ``*remainder``, then returns dividend / divisor * * This is commonly provided by 32bit archs to provide an optimized 64bit * divide. @@ -23,6 +28,11 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) /** * div_s64_rem - signed 64bit divide with 32bit divisor with remainder + * @dividend: signed 64bit dividend + * @divisor: signed 32bit divisor + * @remainder: pointer to signed 32bit remainder + * + * Return: sets ``*remainder``, then returns dividend / divisor */ static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder) { @@ -32,6 +42,11 @@ static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder) /** * div64_u64_rem - unsigned 64bit divide with 64bit divisor and remainder + * @dividend: unsigned 64bit dividend + * @divisor: unsigned 64bit divisor + * @remainder: pointer to unsigned 64bit remainder + * + * Return: sets ``*remainder``, then returns dividend / divisor */ static inline u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder) { @@ -41,6 +56,10 @@ static inline u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder) /** * div64_u64 - unsigned 64bit divide with 64bit divisor + * @dividend: unsigned 64bit dividend + * @divisor: unsigned 64bit divisor + * + * Return: dividend / divisor */ static inline u64 div64_u64(u64 dividend, u64 divisor) { @@ -49,6 +68,10 @@ static inline u64 div64_u64(u64 dividend, u64 divisor) /** * div64_s64 - signed 64bit divide with 64bit divisor + * @dividend: signed 64bit dividend + * @divisor: signed 64bit divisor + * + * Return: dividend / divisor */ static inline s64 div64_s64(s64 dividend, s64 divisor) { @@ -88,6 +111,8 @@ extern s64 div64_s64(s64 dividend, s64 divisor); /** * div_u64 - unsigned 64bit divide with 32bit divisor + * @dividend: unsigned 64bit dividend + * @divisor: unsigned 32bit divisor * * This is the most common 64bit divide and should be used if possible, * as many 32bit archs can optimize this variant better than a full 64bit @@ -103,6 +128,8 @@ static inline u64 div_u64(u64 dividend, u32 divisor) /** * div_s64 - signed 64bit divide with 32bit divisor + * @dividend: signed 64bit dividend + * @divisor: signed 32bit divisor */ #ifndef div_s64 static inline s64 div_s64(s64 dividend, s32 divisor) -- cgit v1.2.3 From 6733bab7bc09b67668028dab562caea1b4ff3c69 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 18 Aug 2017 10:59:16 -0700 Subject: irq_work: Map irq_work_on_queue() to irq_work_on() in !SMP Commit 478850160636 ("irq_work: Implement remote queueing") provides irq_work_on_queue() only for SMP builds. However, providing it simplifies code that submits irq_work to lists of CPUs, eliminating the !SMP special cases. This commit therefore maps irq_work_on_queue() to irq_work_on() in !SMP builds, but validating the specified CPU. Signed-off-by: Paul E. McKenney --- include/linux/irq_work.h | 3 --- kernel/irq_work.c | 9 ++++++--- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 47b9ebd4a74f..d8c9876d5da4 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -33,10 +33,7 @@ void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *)) #define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { .func = (_f), } bool irq_work_queue(struct irq_work *work); - -#ifdef CONFIG_SMP bool irq_work_queue_on(struct irq_work *work, int cpu); -#endif void irq_work_tick(void); void irq_work_sync(struct irq_work *work); diff --git a/kernel/irq_work.c b/kernel/irq_work.c index bcf107ce0854..9f20f6c72579 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -56,7 +56,6 @@ void __weak arch_irq_work_raise(void) */ } -#ifdef CONFIG_SMP /* * Enqueue the irq_work @work on @cpu unless it's already pending * somewhere. @@ -68,6 +67,8 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(cpu)); +#ifdef CONFIG_SMP + /* Arch remote IPI send/receive backend aren't NMI safe */ WARN_ON_ONCE(in_nmi()); @@ -78,10 +79,12 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) arch_send_call_function_single_ipi(cpu); +#else /* #ifdef CONFIG_SMP */ + irq_work_queue(work); +#endif /* #else #ifdef CONFIG_SMP */ + return true; } -EXPORT_SYMBOL_GPL(irq_work_queue_on); -#endif /* Enqueue the irq work @work on the current CPU */ bool irq_work_queue(struct irq_work *work) -- cgit v1.2.3 From 1d48b080bcce0a5e7d7aa2dbcdb35deefc188c3f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 29 Sep 2017 13:50:16 +0200 Subject: sched/debug: Rename task-state printing helpers Steve requested better names for the new task-state helper functions. So introduce the concept of task-state index for the printing and rename __get_task_state() to task_state_index() and __task_state_to_char() to task_index_to_char(). Requested-by: Steven Rostedt Signed-off-by: Peter Zijlstra (Intel) Acked-by: Steven Rostedt Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20170929115016.pzlqc7ss3ccystyg@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- fs/proc/array.c | 2 +- include/linux/sched.h | 6 +++--- include/trace/events/sched.h | 2 +- kernel/trace/trace_output.c | 12 ++++++------ kernel/trace/trace_sched_wakeup.c | 8 ++++---- 5 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/array.c b/fs/proc/array.c index 77a8eacbe032..1b5406ca8e4c 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -137,7 +137,7 @@ static const char * const task_state_array[] = { static inline const char *get_task_state(struct task_struct *tsk) { BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != ARRAY_SIZE(task_state_array)); - return task_state_array[__get_task_state(tsk)]; + return task_state_array[task_state_index(tsk)]; } static inline int get_task_umask(struct task_struct *tsk) diff --git a/include/linux/sched.h b/include/linux/sched.h index bdd6ad6fcce1..33a01f4deb00 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1248,7 +1248,7 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) -static inline unsigned int __get_task_state(struct task_struct *tsk) +static inline unsigned int task_state_index(struct task_struct *tsk) { unsigned int tsk_state = READ_ONCE(tsk->state); unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; @@ -1261,7 +1261,7 @@ static inline unsigned int __get_task_state(struct task_struct *tsk) return fls(state); } -static inline char __task_state_to_char(unsigned int state) +static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; @@ -1272,7 +1272,7 @@ static inline char __task_state_to_char(unsigned int state) static inline char task_state_to_char(struct task_struct *tsk) { - return __task_state_to_char(__get_task_state(tsk)); + return task_index_to_char(task_state_index(tsk)); } /** diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 3c8b7f625670..fab74a12ca0f 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -117,7 +117,7 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct * if (preempt) return TASK_STATE_MAX; - return __get_task_state(p); + return task_state_index(p); } #endif /* CREATE_TRACE_POINTS */ diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index c738e764e2a5..90db994ac900 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -921,8 +921,8 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, trace_assign_type(field, iter->ent); - T = __task_state_to_char(field->next_state); - S = __task_state_to_char(field->prev_state); + T = task_index_to_char(field->next_state); + S = task_index_to_char(field->prev_state); trace_find_cmdline(field->next_pid, comm); trace_seq_printf(&iter->seq, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", @@ -957,8 +957,8 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = __task_state_to_char(field->prev_state); - T = __task_state_to_char(field->next_state); + S = task_index_to_char(field->prev_state); + T = task_index_to_char(field->next_state); trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n", field->prev_pid, field->prev_prio, @@ -993,8 +993,8 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = __task_state_to_char(field->prev_state); - T = __task_state_to_char(field->next_state); + S = task_index_to_char(field->prev_state); + T = task_index_to_char(field->next_state); SEQ_PUT_HEX_FIELD(s, field->prev_pid); SEQ_PUT_HEX_FIELD(s, field->prev_prio); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 0c331978b1a6..500f370d3bb1 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -397,10 +397,10 @@ tracing_sched_switch_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = prev->pid; entry->prev_prio = prev->prio; - entry->prev_state = __get_task_state(prev); + entry->prev_state = task_state_index(prev); entry->next_pid = next->pid; entry->next_prio = next->prio; - entry->next_state = __get_task_state(next); + entry->next_state = task_state_index(next); entry->next_cpu = task_cpu(next); if (!call_filter_check_discard(call, entry, buffer, event)) @@ -425,10 +425,10 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = curr->pid; entry->prev_prio = curr->prio; - entry->prev_state = __get_task_state(curr); + entry->prev_state = task_state_index(curr); entry->next_pid = wakee->pid; entry->next_prio = wakee->prio; - entry->next_state = __get_task_state(wakee); + entry->next_state = task_state_index(wakee); entry->next_cpu = task_cpu(wakee); if (!call_filter_check_discard(call, entry, buffer, event)) -- cgit v1.2.3 From 799ba82de01e7543f6b2042e1a739f3a20255f23 Mon Sep 17 00:00:00 2001 From: luca abeni Date: Thu, 7 Sep 2017 12:09:31 +0200 Subject: sched/deadline: Use C bitfields for the state flags Ask the compiler to use a single bit for storing true / false values, instead of wasting the size of a whole int value. Tested with gcc 5.4.0 on x86_64, and the compiler produces the expected Assembly (similar to the Assembly code generated when explicitly accessing the bits with bitmasks, "&" and "|"). Signed-off-by: luca abeni Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Daniel Bristot de Oliveira Cc: Juri Lelli Cc: Linus Torvalds Cc: Mathieu Poirier Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1504778971-13573-5-git-send-email-luca.abeni@santannapisa.it Signed-off-by: Ingo Molnar --- include/linux/sched.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 33a01f4deb00..0f897dfc195e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -474,10 +474,10 @@ struct sched_dl_entity { * conditions between the inactive timer handler and the wakeup * code. */ - int dl_throttled; - int dl_boosted; - int dl_yielded; - int dl_non_contending; + int dl_throttled : 1; + int dl_boosted : 1; + int dl_yielded : 1; + int dl_non_contending : 1; /* * Bandwidth enforcement timer. Each -deadline task has its -- cgit v1.2.3 From ff0d4a9dc16b1f4c954f6407c233ab848bdfe8b0 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 4 Oct 2017 17:49:00 +0200 Subject: sched/rt: Add a helper to test for a RT task This helper returns true if a task has elevated priority which is true for RT tasks (SCHED_RR and SCHED_FIFO) and also for SCHED_DEADLINE. A task which runs at RT priority due to PI-boosting is not considered as one with elevated priority. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Cc: Jens Axboe Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20171004154901.26904-1-bigeasy@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/sched/rt.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index f93329aba31a..133001627ba1 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -17,6 +17,17 @@ static inline int rt_task(struct task_struct *p) return rt_prio(p->prio); } +static inline bool task_is_realtime(struct task_struct *tsk) +{ + int policy = tsk->policy; + + if (policy == SCHED_FIFO || policy == SCHED_RR) + return true; + if (policy == SCHED_DEADLINE) + return true; + return false; +} + #ifdef CONFIG_RT_MUTEXES /* * Must hold either p->pi_lock or task_rq(p)->lock. -- cgit v1.2.3 From 36436440cd19f59f5be12a1b181d299af2725140 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 4 Oct 2017 17:49:01 +0200 Subject: block/ioprio: Use a helper to check for RT prio A side-effect to the old code is that now SCHED_DEADLINE is also recognized. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Cc: Jens Axboe Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20171004154901.26904-2-bigeasy@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/ioprio.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index 8c1239020d79..2f19aab84a4a 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -2,6 +2,7 @@ #define IOPRIO_H #include +#include #include /* @@ -62,7 +63,7 @@ static inline int task_nice_ioclass(struct task_struct *task) { if (task->policy == SCHED_IDLE) return IOPRIO_CLASS_IDLE; - else if (task->policy == SCHED_FIFO || task->policy == SCHED_RR) + else if (task_is_realtime(task)) return IOPRIO_CLASS_RT; else return IOPRIO_CLASS_BE; -- cgit v1.2.3 From 76f8507f7a6442215df19de74f07eabca2462f1e Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 29 Sep 2017 19:06:38 +0300 Subject: locking/rwsem: Add down_read_killable() Similar to down_read() and down_write_killable(), add killable version of down_read(), based on __down_read_killable() function, added in previous patches. Signed-off-by: Kirill Tkhai Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: arnd@arndb.de Cc: avagin@virtuozzo.com Cc: davem@davemloft.net Cc: fenghua.yu@intel.com Cc: gorcunov@virtuozzo.com Cc: heiko.carstens@de.ibm.com Cc: hpa@zytor.com Cc: ink@jurassic.park.msu.ru Cc: mattst88@gmail.com Cc: rientjes@google.com Cc: rth@twiddle.net Cc: schwidefsky@de.ibm.com Cc: tony.luck@intel.com Cc: viro@zeniv.linux.org.uk Link: http://lkml.kernel.org/r/150670119884.23930.2585570605960763239.stgit@localhost.localdomain Signed-off-by: Ingo Molnar --- include/asm-generic/rwsem.h | 10 ++++++++++ include/linux/rwsem.h | 1 + kernel/locking/rwsem.c | 16 ++++++++++++++++ 3 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h index 6c6a2141f271..b2d68d2d198e 100644 --- a/include/asm-generic/rwsem.h +++ b/include/asm-generic/rwsem.h @@ -37,6 +37,16 @@ static inline void __down_read(struct rw_semaphore *sem) rwsem_down_read_failed(sem); } +static inline int __down_read_killable(struct rw_semaphore *sem) +{ + if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) { + if (IS_ERR(rwsem_down_read_failed_killable(sem))) + return -EINTR; + } + + return 0; +} + static inline int __down_read_trylock(struct rw_semaphore *sem) { long tmp; diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 0ad7318ff299..6ac8ee5f15dd 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -111,6 +111,7 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem) * lock for reading */ extern void down_read(struct rw_semaphore *sem); +extern int __must_check down_read_killable(struct rw_semaphore *sem); /* * trylock for reading -- returns 1 if successful, 0 if contention diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 4d48b1c4870d..e53f7746d9fd 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -28,6 +28,22 @@ void __sched down_read(struct rw_semaphore *sem) EXPORT_SYMBOL(down_read); +int __sched down_read_killable(struct rw_semaphore *sem) +{ + might_sleep(); + rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_); + + if (LOCK_CONTENDED_RETURN(sem, __down_read_trylock, __down_read_killable)) { + rwsem_release(&sem->dep_map, 1, _RET_IP_); + return -EINTR; + } + + rwsem_set_reader_owned(sem); + return 0; +} + +EXPORT_SYMBOL(down_read_killable); + /* * trylock for reading -- returns 1 if successful, 0 if contention */ -- cgit v1.2.3 From a8a217c22116eff6c120d753c9934089fb229af0 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 3 Oct 2017 19:25:27 +0100 Subject: locking/core: Remove {read,spin,write}_can_lock() Outside of the locking code itself, {read,spin,write}_can_lock() have no users in tree. Apparmor (the last remaining user of write_can_lock()) got moved over to lockdep by the previous patch. This patch removes the use of {read,spin,write}_can_lock() from the BUILD_LOCK_OPS macro, deferring to the trylock operation for testing the lock status, and subsequently removes the unused macros altogether. They aren't guaranteed to work in a concurrent environment and can give incorrect results in the case of qrwlock. Signed-off-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: paulmck@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1507055129-12300-2-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/spinlock.h | 10 ---------- arch/arc/include/asm/spinlock.h | 3 --- arch/arm/include/asm/spinlock.h | 6 ------ arch/blackfin/include/asm/spinlock.h | 10 ---------- arch/hexagon/include/asm/spinlock.h | 10 ---------- arch/ia64/include/asm/spinlock.h | 3 --- arch/m32r/include/asm/spinlock.h | 12 ------------ arch/metag/include/asm/spinlock_lnkget.h | 30 ------------------------------ arch/metag/include/asm/spinlock_lock1.h | 20 -------------------- arch/mn10300/include/asm/spinlock.h | 12 ------------ arch/parisc/include/asm/spinlock.h | 18 ------------------ arch/powerpc/include/asm/spinlock.h | 3 --- arch/s390/include/asm/spinlock.h | 12 ------------ arch/sh/include/asm/spinlock-cas.h | 12 ------------ arch/sh/include/asm/spinlock-llsc.h | 12 ------------ arch/sparc/include/asm/spinlock_32.h | 3 --- arch/tile/include/asm/spinlock_32.h | 16 ---------------- arch/tile/include/asm/spinlock_64.h | 18 ------------------ arch/xtensa/include/asm/spinlock.h | 2 -- include/asm-generic/qrwlock.h | 20 -------------------- include/linux/rwlock.h | 3 --- include/linux/spinlock.h | 11 ----------- include/linux/spinlock_up.h | 3 --- kernel/locking/spinlock.c | 6 ++---- 24 files changed, 2 insertions(+), 253 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/include/asm/spinlock.h b/arch/alpha/include/asm/spinlock.h index 718ac0b64adf..7bff6316b8bb 100644 --- a/arch/alpha/include/asm/spinlock.h +++ b/arch/alpha/include/asm/spinlock.h @@ -54,16 +54,6 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) /***********************************************************/ -static inline int arch_read_can_lock(arch_rwlock_t *lock) -{ - return (lock->lock & 1) == 0; -} - -static inline int arch_write_can_lock(arch_rwlock_t *lock) -{ - return lock->lock == 0; -} - static inline void arch_read_lock(arch_rwlock_t *lock) { long regx; diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h index 47efc8451b70..ce9bfcf1d870 100644 --- a/arch/arc/include/asm/spinlock.h +++ b/arch/arc/include/asm/spinlock.h @@ -410,9 +410,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) #endif -#define arch_read_can_lock(x) ((x)->counter > 0) -#define arch_write_can_lock(x) ((x)->counter == __ARCH_RW_LOCK_UNLOCKED__) - #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index c030143c18c6..f5223260c73e 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -193,9 +193,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) dsb_sev(); } -/* write_can_lock - would write_trylock() succeed? */ -#define arch_write_can_lock(x) (ACCESS_ONCE((x)->lock) == 0) - /* * Read locks are a bit more hairy: * - Exclusively load the lock value. @@ -273,9 +270,6 @@ static inline int arch_read_trylock(arch_rwlock_t *rw) } } -/* read_can_lock - would read_trylock() succeed? */ -#define arch_read_can_lock(x) (ACCESS_ONCE((x)->lock) < 0x80000000) - #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) diff --git a/arch/blackfin/include/asm/spinlock.h b/arch/blackfin/include/asm/spinlock.h index f6431439d15d..607ef98c0f6c 100644 --- a/arch/blackfin/include/asm/spinlock.h +++ b/arch/blackfin/include/asm/spinlock.h @@ -48,16 +48,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) __raw_spin_unlock_asm(&lock->lock); } -static inline int arch_read_can_lock(arch_rwlock_t *rw) -{ - return __raw_uncached_fetch_asm(&rw->lock) > 0; -} - -static inline int arch_write_can_lock(arch_rwlock_t *rw) -{ - return __raw_uncached_fetch_asm(&rw->lock) == RW_LOCK_BIAS; -} - static inline void arch_read_lock(arch_rwlock_t *rw) { __raw_read_lock_asm(&rw->lock); diff --git a/arch/hexagon/include/asm/spinlock.h b/arch/hexagon/include/asm/spinlock.h index 53a8d5885887..9f9414b9c303 100644 --- a/arch/hexagon/include/asm/spinlock.h +++ b/arch/hexagon/include/asm/spinlock.h @@ -86,16 +86,6 @@ static inline int arch_read_trylock(arch_rwlock_t *lock) return temp; } -static inline int arch_read_can_lock(arch_rwlock_t *rwlock) -{ - return rwlock->lock == 0; -} - -static inline int arch_write_can_lock(arch_rwlock_t *rwlock) -{ - return rwlock->lock == 0; -} - /* Stuffs a -1 in the lock value? */ static inline void arch_write_lock(arch_rwlock_t *lock) { diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h index df2c121164b8..c728dda59bd2 100644 --- a/arch/ia64/include/asm/spinlock.h +++ b/arch/ia64/include/asm/spinlock.h @@ -127,9 +127,6 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock, arch_spin_lock(lock); } -#define arch_read_can_lock(rw) (*(volatile int *)(rw) >= 0) -#define arch_write_can_lock(rw) (*(volatile int *)(rw) == 0) - #ifdef ASM_SUPPORTED static __always_inline void diff --git a/arch/m32r/include/asm/spinlock.h b/arch/m32r/include/asm/spinlock.h index a56825592b90..002601371b2f 100644 --- a/arch/m32r/include/asm/spinlock.h +++ b/arch/m32r/include/asm/spinlock.h @@ -137,18 +137,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) * semaphore.h for details. -ben */ -/** - * read_can_lock - would read_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_read_can_lock(x) ((int)(x)->lock > 0) - -/** - * write_can_lock - would write_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_write_can_lock(x) ((x)->lock == RW_LOCK_BIAS) - static inline void arch_read_lock(arch_rwlock_t *rw) { unsigned long tmp0, tmp1; diff --git a/arch/metag/include/asm/spinlock_lnkget.h b/arch/metag/include/asm/spinlock_lnkget.h index ad8436feed8d..6a932a952d53 100644 --- a/arch/metag/include/asm/spinlock_lnkget.h +++ b/arch/metag/include/asm/spinlock_lnkget.h @@ -136,21 +136,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) : "memory"); } -/* write_can_lock - would write_trylock() succeed? */ -static inline int arch_write_can_lock(arch_rwlock_t *rw) -{ - int ret; - - asm volatile ("LNKGETD %0, [%1]\n" - "CMP %0, #0\n" - "MOV %0, #1\n" - "XORNZ %0, %0, %0\n" - : "=&d" (ret) - : "da" (&rw->lock) - : "cc"); - return ret; -} - /* * Read locks are a bit more hairy: * - Exclusively load the lock value. @@ -224,21 +209,6 @@ static inline int arch_read_trylock(arch_rwlock_t *rw) return tmp; } -/* read_can_lock - would read_trylock() succeed? */ -static inline int arch_read_can_lock(arch_rwlock_t *rw) -{ - int tmp; - - asm volatile ("LNKGETD %0, [%1]\n" - "CMP %0, %2\n" - "MOV %0, #1\n" - "XORZ %0, %0, %0\n" - : "=&d" (tmp) - : "da" (&rw->lock), "bd" (0x80000000) - : "cc"); - return tmp; -} - #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) diff --git a/arch/metag/include/asm/spinlock_lock1.h b/arch/metag/include/asm/spinlock_lock1.h index c630444cffe9..8ae12bfc8ad8 100644 --- a/arch/metag/include/asm/spinlock_lock1.h +++ b/arch/metag/include/asm/spinlock_lock1.h @@ -104,16 +104,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) rw->lock = 0; } -/* write_can_lock - would write_trylock() succeed? */ -static inline int arch_write_can_lock(arch_rwlock_t *rw) -{ - unsigned int ret; - - barrier(); - ret = rw->lock; - return (ret == 0); -} - /* * Read locks are a bit more hairy: * - Exclusively load the lock value. @@ -171,14 +161,4 @@ static inline int arch_read_trylock(arch_rwlock_t *rw) return (ret < 0x80000000); } -/* read_can_lock - would read_trylock() succeed? */ -static inline int arch_read_can_lock(arch_rwlock_t *rw) -{ - unsigned int ret; - - barrier(); - ret = rw->lock; - return (ret < 0x80000000); -} - #endif /* __ASM_SPINLOCK_LOCK1_H */ diff --git a/arch/mn10300/include/asm/spinlock.h b/arch/mn10300/include/asm/spinlock.h index fe413b41df6c..54f75dac8094 100644 --- a/arch/mn10300/include/asm/spinlock.h +++ b/arch/mn10300/include/asm/spinlock.h @@ -98,18 +98,6 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *lock, * read-locks. */ -/** - * read_can_lock - would read_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_read_can_lock(x) ((int)(x)->lock > 0) - -/** - * write_can_lock - would write_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_write_can_lock(x) ((x)->lock == RW_LOCK_BIAS) - /* * On mn10300, we implement read-write locks as a 32-bit counter * with the high bit (sign) being the "contended" bit. diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index 55bfe4affca3..136e1c9bb8a9 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -168,24 +168,6 @@ static __inline__ int arch_write_trylock(arch_rwlock_t *rw) return result; } -/* - * read_can_lock - would read_trylock() succeed? - * @lock: the rwlock in question. - */ -static __inline__ int arch_read_can_lock(arch_rwlock_t *rw) -{ - return rw->counter >= 0; -} - -/* - * write_can_lock - would write_trylock() succeed? - * @lock: the rwlock in question. - */ -static __inline__ int arch_write_can_lock(arch_rwlock_t *rw) -{ - return !rw->counter; -} - #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index edbe571bcc54..d83f4f755ad8 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -181,9 +181,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) * read-locks. */ -#define arch_read_can_lock(rw) ((rw)->lock >= 0) -#define arch_write_can_lock(rw) (!(rw)->lock) - #ifdef CONFIG_PPC64 #define __DO_SIGN_EXTEND "extsw %0,%0\n" #define WRLOCK_TOKEN LOCK_TOKEN /* it's negative */ diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 8182b521c42f..dc9c58ed9e4c 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -110,18 +110,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lp) * read-locks. */ -/** - * read_can_lock - would read_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_read_can_lock(x) ((int)(x)->lock >= 0) - -/** - * write_can_lock - would write_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_write_can_lock(x) ((x)->lock == 0) - extern int _raw_read_trylock_retry(arch_rwlock_t *lp); extern int _raw_write_trylock_retry(arch_rwlock_t *lp); diff --git a/arch/sh/include/asm/spinlock-cas.h b/arch/sh/include/asm/spinlock-cas.h index 5ed7dbbd94ff..315467834521 100644 --- a/arch/sh/include/asm/spinlock-cas.h +++ b/arch/sh/include/asm/spinlock-cas.h @@ -53,18 +53,6 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) * read-locks. */ -/** - * read_can_lock - would read_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_read_can_lock(x) ((x)->lock > 0) - -/** - * write_can_lock - would write_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_write_can_lock(x) ((x)->lock == RW_LOCK_BIAS) - static inline void arch_read_lock(arch_rwlock_t *rw) { unsigned old; diff --git a/arch/sh/include/asm/spinlock-llsc.h b/arch/sh/include/asm/spinlock-llsc.h index f77263aae760..06be4a55f3c4 100644 --- a/arch/sh/include/asm/spinlock-llsc.h +++ b/arch/sh/include/asm/spinlock-llsc.h @@ -89,18 +89,6 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) * read-locks. */ -/** - * read_can_lock - would read_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_read_can_lock(x) ((x)->lock > 0) - -/** - * write_can_lock - would write_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_write_can_lock(x) ((x)->lock == RW_LOCK_BIAS) - static inline void arch_read_lock(arch_rwlock_t *rw) { unsigned long tmp; diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h index 67345b2dc408..76986b8f7dad 100644 --- a/arch/sparc/include/asm/spinlock_32.h +++ b/arch/sparc/include/asm/spinlock_32.h @@ -190,9 +190,6 @@ static inline int __arch_read_trylock(arch_rwlock_t *rw) #define arch_read_relax(lock) cpu_relax() #define arch_write_relax(lock) cpu_relax() -#define arch_read_can_lock(rw) (!((rw)->lock & 0xff)) -#define arch_write_can_lock(rw) (!(rw)->lock) - #endif /* !(__ASSEMBLY__) */ #endif /* __SPARC_SPINLOCK_H */ diff --git a/arch/tile/include/asm/spinlock_32.h b/arch/tile/include/asm/spinlock_32.h index cba8ba9b8da6..91d05f21cba9 100644 --- a/arch/tile/include/asm/spinlock_32.h +++ b/arch/tile/include/asm/spinlock_32.h @@ -79,22 +79,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) #define _RD_COUNT_SHIFT 24 #define _RD_COUNT_WIDTH 8 -/** - * arch_read_can_lock() - would read_trylock() succeed? - */ -static inline int arch_read_can_lock(arch_rwlock_t *rwlock) -{ - return (rwlock->lock << _RD_COUNT_WIDTH) == 0; -} - -/** - * arch_write_can_lock() - would write_trylock() succeed? - */ -static inline int arch_write_can_lock(arch_rwlock_t *rwlock) -{ - return rwlock->lock == 0; -} - /** * arch_read_lock() - acquire a read lock. */ diff --git a/arch/tile/include/asm/spinlock_64.h b/arch/tile/include/asm/spinlock_64.h index 9a2c2d605752..c802f48badf4 100644 --- a/arch/tile/include/asm/spinlock_64.h +++ b/arch/tile/include/asm/spinlock_64.h @@ -93,24 +93,6 @@ static inline int arch_write_val_locked(int val) return val < 0; /* Optimize "val & __WRITE_LOCK_BIT". */ } -/** - * read_can_lock - would read_trylock() succeed? - * @lock: the rwlock in question. - */ -static inline int arch_read_can_lock(arch_rwlock_t *rw) -{ - return !arch_write_val_locked(rw->lock); -} - -/** - * write_can_lock - would write_trylock() succeed? - * @lock: the rwlock in question. - */ -static inline int arch_write_can_lock(arch_rwlock_t *rw) -{ - return rw->lock == 0; -} - extern void __read_lock_failed(arch_rwlock_t *rw); static inline void arch_read_lock(arch_rwlock_t *rw) diff --git a/arch/xtensa/include/asm/spinlock.h b/arch/xtensa/include/asm/spinlock.h index 3bb49681ee24..d005af51e2e1 100644 --- a/arch/xtensa/include/asm/spinlock.h +++ b/arch/xtensa/include/asm/spinlock.h @@ -97,8 +97,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) * 0x80000000 one writer owns the rwlock, no other writers, no readers */ -#define arch_write_can_lock(x) ((x)->lock == 0) - static inline void arch_write_lock(arch_rwlock_t *rw) { unsigned long tmp; diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h index 7d026bf27713..50925327b0a8 100644 --- a/include/asm-generic/qrwlock.h +++ b/include/asm-generic/qrwlock.h @@ -52,24 +52,6 @@ extern void queued_read_lock_slowpath(struct qrwlock *lock, u32 cnts); extern void queued_write_lock_slowpath(struct qrwlock *lock); -/** - * queued_read_can_lock- would read_trylock() succeed? - * @lock: Pointer to queue rwlock structure - */ -static inline int queued_read_can_lock(struct qrwlock *lock) -{ - return !(atomic_read(&lock->cnts) & _QW_WMASK); -} - -/** - * queued_write_can_lock- would write_trylock() succeed? - * @lock: Pointer to queue rwlock structure - */ -static inline int queued_write_can_lock(struct qrwlock *lock) -{ - return !atomic_read(&lock->cnts); -} - /** * queued_read_trylock - try to acquire read lock of a queue rwlock * @lock : Pointer to queue rwlock structure @@ -169,8 +151,6 @@ static inline void queued_write_unlock(struct qrwlock *lock) * Remapping rwlock architecture specific functions to the corresponding * queue rwlock functions. */ -#define arch_read_can_lock(l) queued_read_can_lock(l) -#define arch_write_can_lock(l) queued_write_can_lock(l) #define arch_read_lock(l) queued_read_lock(l) #define arch_write_lock(l) queued_write_lock(l) #define arch_read_trylock(l) queued_read_trylock(l) diff --git a/include/linux/rwlock.h b/include/linux/rwlock.h index bc2994ed66e1..766c5ca5cbd1 100644 --- a/include/linux/rwlock.h +++ b/include/linux/rwlock.h @@ -50,9 +50,6 @@ do { \ # define do_raw_write_unlock(rwlock) do {arch_write_unlock(&(rwlock)->raw_lock); __release(lock); } while (0) #endif -#define read_can_lock(rwlock) arch_read_can_lock(&(rwlock)->raw_lock) -#define write_can_lock(rwlock) arch_write_can_lock(&(rwlock)->raw_lock) - /* * Define the various rw_lock methods. Note we define these * regardless of whether CONFIG_SMP or CONFIG_PREEMPT are set. The various diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 69e079c5ff98..1e3e48041800 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -278,12 +278,6 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) 1 : ({ local_irq_restore(flags); 0; }); \ }) -/** - * raw_spin_can_lock - would raw_spin_trylock() succeed? - * @lock: the spinlock in question. - */ -#define raw_spin_can_lock(lock) (!raw_spin_is_locked(lock)) - /* Include rwlock functions */ #include @@ -396,11 +390,6 @@ static __always_inline int spin_is_contended(spinlock_t *lock) return raw_spin_is_contended(&lock->rlock); } -static __always_inline int spin_can_lock(spinlock_t *lock) -{ - return raw_spin_can_lock(&lock->rlock); -} - #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) /* diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index 612fb530af41..901cf8f44388 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -77,7 +77,4 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) #define arch_spin_is_contended(lock) (((void)(lock), 0)) -#define arch_read_can_lock(lock) (((void)(lock), 1)) -#define arch_write_can_lock(lock) (((void)(lock), 1)) - #endif /* __LINUX_SPINLOCK_UP_H */ diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index 4b082b5cac9e..8fd48b5552a7 100644 --- a/kernel/locking/spinlock.c +++ b/kernel/locking/spinlock.c @@ -32,8 +32,6 @@ * include/linux/spinlock_api_smp.h */ #else -#define raw_read_can_lock(l) read_can_lock(l) -#define raw_write_can_lock(l) write_can_lock(l) /* * Some architectures can relax in favour of the CPU owning the lock. @@ -68,7 +66,7 @@ void __lockfunc __raw_##op##_lock(locktype##_t *lock) \ \ if (!(lock)->break_lock) \ (lock)->break_lock = 1; \ - while (!raw_##op##_can_lock(lock) && (lock)->break_lock)\ + while ((lock)->break_lock) \ arch_##op##_relax(&lock->raw_lock); \ } \ (lock)->break_lock = 0; \ @@ -88,7 +86,7 @@ unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock) \ \ if (!(lock)->break_lock) \ (lock)->break_lock = 1; \ - while (!raw_##op##_can_lock(lock) && (lock)->break_lock)\ + while ((lock)->break_lock) \ arch_##op##_relax(&lock->raw_lock); \ } \ (lock)->break_lock = 0; \ -- cgit v1.2.3 From a4c1887d4c1462b0ec5a8989f8ba3cdd9057a299 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 3 Oct 2017 19:25:29 +0100 Subject: locking/arch: Remove dummy arch_{read,spin,write}_lock_flags() implementations The arch_{read,spin,write}_lock_flags() macros are simply mapped to the non-flags versions by the majority of architectures, so do this in core code and remove the dummy implementations. Also remove the implementation in spinlock_up.h, since all callers of do_raw_spin_lock_flags() call local_irq_save(flags) anyway. Signed-off-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: paulmck@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1507055129-12300-4-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/spinlock.h | 4 ---- arch/arc/include/asm/spinlock.h | 4 ---- arch/arm/include/asm/spinlock.h | 5 ----- arch/arm64/include/asm/spinlock.h | 5 ----- arch/blackfin/include/asm/spinlock.h | 6 ------ arch/hexagon/include/asm/spinlock.h | 5 ----- arch/ia64/include/asm/spinlock.h | 5 +++-- arch/m32r/include/asm/spinlock.h | 4 ---- arch/metag/include/asm/spinlock.h | 5 ----- arch/metag/include/asm/spinlock_lnkget.h | 3 --- arch/mips/include/asm/spinlock.h | 3 --- arch/mn10300/include/asm/spinlock.h | 4 +--- arch/parisc/include/asm/spinlock.h | 4 +--- arch/powerpc/include/asm/spinlock.h | 4 +--- arch/s390/include/asm/spinlock.h | 4 +--- arch/sh/include/asm/spinlock-cas.h | 4 ---- arch/sh/include/asm/spinlock-llsc.h | 4 ---- arch/sparc/include/asm/spinlock_32.h | 4 ---- arch/sparc/include/asm/spinlock_64.h | 3 --- arch/tile/include/asm/spinlock_32.h | 6 ------ arch/tile/include/asm/spinlock_64.h | 6 ------ arch/x86/include/asm/spinlock.h | 3 --- arch/xtensa/include/asm/spinlock.h | 5 ----- include/asm-generic/qspinlock.h | 1 - include/linux/rwlock.h | 9 +++++++++ include/linux/spinlock.h | 4 ++++ include/linux/spinlock_up.h | 8 -------- 27 files changed, 20 insertions(+), 102 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/include/asm/spinlock.h b/arch/alpha/include/asm/spinlock.h index 7bff6316b8bb..3e2b4a05cb0f 100644 --- a/arch/alpha/include/asm/spinlock.h +++ b/arch/alpha/include/asm/spinlock.h @@ -13,7 +13,6 @@ * We make no fairness assumptions. They have a cost. */ -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) #define arch_spin_is_locked(x) ((x)->lock != 0) static inline int arch_spin_value_unlocked(arch_spinlock_t lock) @@ -160,7 +159,4 @@ static inline void arch_write_unlock(arch_rwlock_t * lock) lock->lock = 0; } -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #endif /* _ALPHA_SPINLOCK_H */ diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h index f85bb585cdfc..2ba04a7db621 100644 --- a/arch/arc/include/asm/spinlock.h +++ b/arch/arc/include/asm/spinlock.h @@ -14,7 +14,6 @@ #include #define arch_spin_is_locked(x) ((x)->slock != __ARCH_SPIN_LOCK_UNLOCKED__) -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) #ifdef CONFIG_ARC_HAS_LLSC @@ -410,7 +409,4 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) #endif -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #endif /* __ASM_SPINLOCK_H */ diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index d40a28fcbc62..daa87212c9a1 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -52,8 +52,6 @@ static inline void dsb_sev(void) * memory. */ -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) - static inline void arch_spin_lock(arch_spinlock_t *lock) { unsigned long tmp; @@ -270,7 +268,4 @@ static inline int arch_read_trylock(arch_rwlock_t *rw) } } -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #endif /* __ASM_SPINLOCK_H */ diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index 1504f2b95c57..aa51a38e46e4 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -27,8 +27,6 @@ * instructions. */ -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) - static inline void arch_spin_lock(arch_spinlock_t *lock) { unsigned int tmp; @@ -303,9 +301,6 @@ static inline int arch_read_trylock(arch_rwlock_t *rw) /* read_can_lock - would read_trylock() succeed? */ #define arch_read_can_lock(x) ((x)->lock < 0x80000000) -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - /* See include/linux/spinlock.h */ #define smp_mb__after_spinlock() smp_mb() diff --git a/arch/blackfin/include/asm/spinlock.h b/arch/blackfin/include/asm/spinlock.h index 3885d12d9939..839d1441af3a 100644 --- a/arch/blackfin/include/asm/spinlock.h +++ b/arch/blackfin/include/asm/spinlock.h @@ -36,8 +36,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) __raw_spin_lock_asm(&lock->lock); } -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) - static inline int arch_spin_trylock(arch_spinlock_t *lock) { return __raw_spin_trylock_asm(&lock->lock); @@ -53,8 +51,6 @@ static inline void arch_read_lock(arch_rwlock_t *rw) __raw_read_lock_asm(&rw->lock); } -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) - static inline int arch_read_trylock(arch_rwlock_t *rw) { return __raw_read_trylock_asm(&rw->lock); @@ -70,8 +66,6 @@ static inline void arch_write_lock(arch_rwlock_t *rw) __raw_write_lock_asm(&rw->lock); } -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - static inline int arch_write_trylock(arch_rwlock_t *rw) { return __raw_write_trylock_asm(&rw->lock); diff --git a/arch/hexagon/include/asm/spinlock.h b/arch/hexagon/include/asm/spinlock.h index 9f9414b9c303..48020863f53a 100644 --- a/arch/hexagon/include/asm/spinlock.h +++ b/arch/hexagon/include/asm/spinlock.h @@ -167,11 +167,6 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock) /* * SMP spinlocks are intended to allow only a single CPU at the lock */ -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) - #define arch_spin_is_locked(x) ((x)->lock != 0) -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #endif diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h index ed1e6212e9de..35b31884863b 100644 --- a/arch/ia64/include/asm/spinlock.h +++ b/arch/ia64/include/asm/spinlock.h @@ -126,6 +126,7 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock, { arch_spin_lock(lock); } +#define arch_spin_lock_flags arch_spin_lock_flags #ifdef ASM_SUPPORTED @@ -153,6 +154,7 @@ arch_read_lock_flags(arch_rwlock_t *lock, unsigned long flags) : "p6", "p7", "r2", "memory"); } +#define arch_read_lock_flags arch_read_lock_flags #define arch_read_lock(lock) arch_read_lock_flags(lock, 0) #else /* !ASM_SUPPORTED */ @@ -205,6 +207,7 @@ arch_write_lock_flags(arch_rwlock_t *lock, unsigned long flags) : "ar.ccv", "p6", "p7", "r2", "r29", "memory"); } +#define arch_write_lock_flags arch_write_lock_flags #define arch_write_lock(rw) arch_write_lock_flags(rw, 0) #define arch_write_trylock(rw) \ @@ -228,8 +231,6 @@ static inline void arch_write_unlock(arch_rwlock_t *x) #else /* !ASM_SUPPORTED */ -#define arch_write_lock_flags(l, flags) arch_write_lock(l) - #define arch_write_lock(l) \ ({ \ __u64 ia64_val, ia64_set_val = ia64_dep_mi(-1, 0, 31, 1); \ diff --git a/arch/m32r/include/asm/spinlock.h b/arch/m32r/include/asm/spinlock.h index 6809a9bbd169..882203db8723 100644 --- a/arch/m32r/include/asm/spinlock.h +++ b/arch/m32r/include/asm/spinlock.h @@ -28,7 +28,6 @@ */ #define arch_spin_is_locked(x) (*(volatile int *)(&(x)->slock) <= 0) -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) /** * arch_spin_trylock - Try spin lock and return a result @@ -305,7 +304,4 @@ static inline int arch_write_trylock(arch_rwlock_t *lock) return 0; } -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #endif /* _ASM_M32R_SPINLOCK_H */ diff --git a/arch/metag/include/asm/spinlock.h b/arch/metag/include/asm/spinlock.h index b5b4174cde5e..80e3e59172f2 100644 --- a/arch/metag/include/asm/spinlock.h +++ b/arch/metag/include/asm/spinlock.h @@ -15,9 +15,4 @@ * locked. */ -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) - -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #endif /* __ASM_SPINLOCK_H */ diff --git a/arch/metag/include/asm/spinlock_lnkget.h b/arch/metag/include/asm/spinlock_lnkget.h index d5c334ddfd62..5708ac0a9d09 100644 --- a/arch/metag/include/asm/spinlock_lnkget.h +++ b/arch/metag/include/asm/spinlock_lnkget.h @@ -209,7 +209,4 @@ static inline int arch_read_trylock(arch_rwlock_t *rw) return tmp; } -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #endif /* __ASM_SPINLOCK_LNKGET_H */ diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h index 4260d3f80d3a..ee81297d9117 100644 --- a/arch/mips/include/asm/spinlock.h +++ b/arch/mips/include/asm/spinlock.h @@ -13,7 +13,4 @@ #include #include -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #endif /* _ASM_SPINLOCK_H */ diff --git a/arch/mn10300/include/asm/spinlock.h b/arch/mn10300/include/asm/spinlock.h index 54f75dac8094..879cd0df53ba 100644 --- a/arch/mn10300/include/asm/spinlock.h +++ b/arch/mn10300/include/asm/spinlock.h @@ -84,6 +84,7 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *lock, : "d" (flags), "a"(&lock->slock), "i"(EPSW_IE | MN10300_CLI_LEVEL) : "memory", "cc"); } +#define arch_spin_lock_flags arch_spin_lock_flags #ifdef __KERNEL__ @@ -171,9 +172,6 @@ static inline int arch_write_trylock(arch_rwlock_t *lock) return 0; } -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index 136e1c9bb8a9..d66d7b1efc4e 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -31,6 +31,7 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *x, cpu_relax(); mb(); } +#define arch_spin_lock_flags arch_spin_lock_flags static inline void arch_spin_unlock(arch_spinlock_t *x) { @@ -168,7 +169,4 @@ static __inline__ int arch_write_trylock(arch_rwlock_t *rw) return result; } -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #endif /* __ASM_SPINLOCK_H */ diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index d83f4f755ad8..b9ebc3085fb7 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -161,6 +161,7 @@ void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) local_irq_restore(flags_dis); } } +#define arch_spin_lock_flags arch_spin_lock_flags static inline void arch_spin_unlock(arch_spinlock_t *lock) { @@ -299,9 +300,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) rw->lock = 0; } -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #define arch_spin_relax(lock) __spin_yield(lock) #define arch_read_relax(lock) __rw_yield(lock) #define arch_write_relax(lock) __rw_yield(lock) diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 4eca60cc81e4..9fa855f91e55 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -81,6 +81,7 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *lp, if (!arch_spin_trylock_once(lp)) arch_spin_lock_wait_flags(lp, flags); } +#define arch_spin_lock_flags arch_spin_lock_flags static inline int arch_spin_trylock(arch_spinlock_t *lp) { @@ -114,9 +115,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lp) extern int _raw_read_trylock_retry(arch_rwlock_t *lp); extern int _raw_write_trylock_retry(arch_rwlock_t *lp); -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - static inline int arch_read_trylock_once(arch_rwlock_t *rw) { int old = ACCESS_ONCE(rw->lock); diff --git a/arch/sh/include/asm/spinlock-cas.h b/arch/sh/include/asm/spinlock-cas.h index 295993c2598e..270ee4d3e25b 100644 --- a/arch/sh/include/asm/spinlock-cas.h +++ b/arch/sh/include/asm/spinlock-cas.h @@ -27,7 +27,6 @@ static inline unsigned __sl_cas(volatile unsigned *p, unsigned old, unsigned new */ #define arch_spin_is_locked(x) ((x)->lock <= 0) -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) static inline void arch_spin_lock(arch_spinlock_t *lock) { @@ -90,7 +89,4 @@ static inline int arch_write_trylock(arch_rwlock_t *rw) return __sl_cas(&rw->lock, RW_LOCK_BIAS, 0) == RW_LOCK_BIAS; } -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #endif /* __ASM_SH_SPINLOCK_CAS_H */ diff --git a/arch/sh/include/asm/spinlock-llsc.h b/arch/sh/include/asm/spinlock-llsc.h index a6f9edd15317..715595de286a 100644 --- a/arch/sh/include/asm/spinlock-llsc.h +++ b/arch/sh/include/asm/spinlock-llsc.h @@ -19,7 +19,6 @@ */ #define arch_spin_is_locked(x) ((x)->lock <= 0) -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) /* * Simple spin lock operations. There are two variants, one clears IRQ's @@ -197,7 +196,4 @@ static inline int arch_write_trylock(arch_rwlock_t *rw) return (oldval > (RW_LOCK_BIAS - 1)); } -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #endif /* __ASM_SH_SPINLOCK_LLSC_H */ diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h index 9d9129efd5d6..12bf857b471e 100644 --- a/arch/sparc/include/asm/spinlock_32.h +++ b/arch/sparc/include/asm/spinlock_32.h @@ -182,10 +182,6 @@ static inline int __arch_read_trylock(arch_rwlock_t *rw) res; \ }) -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) -#define arch_read_lock_flags(rw, flags) arch_read_lock(rw) -#define arch_write_lock_flags(rw, flags) arch_write_lock(rw) - #endif /* !(__ASSEMBLY__) */ #endif /* __SPARC_SPINLOCK_H */ diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h index 3b67705e1b74..99b6e1c4f630 100644 --- a/arch/sparc/include/asm/spinlock_64.h +++ b/arch/sparc/include/asm/spinlock_64.h @@ -13,9 +13,6 @@ #include #include -#define arch_read_lock_flags(p, f) arch_read_lock(p) -#define arch_write_lock_flags(p, f) arch_write_lock(p) - #endif /* !(__ASSEMBLY__) */ #endif /* !(__SPARC64_SPINLOCK_H) */ diff --git a/arch/tile/include/asm/spinlock_32.h b/arch/tile/include/asm/spinlock_32.h index 91d05f21cba9..fb5313d77315 100644 --- a/arch/tile/include/asm/spinlock_32.h +++ b/arch/tile/include/asm/spinlock_32.h @@ -51,9 +51,6 @@ static inline int arch_spin_is_locked(arch_spinlock_t *lock) void arch_spin_lock(arch_spinlock_t *lock); -/* We cannot take an interrupt after getting a ticket, so don't enable them. */ -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) - int arch_spin_trylock(arch_spinlock_t *lock); static inline void arch_spin_unlock(arch_spinlock_t *lock) @@ -109,7 +106,4 @@ void arch_read_unlock(arch_rwlock_t *rwlock); */ void arch_write_unlock(arch_rwlock_t *rwlock); -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #endif /* _ASM_TILE_SPINLOCK_32_H */ diff --git a/arch/tile/include/asm/spinlock_64.h b/arch/tile/include/asm/spinlock_64.h index c802f48badf4..5b616ef642a8 100644 --- a/arch/tile/include/asm/spinlock_64.h +++ b/arch/tile/include/asm/spinlock_64.h @@ -75,9 +75,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) /* Try to get the lock, and return whether we succeeded. */ int arch_spin_trylock(arch_spinlock_t *lock); -/* We cannot take an interrupt after getting a ticket, so don't enable them. */ -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) - /* * Read-write spinlocks, allowing multiple readers * but only one writer. @@ -138,7 +135,4 @@ static inline int arch_write_trylock(arch_rwlock_t *rw) return 0; } -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #endif /* _ASM_TILE_SPINLOCK_64_H */ diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index a558c187f20c..c6a6adf0a5c5 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -41,7 +41,4 @@ #include -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #endif /* _ASM_X86_SPINLOCK_H */ diff --git a/arch/xtensa/include/asm/spinlock.h b/arch/xtensa/include/asm/spinlock.h index d005af51e2e1..c6e1290dcbb7 100644 --- a/arch/xtensa/include/asm/spinlock.h +++ b/arch/xtensa/include/asm/spinlock.h @@ -33,8 +33,6 @@ #define arch_spin_is_locked(x) ((x)->slock != 0) -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) - static inline void arch_spin_lock(arch_spinlock_t *lock) { unsigned long tmp; @@ -198,7 +196,4 @@ static inline void arch_read_unlock(arch_rwlock_t *rw) : "memory"); } -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #endif /* _XTENSA_SPINLOCK_H */ diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h index 66260777d644..b37b4ad7eb94 100644 --- a/include/asm-generic/qspinlock.h +++ b/include/asm-generic/qspinlock.h @@ -121,6 +121,5 @@ static __always_inline bool virt_spin_lock(struct qspinlock *lock) #define arch_spin_lock(l) queued_spin_lock(l) #define arch_spin_trylock(l) queued_spin_trylock(l) #define arch_spin_unlock(l) queued_spin_unlock(l) -#define arch_spin_lock_flags(l, f) queued_spin_lock(l) #endif /* __ASM_GENERIC_QSPINLOCK_H */ diff --git a/include/linux/rwlock.h b/include/linux/rwlock.h index 766c5ca5cbd1..3dcd617e65ae 100644 --- a/include/linux/rwlock.h +++ b/include/linux/rwlock.h @@ -38,6 +38,15 @@ do { \ extern int do_raw_write_trylock(rwlock_t *lock); extern void do_raw_write_unlock(rwlock_t *lock) __releases(lock); #else + +#ifndef arch_read_lock_flags +# define arch_read_lock_flags(lock, flags) arch_read_lock(lock) +#endif + +#ifndef arch_write_lock_flags +# define arch_write_lock_flags(lock, flags) arch_write_lock(lock) +#endif + # define do_raw_read_lock(rwlock) do {__acquire(lock); arch_read_lock(&(rwlock)->raw_lock); } while (0) # define do_raw_read_lock_flags(lock, flags) \ do {__acquire(lock); arch_read_lock_flags(&(lock)->raw_lock, *(flags)); } while (0) diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 1e3e48041800..4e202b00dd66 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -165,6 +165,10 @@ static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock) arch_spin_lock(&lock->raw_lock); } +#ifndef arch_spin_lock_flags +#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) +#endif + static inline void do_raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long *flags) __acquires(lock) { diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index 901cf8f44388..0ac9112c1bbe 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -32,14 +32,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) barrier(); } -static inline void -arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) -{ - local_irq_save(flags); - lock->slock = 0; - barrier(); -} - static inline int arch_spin_trylock(arch_spinlock_t *lock) { char oldval = lock->slock; -- cgit v1.2.3 From 1b0c22e45508ffbd645430e049c52c46bdaad3b4 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 13 Oct 2017 14:12:45 +0200 Subject: regmap: avoid -Wint-in-bool-context warning When we pass the result of a multiplication as the timeout or the delay, we can get a warning from gcc-7: drivers/mmc/host/bcm2835.c:596:149: error: '*' in boolean context, suggest '&&' instead [-Werror=int-in-bool-context] drivers/mfd/arizona-core.c:247:195: error: '*' in boolean context, suggest '&&' instead [-Werror=int-in-bool-context] drivers/gpu/drm/sun4i/sun4i_hdmi_i2c.c:49:27: error: '*' in boolean context, suggest '&&' instead [-Werror=int-in-bool-context] The warning is a bit questionable inside of a macro, but this is intentional on the side of the gcc developers. It is also an indication of another problem: we evaluate the timeout and sleep arguments multiple times, which can have undesired side-effects when those are complex expressions. This changes the two regmap variants to use local variables for storing copies of the timeouts. This adds some more type safety, and avoids both the double-evaluation and the gcc warning. Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81484 Link: http://lkml.kernel.org/r/20170726133756.2161367-1-arnd@arndb.de Signed-off-by: Arnd Bergmann Signed-off-by: Mark Brown --- include/linux/regmap.h | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 1e369f0e921d..edad98890b9b 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -120,22 +120,24 @@ struct reg_sequence { */ #define regmap_read_poll_timeout(map, addr, val, cond, sleep_us, timeout_us) \ ({ \ - ktime_t __timeout = ktime_add_us(ktime_get(), timeout_us); \ + u64 __timeout_us = (timeout_us); \ + unsigned long __sleep_us = (sleep_us); \ + ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \ int __ret; \ - might_sleep_if(sleep_us); \ + might_sleep_if(__sleep_us); \ for (;;) { \ __ret = regmap_read((map), (addr), &(val)); \ if (__ret) \ break; \ if (cond) \ break; \ - if ((timeout_us) && \ + if ((__timeout_us) && \ ktime_compare(ktime_get(), __timeout) > 0) { \ __ret = regmap_read((map), (addr), &(val)); \ break; \ } \ - if (sleep_us) \ - usleep_range(((sleep_us) >> 2) + 1, sleep_us); \ + if (__sleep_us) \ + usleep_range((__sleep_us >> 2) + 1, __sleep_us); \ } \ __ret ?: ((cond) ? 0 : -ETIMEDOUT); \ }) @@ -160,21 +162,23 @@ struct reg_sequence { */ #define regmap_field_read_poll_timeout(field, val, cond, sleep_us, timeout_us) \ ({ \ - ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \ + u64 __timeout_us = (timeout_us); \ + unsigned long __sleep_us = (sleep_us); \ + ktime_t timeout = ktime_add_us(ktime_get(), __timeout_us); \ int pollret; \ - might_sleep_if(sleep_us); \ + might_sleep_if(__sleep_us); \ for (;;) { \ pollret = regmap_field_read((field), &(val)); \ if (pollret) \ break; \ if (cond) \ break; \ - if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \ + if (__timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \ pollret = regmap_field_read((field), &(val)); \ break; \ } \ - if (sleep_us) \ - usleep_range((sleep_us >> 2) + 1, sleep_us); \ + if (__sleep_us) \ + usleep_range((__sleep_us >> 2) + 1, __sleep_us); \ } \ pollret ?: ((cond) ? 0 : -ETIMEDOUT); \ }) -- cgit v1.2.3 From 62518c02f75ff9b19c07b53b8e13ed878211b795 Mon Sep 17 00:00:00 2001 From: Ladislav Michl Date: Mon, 16 Oct 2017 18:04:22 +0200 Subject: irqchip/irq-omap-intc: Remove omap3_init_irq() All mach-omap2 variants are device tree only now, so this function is dead code. Remove it. Signed-off-by: Ladislav Michl Signed-off-by: Thomas Gleixner Acked-by: Tony Lindgren Cc: Marc Zyngier Cc: linux-omap@vger.kernel.org Cc: Jason Cooper Link: https://lkml.kernel.org/r/20171016160422.uu2i7vvrgy7cc4aw@lenoch --- drivers/irqchip/irq-omap-intc.c | 12 ------------ include/linux/irqchip/irq-omap-intc.h | 2 -- 2 files changed, 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-omap-intc.c b/drivers/irqchip/irq-omap-intc.c index b04a8ac6e744..05f7f06dd711 100644 --- a/drivers/irqchip/irq-omap-intc.c +++ b/drivers/irqchip/irq-omap-intc.c @@ -25,10 +25,6 @@ #include -/* Define these here for now until we drop all board-files */ -#define OMAP24XX_IC_BASE 0x480fe000 -#define OMAP34XX_IC_BASE 0x48200000 - /* selected INTC register offsets */ #define INTC_REVISION 0x0000 @@ -364,14 +360,6 @@ omap_intc_handle_irq(struct pt_regs *regs) handle_domain_irq(domain, irqnr, regs); } -void __init omap3_init_irq(void) -{ - omap_nr_irqs = 96; - omap_nr_pending = 3; - omap_init_irq(OMAP34XX_IC_BASE, NULL); - set_handle_irq(omap_intc_handle_irq); -} - static int __init intc_of_init(struct device_node *node, struct device_node *parent) { diff --git a/include/linux/irqchip/irq-omap-intc.h b/include/linux/irqchip/irq-omap-intc.h index 2e3d1afeb674..f19ccee7749f 100644 --- a/include/linux/irqchip/irq-omap-intc.h +++ b/include/linux/irqchip/irq-omap-intc.h @@ -18,8 +18,6 @@ #ifndef __INCLUDE_LINUX_IRQCHIP_IRQ_OMAP_INTC_H #define __INCLUDE_LINUX_IRQCHIP_IRQ_OMAP_INTC_H -void omap3_init_irq(void); - int omap_irq_pending(void); void omap_intc_save_context(void); void omap_intc_restore_context(void); -- cgit v1.2.3 From cbe96375025e14fc76f9ed42ee5225120d7210f8 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 13 Oct 2017 14:56:41 -0700 Subject: bitops: Add clear/set_bit32() to linux/bitops.h Add two simple wrappers around set_bit/clear_bit() that accept the common case of an u32 array. This avoids writing casts in all callers. Signed-off-by: Andi Kleen Reviewed-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20171013215645.23166-2-andi@firstfloor.org Signed-off-by: Ingo Molnar --- include/linux/bitops.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 8fbe259b197c..36794f058ba6 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -227,6 +227,32 @@ static inline unsigned long __ffs64(u64 word) return __ffs((unsigned long)word); } +/* + * clear_bit32 - Clear a bit in memory for u32 array + * @nr: Bit to clear + * @addr: u32 * address of bitmap + * + * Same as clear_bit, but avoids needing casts for u32 arrays. + */ + +static __always_inline void clear_bit32(long nr, volatile u32 *addr) +{ + clear_bit(nr, (volatile unsigned long *)addr); +} + +/* + * set_bit32 - Set a bit in memory for u32 array + * @nr: Bit to clear + * @addr: u32 * address of bitmap + * + * Same as set_bit, but avoids needing casts for u32 arrays. + */ + +static __always_inline void set_bit32(long nr, volatile u32 *addr) +{ + set_bit(nr, (volatile unsigned long *)addr); +} + #ifdef __KERNEL__ #ifndef set_mask_bits -- cgit v1.2.3 From 5cdda5117e125e0dbb020425cc55a4c143c6febc Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 18 Oct 2017 17:24:28 +0200 Subject: locking/static_keys: Improve uninitialized key warning Right now it says: static_key_disable_cpuslocked used before call to jump_label_init ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at kernel/jump_label.c:161 static_key_disable_cpuslocked+0x68/0x70 Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 4.14.0-rc5+ #1 Hardware name: SGI.COM C2112-4GP3/X10DRT-P-Series, BIOS 2.0a 05/09/2016 task: ffffffff81c0e480 task.stack: ffffffff81c00000 RIP: 0010:static_key_disable_cpuslocked+0x68/0x70 RSP: 0000:ffffffff81c03ef0 EFLAGS: 00010096 ORIG_RAX: 0000000000000000 RAX: 0000000000000041 RBX: ffffffff81c32680 RCX: ffffffff81c5cbf8 RDX: 0000000000000001 RSI: 0000000000000092 RDI: 0000000000000002 RBP: ffff88807fffd240 R08: 726f666562206465 R09: 0000000000000136 R10: 0000000000000000 R11: 696e695f6c656261 R12: ffffffff82158900 R13: ffffffff8215f760 R14: 0000000000000001 R15: 0000000000000008 FS: 0000000000000000(0000) GS:ffff883f7f400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88807ffff000 CR3: 0000000001c09000 CR4: 00000000000606b0 Call Trace: static_key_disable+0x16/0x20 start_kernel+0x15a/0x45d ? load_ucode_intel_bsp+0x11/0x2d secondary_startup_64+0xa5/0xb0 Code: 48 c7 c7 a0 15 cf 81 e9 47 53 4b 00 48 89 df e8 5f fc ff ff eb e8 48 c7 c6 \ c0 97 83 81 48 c7 c7 d0 ff a2 81 31 c0 e8 c5 9d f5 ff <0f> ff eb a7 0f ff eb \ b0 e8 eb a2 4b 00 53 48 89 fb e8 42 0e f0 but it doesn't tell me which key it is. So dump the key's name too: static_key_disable_cpuslocked(): static key 'virt_spin_lock_key' used before call to jump_label_init() And that makes pinpointing which key is causing that a lot easier. include/linux/jump_label.h | 14 +++++++------- include/linux/jump_label_ratelimit.h | 6 +++--- kernel/jump_label.c | 14 +++++++------- 3 files changed, 17 insertions(+), 17 deletions(-) Signed-off-by: Borislav Petkov Reviewed-by: Steven Rostedt (VMware) Cc: Boris Ostrovsky Cc: Hannes Frederic Sowa Cc: Jason Baron Cc: Juergen Gross Cc: Linus Torvalds Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20171018152428.ffjgak4o25f7ept6@pd.tnic Signed-off-by: Ingo Molnar --- include/linux/jump_label.h | 14 +++++++------- include/linux/jump_label_ratelimit.h | 6 +++--- kernel/jump_label.c | 14 +++++++------- 3 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index cd5861651b17..979a2f2d529b 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -81,9 +81,9 @@ extern bool static_key_initialized; -#define STATIC_KEY_CHECK_USE() WARN(!static_key_initialized, \ - "%s used before call to jump_label_init", \ - __func__) +#define STATIC_KEY_CHECK_USE(key) WARN(!static_key_initialized, \ + "%s(): static key '%pS' used before call to jump_label_init()", \ + __func__, (key)) #ifdef HAVE_JUMP_LABEL @@ -211,13 +211,13 @@ static __always_inline bool static_key_true(struct static_key *key) static inline void static_key_slow_inc(struct static_key *key) { - STATIC_KEY_CHECK_USE(); + STATIC_KEY_CHECK_USE(key); atomic_inc(&key->enabled); } static inline void static_key_slow_dec(struct static_key *key) { - STATIC_KEY_CHECK_USE(); + STATIC_KEY_CHECK_USE(key); atomic_dec(&key->enabled); } @@ -236,7 +236,7 @@ static inline int jump_label_apply_nops(struct module *mod) static inline void static_key_enable(struct static_key *key) { - STATIC_KEY_CHECK_USE(); + STATIC_KEY_CHECK_USE(key); if (atomic_read(&key->enabled) != 0) { WARN_ON_ONCE(atomic_read(&key->enabled) != 1); @@ -247,7 +247,7 @@ static inline void static_key_enable(struct static_key *key) static inline void static_key_disable(struct static_key *key) { - STATIC_KEY_CHECK_USE(); + STATIC_KEY_CHECK_USE(key); if (atomic_read(&key->enabled) != 1) { WARN_ON_ONCE(atomic_read(&key->enabled) != 0); diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h index 23da3af459fe..93086df0a847 100644 --- a/include/linux/jump_label_ratelimit.h +++ b/include/linux/jump_label_ratelimit.h @@ -24,18 +24,18 @@ struct static_key_deferred { }; static inline void static_key_slow_dec_deferred(struct static_key_deferred *key) { - STATIC_KEY_CHECK_USE(); + STATIC_KEY_CHECK_USE(key); static_key_slow_dec(&key->key); } static inline void static_key_deferred_flush(struct static_key_deferred *key) { - STATIC_KEY_CHECK_USE(); + STATIC_KEY_CHECK_USE(key); } static inline void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) { - STATIC_KEY_CHECK_USE(); + STATIC_KEY_CHECK_USE(key); } #endif /* HAVE_JUMP_LABEL */ #endif /* _LINUX_JUMP_LABEL_RATELIMIT_H */ diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 0bf2e8f5244a..8ff4ca4665ff 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -83,7 +83,7 @@ static void static_key_slow_inc_cpuslocked(struct static_key *key) { int v, v1; - STATIC_KEY_CHECK_USE(); + STATIC_KEY_CHECK_USE(key); /* * Careful if we get concurrent static_key_slow_inc() calls; @@ -128,7 +128,7 @@ EXPORT_SYMBOL_GPL(static_key_slow_inc); void static_key_enable_cpuslocked(struct static_key *key) { - STATIC_KEY_CHECK_USE(); + STATIC_KEY_CHECK_USE(key); if (atomic_read(&key->enabled) > 0) { WARN_ON_ONCE(atomic_read(&key->enabled) != 1); @@ -158,7 +158,7 @@ EXPORT_SYMBOL_GPL(static_key_enable); void static_key_disable_cpuslocked(struct static_key *key) { - STATIC_KEY_CHECK_USE(); + STATIC_KEY_CHECK_USE(key); if (atomic_read(&key->enabled) != 1) { WARN_ON_ONCE(atomic_read(&key->enabled) != 0); @@ -224,21 +224,21 @@ static void jump_label_update_timeout(struct work_struct *work) void static_key_slow_dec(struct static_key *key) { - STATIC_KEY_CHECK_USE(); + STATIC_KEY_CHECK_USE(key); __static_key_slow_dec(key, 0, NULL); } EXPORT_SYMBOL_GPL(static_key_slow_dec); void static_key_slow_dec_deferred(struct static_key_deferred *key) { - STATIC_KEY_CHECK_USE(); + STATIC_KEY_CHECK_USE(key); __static_key_slow_dec(&key->key, key->timeout, &key->work); } EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred); void static_key_deferred_flush(struct static_key_deferred *key) { - STATIC_KEY_CHECK_USE(); + STATIC_KEY_CHECK_USE(key); flush_delayed_work(&key->work); } EXPORT_SYMBOL_GPL(static_key_deferred_flush); @@ -246,7 +246,7 @@ EXPORT_SYMBOL_GPL(static_key_deferred_flush); void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) { - STATIC_KEY_CHECK_USE(); + STATIC_KEY_CHECK_USE(key); key->timeout = rl; INIT_DELAYED_WORK(&key->work, jump_label_update_timeout); } -- cgit v1.2.3 From f1d783585486c7c612f277c2a6f0c9bb5a67e463 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 5 Oct 2017 10:44:54 +0900 Subject: irqdomain: Move revmap_trees_mutex to struct irq_domain The revmap_trees_mutex protects domain->revmap_tree. There is no need to make it global because it is allowed to modify revmap_tree of two different domains concurrently. Having said that, this would not be a actual bottleneck because the interrupt map/unmap does not occur quite often. Rather, the motivation is to tidy up the code from a data structure point of view. Signed-off-by: Masahiro Yamada Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 2 ++ kernel/irq/irqdomain.c | 14 +++++++------- 2 files changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 7d0c6c144708..df162f7a4aad 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -32,6 +32,7 @@ #include #include #include +#include #include struct device_node; @@ -176,6 +177,7 @@ struct irq_domain { unsigned int revmap_direct_max_irq; unsigned int revmap_size; struct radix_tree_root revmap_tree; + struct mutex revmap_tree_mutex; unsigned int linear_revmap[]; }; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index b50f737574ae..31d0f9ff4f00 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -21,7 +21,6 @@ static LIST_HEAD(irq_domain_list); static DEFINE_MUTEX(irq_domain_mutex); -static DEFINE_MUTEX(revmap_trees_mutex); static struct irq_domain *irq_default_domain; static void irq_domain_check_hierarchy(struct irq_domain *domain); @@ -211,6 +210,7 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, /* Fill structure */ INIT_RADIX_TREE(&domain->revmap_tree, GFP_KERNEL); + mutex_init(&domain->revmap_tree_mutex); domain->ops = ops; domain->host_data = host_data; domain->hwirq_max = hwirq_max; @@ -462,9 +462,9 @@ static void irq_domain_clear_mapping(struct irq_domain *domain, if (hwirq < domain->revmap_size) { domain->linear_revmap[hwirq] = 0; } else { - mutex_lock(&revmap_trees_mutex); + mutex_lock(&domain->revmap_tree_mutex); radix_tree_delete(&domain->revmap_tree, hwirq); - mutex_unlock(&revmap_trees_mutex); + mutex_unlock(&domain->revmap_tree_mutex); } } @@ -475,9 +475,9 @@ static void irq_domain_set_mapping(struct irq_domain *domain, if (hwirq < domain->revmap_size) { domain->linear_revmap[hwirq] = irq_data->irq; } else { - mutex_lock(&revmap_trees_mutex); + mutex_lock(&domain->revmap_tree_mutex); radix_tree_insert(&domain->revmap_tree, hwirq, irq_data); - mutex_unlock(&revmap_trees_mutex); + mutex_unlock(&domain->revmap_tree_mutex); } } @@ -1459,11 +1459,11 @@ static void irq_domain_fix_revmap(struct irq_data *d) return; /* Not using radix tree. */ /* Fix up the revmap. */ - mutex_lock(&revmap_trees_mutex); + mutex_lock(&d->domain->revmap_tree_mutex); slot = radix_tree_lookup_slot(&d->domain->revmap_tree, d->hwirq); if (slot) radix_tree_replace_slot(&d->domain->revmap_tree, slot, d); - mutex_unlock(&revmap_trees_mutex); + mutex_unlock(&d->domain->revmap_tree_mutex); } /** -- cgit v1.2.3 From eda0d04acc5e317da675ee93a3f09e7c2e2fa592 Mon Sep 17 00:00:00 2001 From: Shanker Donthineni Date: Fri, 6 Oct 2017 10:24:00 -0500 Subject: irqchip/gic-v3: Add support for Range Selector (RS) feature A new feature Range Selector (RS) has been added to GIC specification in order to support more than 16 CPUs at affinity level 0. New fields are introduced in SGI system registers (ICC_SGI0R_EL1, ICC_SGI1R_EL1 and ICC_ASGI1R_EL1) to relax an artificial limit of 16 at level 0. - A new RSS field in ICC_CTLR_EL3, ICC_CTLR_EL1 and ICV_CTLR_EL1: [18] - Range Selector Support (RSS) 0b0 = Targeted SGIs with affinity level 0 values of 0-15 are supported. 0b1 = Targeted SGIs with affinity level 0 values of 0-255 are supported. - A new RS field in ICC_SGI0R_EL1, ICC_SGI1R_EL1 and ICC_ASGI1R_EL1: [47:44] - RangeSelector (RS) which group of 16 TargetList[n] field TargetList[n] represents aff0 value ((RS*16)+n) When ICC_CTLR_EL3.RSS==0 or ICC_CTLR_EL1.RSS==0, RS is RES0. - A new RSS field in GICD_TYPER: [26] - Range Selector Support (RSS) 0b0 = Targeted SGIs with affinity level 0 values of 0-15 are supported. 0b1 = Targeted SGIs with affinity level 0 values of 0-255 are supported. Signed-off-by: Shanker Donthineni Signed-off-by: Marc Zyngier --- arch/arm/include/asm/arch_gicv3.h | 5 ++++ arch/arm64/include/asm/arch_gicv3.h | 5 ++++ drivers/irqchip/irq-gic-v3.c | 50 ++++++++++++++++++++++++++++++------- include/linux/irqchip/arm-gic-v3.h | 4 +++ 4 files changed, 55 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index eee269321923..1070044f5c3f 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -196,6 +196,11 @@ static inline void gic_write_ctlr(u32 val) isb(); } +static inline u32 gic_read_ctlr(void) +{ + return read_sysreg(ICC_CTLR); +} + static inline void gic_write_grpen1(u32 val) { write_sysreg(val, ICC_IGRPEN1); diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index b7e3f74822da..9becba9ab392 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -87,6 +87,11 @@ static inline void gic_write_ctlr(u32 val) isb(); } +static inline u32 gic_read_ctlr(void) +{ + return read_sysreg_s(SYS_ICC_CTLR_EL1); +} + static inline void gic_write_grpen1(u32 val) { write_sysreg_s(val, SYS_ICC_IGRPEN1_EL1); diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index b5df99c6f680..b54b55597ffb 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -55,6 +55,7 @@ struct gic_chip_data { struct irq_domain *domain; u64 redist_stride; u32 nr_redist_regions; + bool has_rss; unsigned int irq_nr; struct partition_desc *ppi_descs[16]; }; @@ -63,7 +64,9 @@ static struct gic_chip_data gic_data __read_mostly; static struct static_key supports_deactivate = STATIC_KEY_INIT_TRUE; static struct gic_kvm_info gic_v3_kvm_info; +static DEFINE_PER_CPU(bool, has_rss); +#define MPIDR_RS(mpidr) (((mpidr) & 0xF0UL) >> 4) #define gic_data_rdist() (this_cpu_ptr(gic_data.rdists.rdist)) #define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base) #define gic_data_rdist_sgi_base() (gic_data_rdist_rd_base() + SZ_64K) @@ -526,6 +529,10 @@ static void gic_update_vlpi_properties(void) static void gic_cpu_sys_reg_init(void) { + int i, cpu = smp_processor_id(); + u64 mpidr = cpu_logical_map(cpu); + u64 need_rss = MPIDR_RS(mpidr); + /* * Need to check that the SRE bit has actually been set. If * not, it means that SRE is disabled at EL2. We're going to @@ -557,6 +564,30 @@ static void gic_cpu_sys_reg_init(void) /* ... and let's hit the road... */ gic_write_grpen1(1); + + /* Keep the RSS capability status in per_cpu variable */ + per_cpu(has_rss, cpu) = !!(gic_read_ctlr() & ICC_CTLR_EL1_RSS); + + /* Check all the CPUs have capable of sending SGIs to other CPUs */ + for_each_online_cpu(i) { + bool have_rss = per_cpu(has_rss, i) && per_cpu(has_rss, cpu); + + need_rss |= MPIDR_RS(cpu_logical_map(i)); + if (need_rss && (!have_rss)) + pr_crit("CPU%d (%lx) can't SGI CPU%d (%lx), no RSS\n", + cpu, (unsigned long)mpidr, + i, (unsigned long)cpu_logical_map(i)); + } + + /** + * GIC spec says, when ICC_CTLR_EL1.RSS==1 and GICD_TYPER.RSS==0, + * writing ICC_ASGI1R_EL1 register with RS != 0 is a CONSTRAINED + * UNPREDICTABLE choice of : + * - The write is ignored. + * - The RS field is treated as 0. + */ + if (need_rss && (!gic_data.has_rss)) + pr_crit_once("RSS is required but GICD doesn't support it\n"); } static int gic_dist_supports_lpis(void) @@ -591,6 +622,9 @@ static void gic_cpu_init(void) #ifdef CONFIG_SMP +#define MPIDR_TO_SGI_RS(mpidr) (MPIDR_RS(mpidr) << ICC_SGI1R_RS_SHIFT) +#define MPIDR_TO_SGI_CLUSTER_ID(mpidr) ((mpidr) & ~0xFUL) + static int gic_starting_cpu(unsigned int cpu) { gic_cpu_init(); @@ -605,13 +639,6 @@ static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask, u16 tlist = 0; while (cpu < nr_cpu_ids) { - /* - * If we ever get a cluster of more than 16 CPUs, just - * scream and skip that CPU. - */ - if (WARN_ON((mpidr & 0xff) >= 16)) - goto out; - tlist |= 1 << (mpidr & 0xf); next_cpu = cpumask_next(cpu, mask); @@ -621,7 +648,7 @@ static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask, mpidr = cpu_logical_map(cpu); - if (cluster_id != (mpidr & ~0xffUL)) { + if (cluster_id != MPIDR_TO_SGI_CLUSTER_ID(mpidr)) { cpu--; goto out; } @@ -643,6 +670,7 @@ static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq) MPIDR_TO_SGI_AFFINITY(cluster_id, 2) | irq << ICC_SGI1R_SGI_ID_SHIFT | MPIDR_TO_SGI_AFFINITY(cluster_id, 1) | + MPIDR_TO_SGI_RS(cluster_id) | tlist << ICC_SGI1R_TARGET_LIST_SHIFT); pr_debug("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val); @@ -663,7 +691,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq) smp_wmb(); for_each_cpu(cpu, mask) { - unsigned long cluster_id = cpu_logical_map(cpu) & ~0xffUL; + u64 cluster_id = MPIDR_TO_SGI_CLUSTER_ID(cpu_logical_map(cpu)); u16 tlist; tlist = gic_compute_target_list(&cpu, mask, cluster_id); @@ -1007,6 +1035,10 @@ static int __init gic_init_bases(void __iomem *dist_base, goto out_free; } + gic_data.has_rss = !!(typer & GICD_TYPER_RSS); + pr_info("Distributor has %sRange Selector support\n", + gic_data.has_rss ? "" : "no "); + set_handle_irq(gic_handle_irq); gic_update_vlpi_properties(); diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 1ea576c8126f..b8b59989bd73 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -68,6 +68,7 @@ #define GICD_CTLR_ENABLE_SS_G1 (1U << 1) #define GICD_CTLR_ENABLE_SS_G0 (1U << 0) +#define GICD_TYPER_RSS (1U << 26) #define GICD_TYPER_LPIS (1U << 17) #define GICD_TYPER_MBIS (1U << 16) @@ -459,6 +460,7 @@ #define ICC_CTLR_EL1_SEIS_MASK (0x1 << ICC_CTLR_EL1_SEIS_SHIFT) #define ICC_CTLR_EL1_A3V_SHIFT 15 #define ICC_CTLR_EL1_A3V_MASK (0x1 << ICC_CTLR_EL1_A3V_SHIFT) +#define ICC_CTLR_EL1_RSS (0x1 << 18) #define ICC_PMR_EL1_SHIFT 0 #define ICC_PMR_EL1_MASK (0xff << ICC_PMR_EL1_SHIFT) #define ICC_BPR0_EL1_SHIFT 0 @@ -547,6 +549,8 @@ #define ICC_SGI1R_AFFINITY_2_SHIFT 32 #define ICC_SGI1R_AFFINITY_2_MASK (0xffULL << ICC_SGI1R_AFFINITY_2_SHIFT) #define ICC_SGI1R_IRQ_ROUTING_MODE_BIT 40 +#define ICC_SGI1R_RS_SHIFT 44 +#define ICC_SGI1R_RS_MASK (0xfULL << ICC_SGI1R_RS_SHIFT) #define ICC_SGI1R_AFFINITY_3_SHIFT 48 #define ICC_SGI1R_AFFINITY_3_MASK (0xffULL << ICC_SGI1R_AFFINITY_3_SHIFT) -- cgit v1.2.3 From ab60491ee5d346557f152c7e8d3e7238c9b96c5c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 8 Oct 2017 18:48:06 +0100 Subject: irqchip/gic-v3-its: Make GICv4_ITS_LIST_MAX globally available As we're about to make use of the maximum number of ITSs in a GICv4 system, let's make this value global (and rename it to GICv4_ITS_LIST_MAX). Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 10 ++-------- include/linux/irqchip/arm-gic-v4.h | 6 ++++++ 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 994f0879e7df..a63b4ee34860 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -156,12 +156,6 @@ static DEFINE_SPINLOCK(its_lock); static struct rdists *gic_rdists; static struct irq_domain *its_parent; -/* - * We have a maximum number of 16 ITSs in the whole system if we're - * using the ITSList mechanism - */ -#define ITS_LIST_MAX 16 - static unsigned long its_list_map; static u16 vmovp_seq_num; static DEFINE_RAW_SPINLOCK(vmovp_lock); @@ -2988,8 +2982,8 @@ static int __init its_compute_its_list_map(struct resource *res, * locking. Should this change, we should address * this. */ - its_number = find_first_zero_bit(&its_list_map, ITS_LIST_MAX); - if (its_number >= ITS_LIST_MAX) { + its_number = find_first_zero_bit(&its_list_map, GICv4_ITS_LIST_MAX); + if (its_number >= GICv4_ITS_LIST_MAX) { pr_err("ITS@%pa: No ITSList entry available!\n", &res->start); return -EINVAL; diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index 58a4d89aa82c..e26a668826e6 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -20,6 +20,12 @@ struct its_vpe; +/* + * Maximum number of ITTs when GITS_TYPER.VMOVP == 0, using the + * ITSList mechanism to perform inter-ITS synchronization. + */ +#define GICv4_ITS_LIST_MAX 16 + /* Embedded in kvm.arch */ struct its_vm { struct fwnode_handle *fwnode; -- cgit v1.2.3 From 2247e1bf70639642b1c1375aa9176ccd95736400 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 8 Oct 2017 18:50:36 +0100 Subject: irqchip/gic-v3-its: Limit scope of VPE mapping to be per ITS So far, we map all VPEs on all ITSs. While this is not wrong, this is quite a big hammer, as moving a VPE around requires all ITSs to be synchronized. Needles to say, this is an expensive proposition. Instead, let's switch to a mode where we issue VMAPP commands only on ITSs that are actually involved in reporting interrupts to the given VM. For that purpose, we refcount the number of interrupts are are mapped for this VM on each ITS, performing the map/unmap operations as required. It then allows us to use this refcount to only issue VMOVP to the ITSs that need to know about this VM. Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 75 ++++++++++++++++++++++++++++++++++++++ include/linux/irqchip/arm-gic-v4.h | 1 + 2 files changed, 76 insertions(+) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index b14585d6397b..dc0ece20f964 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -971,6 +971,9 @@ static void its_send_vmovp(struct its_vpe *vpe) if (!its->is_v4) continue; + if (!vpe->its_vm->vlpi_count[its->list_nr]) + continue; + desc.its_vmovp_cmd.col = &its->collections[col_id]; its_send_single_vcommand(its, its_build_vmovp_cmd, &desc); } @@ -1154,6 +1157,58 @@ static int its_irq_set_irqchip_state(struct irq_data *d, return 0; } +static void its_map_vm(struct its_node *its, struct its_vm *vm) +{ + unsigned long flags; + + /* Not using the ITS list? Everything is always mapped. */ + if (!its_list_map) + return; + + raw_spin_lock_irqsave(&vmovp_lock, flags); + + /* + * If the VM wasn't mapped yet, iterate over the vpes and get + * them mapped now. + */ + vm->vlpi_count[its->list_nr]++; + + if (vm->vlpi_count[its->list_nr] == 1) { + int i; + + for (i = 0; i < vm->nr_vpes; i++) { + struct its_vpe *vpe = vm->vpes[i]; + + /* Map the VPE to the first possible CPU */ + vpe->col_idx = cpumask_first(cpu_online_mask); + its_send_vmapp(its, vpe, true); + its_send_vinvall(its, vpe); + } + } + + raw_spin_unlock_irqrestore(&vmovp_lock, flags); +} + +static void its_unmap_vm(struct its_node *its, struct its_vm *vm) +{ + unsigned long flags; + + /* Not using the ITS list? Everything is always mapped. */ + if (!its_list_map) + return; + + raw_spin_lock_irqsave(&vmovp_lock, flags); + + if (!--vm->vlpi_count[its->list_nr]) { + int i; + + for (i = 0; i < vm->nr_vpes; i++) + its_send_vmapp(its, vm->vpes[i], false); + } + + raw_spin_unlock_irqrestore(&vmovp_lock, flags); +} + static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info) { struct its_device *its_dev = irq_data_get_irq_chip_data(d); @@ -1189,6 +1244,9 @@ static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info) /* Already mapped, move it around */ its_send_vmovi(its_dev, event); } else { + /* Ensure all the VPEs are mapped on this ITS */ + its_map_vm(its_dev->its, info->map->vm); + /* Drop the physical mapping */ its_send_discard(its_dev, event); @@ -1250,6 +1308,9 @@ static int its_vlpi_unmap(struct irq_data *d) LPI_PROP_ENABLED | LPI_PROP_GROUP1)); + /* Potentially unmap the VM from this ITS */ + its_unmap_vm(its_dev->its, its_dev->event_map.vm); + /* * Drop the refcount and make the device available again if * this was the last VLPI. @@ -2463,6 +2524,9 @@ static void its_vpe_invall(struct its_vpe *vpe) if (!its->is_v4) continue; + if (its_list_map && !vpe->its_vm->vlpi_count[its->list_nr]) + continue; + its_send_vinvall(its, vpe); } } @@ -2713,6 +2777,10 @@ static int its_vpe_irq_domain_activate(struct irq_domain *domain, struct its_vpe *vpe = irq_data_get_irq_chip_data(d); struct its_node *its; + /* If we use the list map, we issue VMAPP on demand... */ + if (its_list_map) + return true; + /* Map the VPE to the first possible CPU */ vpe->col_idx = cpumask_first(cpu_online_mask); @@ -2733,6 +2801,13 @@ static void its_vpe_irq_domain_deactivate(struct irq_domain *domain, struct its_vpe *vpe = irq_data_get_irq_chip_data(d); struct its_node *its; + /* + * If we use the list map, we unmap the VPE once no VLPIs are + * associated with the VM. + */ + if (its_list_map) + return; + list_for_each_entry(its, &its_nodes, entry) { if (!its->is_v4) continue; diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index e26a668826e6..43cde15f221b 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -36,6 +36,7 @@ struct its_vm { irq_hw_number_t db_lpi_base; unsigned long *db_bitmap; int nr_db_lpis; + u32 vlpi_count[GICv4_ITS_LIST_MAX]; }; /* Embedded in kvm_vcpu.arch */ -- cgit v1.2.3 From 7d7363e403ce959941f80684cc5f33e747afff17 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 16 Oct 2017 16:32:51 -0700 Subject: documentation: kernel-api: add more info on bitmap functions There are some good comments about bitmap operations in lib/bitmap.c and include/linux/bitmap.h, so format them for document generation and pull them into core-api/kernel-api.rst. I converted the "tables" of functions from using tabs to using spaces so that they are more readable in the source file and in the generated output. Signed-off-by: Randy Dunlap Signed-off-by: Jonathan Corbet --- Documentation/core-api/kernel-api.rst | 12 ++++ include/linux/bitmap.h | 105 ++++++++++++++++++---------------- lib/bitmap.c | 4 +- 3 files changed, 72 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index 9c6902ba6e67..81754add8a49 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -53,6 +53,18 @@ The Linux kernel provides more basic utility functions. Bitmap Operations ----------------- +.. kernel-doc:: lib/bitmap.c + :doc: bitmap introduction + +.. kernel-doc:: include/linux/bitmap.h + :doc: declare bitmap + +.. kernel-doc:: include/linux/bitmap.h + :doc: bitmap overview + +.. kernel-doc:: include/linux/bitmap.h + :doc: bitmap bitops + .. kernel-doc:: lib/bitmap.c :export: diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 5c4178016b1e..d9974c7a0a61 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -21,65 +21,74 @@ * See lib/bitmap.c for more details. */ -/* +/** + * DOC: bitmap overview + * * The available bitmap operations and their rough meaning in the * case that the bitmap is a single unsigned long are thus: * * Note that nbits should be always a compile time evaluable constant. * Otherwise many inlines will generate horrible code. * - * bitmap_zero(dst, nbits) *dst = 0UL - * bitmap_fill(dst, nbits) *dst = ~0UL - * bitmap_copy(dst, src, nbits) *dst = *src - * bitmap_and(dst, src1, src2, nbits) *dst = *src1 & *src2 - * bitmap_or(dst, src1, src2, nbits) *dst = *src1 | *src2 - * bitmap_xor(dst, src1, src2, nbits) *dst = *src1 ^ *src2 - * bitmap_andnot(dst, src1, src2, nbits) *dst = *src1 & ~(*src2) - * bitmap_complement(dst, src, nbits) *dst = ~(*src) - * bitmap_equal(src1, src2, nbits) Are *src1 and *src2 equal? - * bitmap_intersects(src1, src2, nbits) Do *src1 and *src2 overlap? - * bitmap_subset(src1, src2, nbits) Is *src1 a subset of *src2? - * bitmap_empty(src, nbits) Are all bits zero in *src? - * bitmap_full(src, nbits) Are all bits set in *src? - * bitmap_weight(src, nbits) Hamming Weight: number set bits - * bitmap_set(dst, pos, nbits) Set specified bit area - * bitmap_clear(dst, pos, nbits) Clear specified bit area - * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area - * bitmap_find_next_zero_area_off(buf, len, pos, n, mask) as above - * bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n - * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n - * bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src) - * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) - * bitmap_onto(dst, orig, relmap, nbits) *dst = orig relative to relmap - * bitmap_fold(dst, orig, sz, nbits) dst bits = orig bits mod sz - * bitmap_parse(buf, buflen, dst, nbits) Parse bitmap dst from kernel buf - * bitmap_parse_user(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf - * bitmap_parselist(buf, dst, nbits) Parse bitmap dst from kernel buf - * bitmap_parselist_user(buf, dst, nbits) Parse bitmap dst from user buf - * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region - * bitmap_release_region(bitmap, pos, order) Free specified bit region - * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region - * bitmap_from_u32array(dst, nbits, buf, nwords) *dst = *buf (nwords 32b words) - * bitmap_to_u32array(buf, nwords, src, nbits) *buf = *dst (nwords 32b words) + * :: + * + * bitmap_zero(dst, nbits) *dst = 0UL + * bitmap_fill(dst, nbits) *dst = ~0UL + * bitmap_copy(dst, src, nbits) *dst = *src + * bitmap_and(dst, src1, src2, nbits) *dst = *src1 & *src2 + * bitmap_or(dst, src1, src2, nbits) *dst = *src1 | *src2 + * bitmap_xor(dst, src1, src2, nbits) *dst = *src1 ^ *src2 + * bitmap_andnot(dst, src1, src2, nbits) *dst = *src1 & ~(*src2) + * bitmap_complement(dst, src, nbits) *dst = ~(*src) + * bitmap_equal(src1, src2, nbits) Are *src1 and *src2 equal? + * bitmap_intersects(src1, src2, nbits) Do *src1 and *src2 overlap? + * bitmap_subset(src1, src2, nbits) Is *src1 a subset of *src2? + * bitmap_empty(src, nbits) Are all bits zero in *src? + * bitmap_full(src, nbits) Are all bits set in *src? + * bitmap_weight(src, nbits) Hamming Weight: number set bits + * bitmap_set(dst, pos, nbits) Set specified bit area + * bitmap_clear(dst, pos, nbits) Clear specified bit area + * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area + * bitmap_find_next_zero_area_off(buf, len, pos, n, mask) as above + * bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n + * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n + * bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src) + * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) + * bitmap_onto(dst, orig, relmap, nbits) *dst = orig relative to relmap + * bitmap_fold(dst, orig, sz, nbits) dst bits = orig bits mod sz + * bitmap_parse(buf, buflen, dst, nbits) Parse bitmap dst from kernel buf + * bitmap_parse_user(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf + * bitmap_parselist(buf, dst, nbits) Parse bitmap dst from kernel buf + * bitmap_parselist_user(buf, dst, nbits) Parse bitmap dst from user buf + * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region + * bitmap_release_region(bitmap, pos, order) Free specified bit region + * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region + * bitmap_from_u32array(dst, nbits, buf, nwords) *dst = *buf (nwords 32b words) + * bitmap_to_u32array(buf, nwords, src, nbits) *buf = *dst (nwords 32b words) + * */ -/* - * Also the following operations in asm/bitops.h apply to bitmaps. +/** + * DOC: bitmap bitops + * + * Also the following operations in asm/bitops.h apply to bitmaps.:: + * + * set_bit(bit, addr) *addr |= bit + * clear_bit(bit, addr) *addr &= ~bit + * change_bit(bit, addr) *addr ^= bit + * test_bit(bit, addr) Is bit set in *addr? + * test_and_set_bit(bit, addr) Set bit and return old value + * test_and_clear_bit(bit, addr) Clear bit and return old value + * test_and_change_bit(bit, addr) Change bit and return old value + * find_first_zero_bit(addr, nbits) Position first zero bit in *addr + * find_first_bit(addr, nbits) Position first set bit in *addr + * find_next_zero_bit(addr, nbits, bit) Position next zero bit in *addr >= bit + * find_next_bit(addr, nbits, bit) Position next set bit in *addr >= bit * - * set_bit(bit, addr) *addr |= bit - * clear_bit(bit, addr) *addr &= ~bit - * change_bit(bit, addr) *addr ^= bit - * test_bit(bit, addr) Is bit set in *addr? - * test_and_set_bit(bit, addr) Set bit and return old value - * test_and_clear_bit(bit, addr) Clear bit and return old value - * test_and_change_bit(bit, addr) Change bit and return old value - * find_first_zero_bit(addr, nbits) Position first zero bit in *addr - * find_first_bit(addr, nbits) Position first set bit in *addr - * find_next_zero_bit(addr, nbits, bit) Position next zero bit in *addr >= bit - * find_next_bit(addr, nbits, bit) Position next set bit in *addr >= bit */ -/* +/** + * DOC: declare bitmap * The DECLARE_BITMAP(name,bits) macro, in linux/types.h, can be used * to declare an array named 'name' of just enough unsigned longs to * contain all bit positions from 0 to 'bits' - 1. diff --git a/lib/bitmap.c b/lib/bitmap.c index c82c61b66e16..d8f0c094b18e 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -18,7 +18,9 @@ #include -/* +/** + * DOC: bitmap introduction + * * bitmaps provide an array of bits, implemented using an an * array of unsigned longs. The number of valid bits in a * given bitmap does _not_ need to be an exact multiple of -- cgit v1.2.3 From 590c845930457d25d27dc1fdd964a1ce18ef2d7d Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 6 Oct 2017 08:14:37 +0900 Subject: kprobes: Disable the jprobes APIs Disable the jprobes APIs and comment out the jprobes API function code. This is in preparation of removing all jprobes related code (including kprobe's break_handler). Nowadays ftrace and other tracing features are mature enough to replace jprobes use-cases. Users can safely use ftrace and perf probe etc. for their use cases. Signed-off-by: Masami Hiramatsu Cc: Alexei Starovoitov Cc: Ananth N Mavinakayanahalli Cc: Anil S Keshavamurthy Cc: David S . Miller Cc: Ian McDonald Cc: Kees Cook Cc: Linus Torvalds Cc: Paul E . McKenney Cc: Peter Zijlstra Cc: Stephen Hemminger Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vlad Yasevich Link: http://lkml.kernel.org/r/150724527741.5014.15465541485637899227.stgit@devbox Signed-off-by: Ingo Molnar --- include/linux/kprobes.h | 40 ++++++++++++++++++---------------------- kernel/kprobes.c | 2 ++ 2 files changed, 20 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index bd2684700b74..56b2e698dbad 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -391,10 +391,6 @@ int register_kprobes(struct kprobe **kps, int num); void unregister_kprobes(struct kprobe **kps, int num); int setjmp_pre_handler(struct kprobe *, struct pt_regs *); int longjmp_break_handler(struct kprobe *, struct pt_regs *); -int register_jprobe(struct jprobe *p); -void unregister_jprobe(struct jprobe *p); -int register_jprobes(struct jprobe **jps, int num); -void unregister_jprobes(struct jprobe **jps, int num); void jprobe_return(void); unsigned long arch_deref_entry_point(void *); @@ -443,20 +439,6 @@ static inline void unregister_kprobe(struct kprobe *p) static inline void unregister_kprobes(struct kprobe **kps, int num) { } -static inline int register_jprobe(struct jprobe *p) -{ - return -ENOSYS; -} -static inline int register_jprobes(struct jprobe **jps, int num) -{ - return -ENOSYS; -} -static inline void unregister_jprobe(struct jprobe *p) -{ -} -static inline void unregister_jprobes(struct jprobe **jps, int num) -{ -} static inline void jprobe_return(void) { } @@ -486,6 +468,20 @@ static inline int enable_kprobe(struct kprobe *kp) return -ENOSYS; } #endif /* CONFIG_KPROBES */ +static inline int __deprecated register_jprobe(struct jprobe *p) +{ + return -ENOSYS; +} +static inline int __deprecated register_jprobes(struct jprobe **jps, int num) +{ + return -ENOSYS; +} +static inline void __deprecated unregister_jprobe(struct jprobe *p) +{ +} +static inline void __deprecated unregister_jprobes(struct jprobe **jps, int num) +{ +} static inline int disable_kretprobe(struct kretprobe *rp) { return disable_kprobe(&rp->kp); @@ -494,13 +490,13 @@ static inline int enable_kretprobe(struct kretprobe *rp) { return enable_kprobe(&rp->kp); } -static inline int disable_jprobe(struct jprobe *jp) +static inline int __deprecated disable_jprobe(struct jprobe *jp) { - return disable_kprobe(&jp->kp); + return -ENOSYS; } -static inline int enable_jprobe(struct jprobe *jp) +static inline int __deprecated enable_jprobe(struct jprobe *jp) { - return enable_kprobe(&jp->kp); + return -ENOSYS; } #ifndef CONFIG_KPROBES diff --git a/kernel/kprobes.c b/kernel/kprobes.c index a8fc1492b308..da2ccf142358 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1771,6 +1771,7 @@ unsigned long __weak arch_deref_entry_point(void *entry) return (unsigned long)entry; } +#if 0 int register_jprobes(struct jprobe **jps, int num) { int ret = 0, i; @@ -1839,6 +1840,7 @@ void unregister_jprobes(struct jprobe **jps, int num) } } EXPORT_SYMBOL_GPL(unregister_jprobes); +#endif #ifdef CONFIG_KRETPROBES /* -- cgit v1.2.3 From 52f737c2da40259ac9962170ce608b6fb1b55ee4 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 19 Oct 2017 13:28:38 -0700 Subject: timer: Provide wrappers safe for use with LOCKDEP Under LOCKDEP, the timer lock_class_key (set up in __setup_timer) needs to be tied to the caller's context, so an inline for timer_setup() won't work. We do, however, want to keep the inline version around for argument type checking, though, so this provides macro wrappers in the LOCKDEP case. This fixes the case of different timers sharing the same LOCKDEP instance, and producing a false positive warning: [ 580.840858] ====================================================== [ 580.842299] WARNING: possible circular locking dependency detected [ 580.843684] 4.14.0-rc4+ #17 Not tainted [ 580.844554] ------------------------------------------------------ [ 580.845945] swapper/9/0 is trying to acquire lock: [ 580.847024] (slock-AF_INET){+.-.}, at: [] tcp_write_timer+0x24/0xd0 [ 580.848834] but task is already holding lock: [ 580.850107] ((timer)#2){+.-.}, at: [] call_timer_fn+0x0/0x300 [ 580.851663] which lock already depends on the new lock. [ 580.853439] the existing dependency chain (in reverse order) is: [ 580.855311] -> #1 ((timer)#2){+.-.}: [ 580.856538] __lock_acquire+0x114d/0x11a0 [ 580.857506] lock_acquire+0xb0/0x1d0 [ 580.858373] del_timer_sync+0x3c/0xb0 [ 580.859260] inet_csk_reqsk_queue_drop+0x7f/0x1b0 ... -> #0 (slock-AF_INET){+.-.}: [ 580.884980] check_prev_add+0x666/0x700 [ 580.885790] __lock_acquire+0x114d/0x11a0 [ 580.886575] lock_acquire+0xb0/0x1d0 [ 580.887289] _raw_spin_lock+0x2c/0x40 [ 580.888021] tcp_write_timer+0x24/0xd0 ... [ 580.900055] Possible unsafe locking scenario: [ 580.901043] CPU0 CPU1 [ 580.901797] ---- ---- [ 580.902540] lock((timer)#2); [ 580.903046] lock(slock-AF_INET); [ 580.904006] lock((timer)#2); [ 580.904915] lock(slock-AF_INET); [ 580.905502] In this report, del_timer_sync() is from: inet_csk_reqsk_queue_drop() reqsk_queue_unlink() del_timer_sync(&req->rsk_timer) but tcp_write_timer()'s timer is attached to icsk_retransmit_timer. Both had the same lock_class_key, since they were using timer_setup(). Switching to a macro allows for a separate context, avoiding the false positive. Fixes: 686fef928bba ("timer: Prepare to change timer callback argument type") Reported-by: Craig Gallek Suggested-by: Eric Dumazet Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Cc: netdev@vger.kernel.org Cc: "David S. Miller" Link: https://lkml.kernel.org/r/20171019202838.GA43223@beast --- include/linux/timer.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index 10685c33e679..09950482309b 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -150,6 +150,7 @@ static inline void init_timer_on_stack_key(struct timer_list *timer, #define TIMER_DATA_TYPE unsigned long #define TIMER_FUNC_TYPE void (*)(TIMER_DATA_TYPE) +#ifndef CONFIG_LOCKDEP static inline void timer_setup(struct timer_list *timer, void (*callback)(struct timer_list *), unsigned int flags) @@ -165,6 +166,19 @@ static inline void timer_setup_on_stack(struct timer_list *timer, __setup_timer_on_stack(timer, (TIMER_FUNC_TYPE)callback, (TIMER_DATA_TYPE)timer, flags); } +#else +/* + * Under LOCKDEP, the timer lock_class_key (set up in __init_timer) needs + * to be tied to the caller's context, so an inline (above) won't work. We + * do want to keep the inline for argument type checking, though. + */ +# define timer_setup(timer, callback, flags) \ + __setup_timer(timer, (TIMER_FUNC_TYPE)callback, \ + (TIMER_DATA_TYPE)timer, flags) +# define timer_setup_on_stack(timer, callback, flags) \ + __setup_timer_on_stack(timer, (TIMER_FUNC_TYPE)callback,\ + (TIMER_DATA_TYPE)timer, flags) +#endif #define from_timer(var, callback_timer, timer_fieldname) \ container_of(callback_timer, typeof(*var), timer_fieldname) -- cgit v1.2.3 From 83e3c48729d9ebb7af5a31a504f3fd6aff0348c4 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 29 Sep 2017 17:08:16 +0300 Subject: mm/sparsemem: Allocate mem_section at runtime for CONFIG_SPARSEMEM_EXTREME=y Size of the mem_section[] array depends on the size of the physical address space. In preparation for boot-time switching between paging modes on x86-64 we need to make the allocation of mem_section[] dynamic, because otherwise we waste a lot of RAM: with CONFIG_NODE_SHIFT=10, mem_section[] size is 32kB for 4-level paging and 2MB for 5-level paging mode. The patch allocates the array on the first call to sparse_memory_present_with_active_regions(). Signed-off-by: Kirill A. Shutemov Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Cyrill Gorcunov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20170929140821.37654-2-kirill.shutemov@linux.intel.com Signed-off-by: Ingo Molnar --- include/linux/mmzone.h | 6 +++++- mm/page_alloc.c | 10 ++++++++++ mm/sparse.c | 17 +++++++++++------ 3 files changed, 26 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c8f89417740b..e796edf1296f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1150,13 +1150,17 @@ struct mem_section { #define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) #ifdef CONFIG_SPARSEMEM_EXTREME -extern struct mem_section *mem_section[NR_SECTION_ROOTS]; +extern struct mem_section **mem_section; #else extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; #endif static inline struct mem_section *__nr_to_section(unsigned long nr) { +#ifdef CONFIG_SPARSEMEM_EXTREME + if (!mem_section) + return NULL; +#endif if (!mem_section[SECTION_NR_TO_ROOT(nr)]) return NULL; return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 77e4d3c5c57b..8dfd13f724d9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5646,6 +5646,16 @@ void __init sparse_memory_present_with_active_regions(int nid) unsigned long start_pfn, end_pfn; int i, this_nid; +#ifdef CONFIG_SPARSEMEM_EXTREME + if (!mem_section) { + unsigned long size, align; + + size = sizeof(struct mem_section) * NR_SECTION_ROOTS; + align = 1 << (INTERNODE_CACHE_SHIFT); + mem_section = memblock_virt_alloc(size, align); + } +#endif + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid) memory_present(this_nid, start_pfn, end_pfn); } diff --git a/mm/sparse.c b/mm/sparse.c index 83b3bf6461af..b00a97398795 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -22,8 +22,7 @@ * 1) mem_section - memory sections, mem_map's for valid memory */ #ifdef CONFIG_SPARSEMEM_EXTREME -struct mem_section *mem_section[NR_SECTION_ROOTS] - ____cacheline_internodealigned_in_smp; +struct mem_section **mem_section; #else struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT] ____cacheline_internodealigned_in_smp; @@ -100,7 +99,7 @@ static inline int sparse_index_init(unsigned long section_nr, int nid) int __section_nr(struct mem_section* ms) { unsigned long root_nr; - struct mem_section* root; + struct mem_section *root = NULL; for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) { root = __nr_to_section(root_nr * SECTIONS_PER_ROOT); @@ -111,7 +110,7 @@ int __section_nr(struct mem_section* ms) break; } - VM_BUG_ON(root_nr == NR_SECTION_ROOTS); + VM_BUG_ON(!root); return (root_nr * SECTIONS_PER_ROOT) + (ms - root); } @@ -329,11 +328,17 @@ again: static void __init check_usemap_section_nr(int nid, unsigned long *usemap) { unsigned long usemap_snr, pgdat_snr; - static unsigned long old_usemap_snr = NR_MEM_SECTIONS; - static unsigned long old_pgdat_snr = NR_MEM_SECTIONS; + static unsigned long old_usemap_snr; + static unsigned long old_pgdat_snr; struct pglist_data *pgdat = NODE_DATA(nid); int usemap_nid; + /* First call */ + if (!old_usemap_snr) { + old_usemap_snr = NR_MEM_SECTIONS; + old_pgdat_snr = NR_MEM_SECTIONS; + } + usemap_snr = pfn_to_section_nr(__pa(usemap) >> PAGE_SHIFT); pgdat_snr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT); if (usemap_snr == pgdat_snr) -- cgit v1.2.3 From e4d0b679a8467b6d0c169642f0b5f57d8d6eacc2 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 17 Sep 2017 14:30:06 -0700 Subject: srcu: Add parameters to SRCU docbook comments Signed-off-by: Paul E. McKenney --- include/linux/srcu.h | 1 + kernel/rcu/srcutree.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 39af9bc0f653..62be8966e837 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -78,6 +78,7 @@ void synchronize_srcu(struct srcu_struct *sp); /** * srcu_read_lock_held - might we be in SRCU read-side critical section? + * @sp: The srcu_struct structure to check * * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 729a8706751d..6d5880089ff6 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -854,7 +854,7 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, /** * call_srcu() - Queue a callback for invocation after an SRCU grace period * @sp: srcu_struct in queue the callback - * @head: structure to be used for queueing the SRCU callback. + * @rhp: structure to be used for queueing the SRCU callback. * @func: function to be invoked after the SRCU grace period * * The callback function will be invoked some time after a full SRCU -- cgit v1.2.3 From c6cd924efe941ef62eb805c59e4a09e219ac5c6d Mon Sep 17 00:00:00 2001 From: Yanjiang Jin Date: Tue, 24 Oct 2017 14:23:41 +0800 Subject: cpu/hotplug: Remove obsolete notifier macros commit 530e9b76ae8f ("cpu/hotplug: Remove obsolete cpu hotplug register/unregister functions")' removed the below macros: - #define CPU_UP_CANCELED 0x0004 /* CPU (unsigned)v NOT coming up */ - #define CPU_DOWN_PREPARE 0x0005 /* CPU (unsigned)v going down */ - #define CPU_DOWN_FAILED 0x0006 /* CPU (unsigned)v NOT going down */ But "CPU_UP_CANCELED_FROZEN, CPU_DOWN_PREPARE_FROZEN and CPU_DOWN_FAILED_FROZEN" still refer to them, and nobody uses these "FROZEN" macros now, so remove them too. Signed-off-by: Yanjiang Jin Signed-off-by: Thomas Gleixner Cc: peterz@infradead.org Cc: bigeasy@linutronix.de Cc: jinyanjiang@gmail.com Link: https://lkml.kernel.org/r/20171024062341.179678-1-yanjiang.jin@windriver.com --- include/linux/cpu.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ca73bc1563f4..cd4771b772c0 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -72,9 +72,6 @@ struct notifier_block; #define CPU_ONLINE_FROZEN (CPU_ONLINE | CPU_TASKS_FROZEN) #define CPU_UP_PREPARE_FROZEN (CPU_UP_PREPARE | CPU_TASKS_FROZEN) -#define CPU_UP_CANCELED_FROZEN (CPU_UP_CANCELED | CPU_TASKS_FROZEN) -#define CPU_DOWN_PREPARE_FROZEN (CPU_DOWN_PREPARE | CPU_TASKS_FROZEN) -#define CPU_DOWN_FAILED_FROZEN (CPU_DOWN_FAILED | CPU_TASKS_FROZEN) #define CPU_DEAD_FROZEN (CPU_DEAD | CPU_TASKS_FROZEN) #ifdef CONFIG_SMP -- cgit v1.2.3 From e22cdc3fc5991956146b9856d36b4971fe54dcd6 Mon Sep 17 00:00:00 2001 From: Rakib Mullick Date: Mon, 23 Oct 2017 19:01:54 +0600 Subject: sched/isolcpus: Fix "isolcpus=" boot parameter handling when !CONFIG_CPUMASK_OFFSTACK cpulist_parse() uses nr_cpumask_bits as a limit to parse the passed buffer from kernel commandline. What nr_cpumask_bits represents varies depending upon the CONFIG_CPUMASK_OFFSTACK option: - If CONFIG_CPUMASK_OFFSTACK=n, then nr_cpumask_bits is the same as NR_CPUS, which might not represent the # of CPUs that really exist (default 64). So, there's a chance of a gap between nr_cpu_ids and NR_CPUS, which ultimately lead towards invalid cpulist_parse() operation. For example, if isolcpus=9 is passed on an 8 cpu system (CONFIG_CPUMASK_OFFSTACK=n) it doesn't show the error that it's supposed to. This patch fixes this bug by finding the last CPU of the passed isolcpus= list and checking it against nr_cpu_ids. It also fixes the error message where the nr_cpu_ids should be nr_cpu_ids-1, since CPU numbering starts from 0. Signed-off-by: Rakib Mullick Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: adobriyan@gmail.com Cc: akpm@linux-foundation.org Cc: longman@redhat.com Cc: mka@chromium.org Cc: tj@kernel.org Link: http://lkml.kernel.org/r/20171023130154.9050-1-rakib.mullick@gmail.com [ Enhanced the changelog and the kernel message. ] Signed-off-by: Ingo Molnar include/linux/cpumask.h | 16 ++++++++++++++++ kernel/sched/topology.c | 4 ++-- 2 files changed, 18 insertions(+), 2 deletions(-) --- include/linux/cpumask.h | 16 ++++++++++++++++ kernel/sched/topology.c | 4 ++-- 2 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index cd415b733c2a..63661de67ad4 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -130,6 +130,11 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) return 0; } +static inline unsigned int cpumask_last(const struct cpumask *srcp) +{ + return 0; +} + /* Valid inputs for n are -1 and 0. */ static inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { @@ -178,6 +183,17 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits); } +/** + * cpumask_last - get the last CPU in a cpumask + * @srcp: - the cpumask pointer + * + * Returns >= nr_cpumask_bits if no CPUs set. + */ +static inline unsigned int cpumask_last(const struct cpumask *srcp) +{ + return find_last_bit(cpumask_bits(srcp), nr_cpumask_bits); +} + unsigned int cpumask_next(int n, const struct cpumask *srcp); /** diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index e50450c2fed8..e3d31b0880dc 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -476,8 +476,8 @@ static int __init isolated_cpu_setup(char *str) alloc_bootmem_cpumask_var(&cpu_isolated_map); ret = cpulist_parse(str, cpu_isolated_map); - if (ret) { - pr_err("sched: Error, all isolcpus= values must be between 0 and %u\n", nr_cpu_ids); + if (ret || cpumask_last(cpu_isolated_map) >= nr_cpu_ids) { + pr_err("sched: Error, all isolcpus= values must be between 0 and %u - ignoring them.\n", nr_cpu_ids-1); return 0; } return 1; -- cgit v1.2.3 From d15155824c5014803d91b829736d249c500bdda6 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 24 Oct 2017 11:22:46 +0100 Subject: linux/compiler.h: Split into compiler.h and compiler_types.h linux/compiler.h is included indirectly by linux/types.h via uapi/linux/types.h -> uapi/linux/posix_types.h -> linux/stddef.h -> uapi/linux/stddef.h and is needed to provide a proper definition of offsetof. Unfortunately, compiler.h requires a definition of smp_read_barrier_depends() for defining lockless_dereference() and soon for defining READ_ONCE(), which means that all users of READ_ONCE() will need to include asm/barrier.h to avoid splats such as: In file included from include/uapi/linux/stddef.h:1:0, from include/linux/stddef.h:4, from arch/h8300/kernel/asm-offsets.c:11: include/linux/list.h: In function 'list_empty': >> include/linux/compiler.h:343:2: error: implicit declaration of function 'smp_read_barrier_depends' [-Werror=implicit-function-declaration] smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \ ^ A better alternative is to include asm/barrier.h in linux/compiler.h, but this requires a type definition for "bool" on some architectures (e.g. x86), which is defined later by linux/types.h. Type "bool" is also used directly in linux/compiler.h, so the whole thing is pretty fragile. This patch splits compiler.h in two: compiler_types.h contains type annotations, definitions and the compiler-specific parts, whereas compiler.h #includes compiler-types.h and additionally defines macros such as {READ,WRITE.ACCESS}_ONCE(). uapi/linux/stddef.h and linux/linkage.h are then moved over to include linux/compiler_types.h, which fixes the build for h8 and blackfin. Signed-off-by: Will Deacon Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1508840570-22169-2-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar --- arch/arm/include/asm/ptrace.h | 3 +- arch/sparc/include/asm/ptrace.h | 1 + arch/um/include/shared/init.h | 2 +- include/linux/compiler-clang.h | 2 +- include/linux/compiler-gcc.h | 2 +- include/linux/compiler-intel.h | 2 +- include/linux/compiler.h | 265 +------------------------------------- include/linux/compiler_types.h | 274 ++++++++++++++++++++++++++++++++++++++++ include/linux/linkage.h | 2 +- include/uapi/linux/stddef.h | 2 +- scripts/headers_install.sh | 2 +- 11 files changed, 286 insertions(+), 271 deletions(-) create mode 100644 include/linux/compiler_types.h (limited to 'include/linux') diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h index e9c9a117bd25..c7cdbb43ae7c 100644 --- a/arch/arm/include/asm/ptrace.h +++ b/arch/arm/include/asm/ptrace.h @@ -126,8 +126,7 @@ extern unsigned long profile_pc(struct pt_regs *regs); /* * kprobe-based event tracer support */ -#include -#include +#include #define MAX_REG_OFFSET (offsetof(struct pt_regs, ARM_ORIG_r0)) extern int regs_query_register_offset(const char *name); diff --git a/arch/sparc/include/asm/ptrace.h b/arch/sparc/include/asm/ptrace.h index d73428e4333c..b383484edcd3 100644 --- a/arch/sparc/include/asm/ptrace.h +++ b/arch/sparc/include/asm/ptrace.h @@ -6,6 +6,7 @@ #if defined(__sparc__) && defined(__arch64__) #ifndef __ASSEMBLY__ +#include #include #include diff --git a/arch/um/include/shared/init.h b/arch/um/include/shared/init.h index 233e2593eee0..094e96ce653b 100644 --- a/arch/um/include/shared/init.h +++ b/arch/um/include/shared/init.h @@ -40,7 +40,7 @@ typedef int (*initcall_t)(void); typedef void (*exitcall_t)(void); -#include +#include /* These are for everybody (although not all archs will actually discard it in modules) */ diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index de179993e039..5947a3e6c0e6 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -1,4 +1,4 @@ -#ifndef __LINUX_COMPILER_H +#ifndef __LINUX_COMPILER_TYPES_H #error "Please don't include directly, include instead." #endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 16d41de92ee3..ce8e965646ef 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -1,4 +1,4 @@ -#ifndef __LINUX_COMPILER_H +#ifndef __LINUX_COMPILER_TYPES_H #error "Please don't include directly, include instead." #endif diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index d4c71132d07f..e438ac89c692 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -1,4 +1,4 @@ -#ifndef __LINUX_COMPILER_H +#ifndef __LINUX_COMPILER_TYPES_H #error "Please don't include directly, include instead." #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index e95a2631e545..08083186e54f 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -1,111 +1,12 @@ #ifndef __LINUX_COMPILER_H #define __LINUX_COMPILER_H -#ifndef __ASSEMBLY__ +#include -#ifdef __CHECKER__ -# define __user __attribute__((noderef, address_space(1))) -# define __kernel __attribute__((address_space(0))) -# define __safe __attribute__((safe)) -# define __force __attribute__((force)) -# define __nocast __attribute__((nocast)) -# define __iomem __attribute__((noderef, address_space(2))) -# define __must_hold(x) __attribute__((context(x,1,1))) -# define __acquires(x) __attribute__((context(x,0,1))) -# define __releases(x) __attribute__((context(x,1,0))) -# define __acquire(x) __context__(x,1) -# define __release(x) __context__(x,-1) -# define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) -# define __percpu __attribute__((noderef, address_space(3))) -# define __rcu __attribute__((noderef, address_space(4))) -# define __private __attribute__((noderef)) -extern void __chk_user_ptr(const volatile void __user *); -extern void __chk_io_ptr(const volatile void __iomem *); -# define ACCESS_PRIVATE(p, member) (*((typeof((p)->member) __force *) &(p)->member)) -#else /* __CHECKER__ */ -# ifdef STRUCTLEAK_PLUGIN -# define __user __attribute__((user)) -# else -# define __user -# endif -# define __kernel -# define __safe -# define __force -# define __nocast -# define __iomem -# define __chk_user_ptr(x) (void)0 -# define __chk_io_ptr(x) (void)0 -# define __builtin_warning(x, y...) (1) -# define __must_hold(x) -# define __acquires(x) -# define __releases(x) -# define __acquire(x) (void)0 -# define __release(x) (void)0 -# define __cond_lock(x,c) (c) -# define __percpu -# define __rcu -# define __private -# define ACCESS_PRIVATE(p, member) ((p)->member) -#endif /* __CHECKER__ */ - -/* Indirect macros required for expanded argument pasting, eg. __LINE__. */ -#define ___PASTE(a,b) a##b -#define __PASTE(a,b) ___PASTE(a,b) +#ifndef __ASSEMBLY__ #ifdef __KERNEL__ -#ifdef __GNUC__ -#include -#endif - -#if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__) -#define notrace __attribute__((hotpatch(0,0))) -#else -#define notrace __attribute__((no_instrument_function)) -#endif - -/* Intel compiler defines __GNUC__. So we will overwrite implementations - * coming from above header files here - */ -#ifdef __INTEL_COMPILER -# include -#endif - -/* Clang compiler defines __GNUC__. So we will overwrite implementations - * coming from above header files here - */ -#ifdef __clang__ -#include -#endif - -/* - * Generic compiler-dependent macros required for kernel - * build go below this comment. Actual compiler/compiler version - * specific implementations come from the above header files - */ - -struct ftrace_branch_data { - const char *func; - const char *file; - unsigned line; - union { - struct { - unsigned long correct; - unsigned long incorrect; - }; - struct { - unsigned long miss; - unsigned long hit; - }; - unsigned long miss_hit[2]; - }; -}; - -struct ftrace_likely_data { - struct ftrace_branch_data data; - unsigned long constant; -}; - /* * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code * to disable branch tracing on a per file basis. @@ -332,6 +233,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * with an explicit memory barrier or atomic instruction that provides the * required ordering. */ +#include #define __READ_ONCE(x, check) \ ({ \ @@ -362,167 +264,6 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s #endif /* __ASSEMBLY__ */ -#ifdef __KERNEL__ -/* - * Allow us to mark functions as 'deprecated' and have gcc emit a nice - * warning for each use, in hopes of speeding the functions removal. - * Usage is: - * int __deprecated foo(void) - */ -#ifndef __deprecated -# define __deprecated /* unimplemented */ -#endif - -#ifdef MODULE -#define __deprecated_for_modules __deprecated -#else -#define __deprecated_for_modules -#endif - -#ifndef __must_check -#define __must_check -#endif - -#ifndef CONFIG_ENABLE_MUST_CHECK -#undef __must_check -#define __must_check -#endif -#ifndef CONFIG_ENABLE_WARN_DEPRECATED -#undef __deprecated -#undef __deprecated_for_modules -#define __deprecated -#define __deprecated_for_modules -#endif - -#ifndef __malloc -#define __malloc -#endif - -/* - * Allow us to avoid 'defined but not used' warnings on functions and data, - * as well as force them to be emitted to the assembly file. - * - * As of gcc 3.4, static functions that are not marked with attribute((used)) - * may be elided from the assembly file. As of gcc 3.4, static data not so - * marked will not be elided, but this may change in a future gcc version. - * - * NOTE: Because distributions shipped with a backported unit-at-a-time - * compiler in gcc 3.3, we must define __used to be __attribute__((used)) - * for gcc >=3.3 instead of 3.4. - * - * In prior versions of gcc, such functions and data would be emitted, but - * would be warned about except with attribute((unused)). - * - * Mark functions that are referenced only in inline assembly as __used so - * the code is emitted even though it appears to be unreferenced. - */ -#ifndef __used -# define __used /* unimplemented */ -#endif - -#ifndef __maybe_unused -# define __maybe_unused /* unimplemented */ -#endif - -#ifndef __always_unused -# define __always_unused /* unimplemented */ -#endif - -#ifndef noinline -#define noinline -#endif - -/* - * Rather then using noinline to prevent stack consumption, use - * noinline_for_stack instead. For documentation reasons. - */ -#define noinline_for_stack noinline - -#ifndef __always_inline -#define __always_inline inline -#endif - -#endif /* __KERNEL__ */ - -/* - * From the GCC manual: - * - * Many functions do not examine any values except their arguments, - * and have no effects except the return value. Basically this is - * just slightly more strict class than the `pure' attribute above, - * since function is not allowed to read global memory. - * - * Note that a function that has pointer arguments and examines the - * data pointed to must _not_ be declared `const'. Likewise, a - * function that calls a non-`const' function usually must not be - * `const'. It does not make sense for a `const' function to return - * `void'. - */ -#ifndef __attribute_const__ -# define __attribute_const__ /* unimplemented */ -#endif - -#ifndef __designated_init -# define __designated_init -#endif - -#ifndef __latent_entropy -# define __latent_entropy -#endif - -#ifndef __randomize_layout -# define __randomize_layout __designated_init -#endif - -#ifndef __no_randomize_layout -# define __no_randomize_layout -#endif - -#ifndef randomized_struct_fields_start -# define randomized_struct_fields_start -# define randomized_struct_fields_end -#endif - -/* - * Tell gcc if a function is cold. The compiler will assume any path - * directly leading to the call is unlikely. - */ - -#ifndef __cold -#define __cold -#endif - -/* Simple shorthand for a section definition */ -#ifndef __section -# define __section(S) __attribute__ ((__section__(#S))) -#endif - -#ifndef __visible -#define __visible -#endif - -#ifndef __nostackprotector -# define __nostackprotector -#endif - -/* - * Assume alignment of return value. - */ -#ifndef __assume_aligned -#define __assume_aligned(a, ...) -#endif - - -/* Are two types/vars the same type (ignoring qualifiers)? */ -#ifndef __same_type -# define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) -#endif - -/* Is this type a native word size -- useful for atomic operations */ -#ifndef __native_word -# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) -#endif - /* Compile time object size, -1 for unknown */ #ifndef __compiletime_object_size # define __compiletime_object_size(obj) -1 diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h new file mode 100644 index 000000000000..6b79a9bba9a7 --- /dev/null +++ b/include/linux/compiler_types.h @@ -0,0 +1,274 @@ +#ifndef __LINUX_COMPILER_TYPES_H +#define __LINUX_COMPILER_TYPES_H + +#ifndef __ASSEMBLY__ + +#ifdef __CHECKER__ +# define __user __attribute__((noderef, address_space(1))) +# define __kernel __attribute__((address_space(0))) +# define __safe __attribute__((safe)) +# define __force __attribute__((force)) +# define __nocast __attribute__((nocast)) +# define __iomem __attribute__((noderef, address_space(2))) +# define __must_hold(x) __attribute__((context(x,1,1))) +# define __acquires(x) __attribute__((context(x,0,1))) +# define __releases(x) __attribute__((context(x,1,0))) +# define __acquire(x) __context__(x,1) +# define __release(x) __context__(x,-1) +# define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) +# define __percpu __attribute__((noderef, address_space(3))) +# define __rcu __attribute__((noderef, address_space(4))) +# define __private __attribute__((noderef)) +extern void __chk_user_ptr(const volatile void __user *); +extern void __chk_io_ptr(const volatile void __iomem *); +# define ACCESS_PRIVATE(p, member) (*((typeof((p)->member) __force *) &(p)->member)) +#else /* __CHECKER__ */ +# ifdef STRUCTLEAK_PLUGIN +# define __user __attribute__((user)) +# else +# define __user +# endif +# define __kernel +# define __safe +# define __force +# define __nocast +# define __iomem +# define __chk_user_ptr(x) (void)0 +# define __chk_io_ptr(x) (void)0 +# define __builtin_warning(x, y...) (1) +# define __must_hold(x) +# define __acquires(x) +# define __releases(x) +# define __acquire(x) (void)0 +# define __release(x) (void)0 +# define __cond_lock(x,c) (c) +# define __percpu +# define __rcu +# define __private +# define ACCESS_PRIVATE(p, member) ((p)->member) +#endif /* __CHECKER__ */ + +/* Indirect macros required for expanded argument pasting, eg. __LINE__. */ +#define ___PASTE(a,b) a##b +#define __PASTE(a,b) ___PASTE(a,b) + +#ifdef __KERNEL__ + +#ifdef __GNUC__ +#include +#endif + +#if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__) +#define notrace __attribute__((hotpatch(0,0))) +#else +#define notrace __attribute__((no_instrument_function)) +#endif + +/* Intel compiler defines __GNUC__. So we will overwrite implementations + * coming from above header files here + */ +#ifdef __INTEL_COMPILER +# include +#endif + +/* Clang compiler defines __GNUC__. So we will overwrite implementations + * coming from above header files here + */ +#ifdef __clang__ +#include +#endif + +/* + * Generic compiler-dependent macros required for kernel + * build go below this comment. Actual compiler/compiler version + * specific implementations come from the above header files + */ + +struct ftrace_branch_data { + const char *func; + const char *file; + unsigned line; + union { + struct { + unsigned long correct; + unsigned long incorrect; + }; + struct { + unsigned long miss; + unsigned long hit; + }; + unsigned long miss_hit[2]; + }; +}; + +struct ftrace_likely_data { + struct ftrace_branch_data data; + unsigned long constant; +}; + +#endif /* __KERNEL__ */ + +#endif /* __ASSEMBLY__ */ + +#ifdef __KERNEL__ +/* + * Allow us to mark functions as 'deprecated' and have gcc emit a nice + * warning for each use, in hopes of speeding the functions removal. + * Usage is: + * int __deprecated foo(void) + */ +#ifndef __deprecated +# define __deprecated /* unimplemented */ +#endif + +#ifdef MODULE +#define __deprecated_for_modules __deprecated +#else +#define __deprecated_for_modules +#endif + +#ifndef __must_check +#define __must_check +#endif + +#ifndef CONFIG_ENABLE_MUST_CHECK +#undef __must_check +#define __must_check +#endif +#ifndef CONFIG_ENABLE_WARN_DEPRECATED +#undef __deprecated +#undef __deprecated_for_modules +#define __deprecated +#define __deprecated_for_modules +#endif + +#ifndef __malloc +#define __malloc +#endif + +/* + * Allow us to avoid 'defined but not used' warnings on functions and data, + * as well as force them to be emitted to the assembly file. + * + * As of gcc 3.4, static functions that are not marked with attribute((used)) + * may be elided from the assembly file. As of gcc 3.4, static data not so + * marked will not be elided, but this may change in a future gcc version. + * + * NOTE: Because distributions shipped with a backported unit-at-a-time + * compiler in gcc 3.3, we must define __used to be __attribute__((used)) + * for gcc >=3.3 instead of 3.4. + * + * In prior versions of gcc, such functions and data would be emitted, but + * would be warned about except with attribute((unused)). + * + * Mark functions that are referenced only in inline assembly as __used so + * the code is emitted even though it appears to be unreferenced. + */ +#ifndef __used +# define __used /* unimplemented */ +#endif + +#ifndef __maybe_unused +# define __maybe_unused /* unimplemented */ +#endif + +#ifndef __always_unused +# define __always_unused /* unimplemented */ +#endif + +#ifndef noinline +#define noinline +#endif + +/* + * Rather then using noinline to prevent stack consumption, use + * noinline_for_stack instead. For documentation reasons. + */ +#define noinline_for_stack noinline + +#ifndef __always_inline +#define __always_inline inline +#endif + +#endif /* __KERNEL__ */ + +/* + * From the GCC manual: + * + * Many functions do not examine any values except their arguments, + * and have no effects except the return value. Basically this is + * just slightly more strict class than the `pure' attribute above, + * since function is not allowed to read global memory. + * + * Note that a function that has pointer arguments and examines the + * data pointed to must _not_ be declared `const'. Likewise, a + * function that calls a non-`const' function usually must not be + * `const'. It does not make sense for a `const' function to return + * `void'. + */ +#ifndef __attribute_const__ +# define __attribute_const__ /* unimplemented */ +#endif + +#ifndef __designated_init +# define __designated_init +#endif + +#ifndef __latent_entropy +# define __latent_entropy +#endif + +#ifndef __randomize_layout +# define __randomize_layout __designated_init +#endif + +#ifndef __no_randomize_layout +# define __no_randomize_layout +#endif + +#ifndef randomized_struct_fields_start +# define randomized_struct_fields_start +# define randomized_struct_fields_end +#endif + +/* + * Tell gcc if a function is cold. The compiler will assume any path + * directly leading to the call is unlikely. + */ + +#ifndef __cold +#define __cold +#endif + +/* Simple shorthand for a section definition */ +#ifndef __section +# define __section(S) __attribute__ ((__section__(#S))) +#endif + +#ifndef __visible +#define __visible +#endif + +#ifndef __nostackprotector +# define __nostackprotector +#endif + +/* + * Assume alignment of return value. + */ +#ifndef __assume_aligned +#define __assume_aligned(a, ...) +#endif + + +/* Are two types/vars the same type (ignoring qualifiers)? */ +#ifndef __same_type +# define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) +#endif + +/* Is this type a native word size -- useful for atomic operations */ +#ifndef __native_word +# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) +#endif + +#endif /* __LINUX_COMPILER_TYPES_H */ diff --git a/include/linux/linkage.h b/include/linux/linkage.h index a6a42dd02466..ebd61b80fed4 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -1,7 +1,7 @@ #ifndef _LINUX_LINKAGE_H #define _LINUX_LINKAGE_H -#include +#include #include #include #include diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 621fa8ac4425..d1f7cb732dfc 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -1,4 +1,4 @@ -#include +#include #ifndef __always_inline #define __always_inline inline diff --git a/scripts/headers_install.sh b/scripts/headers_install.sh index fdebd66f8fc1..63b8cc26456a 100755 --- a/scripts/headers_install.sh +++ b/scripts/headers_install.sh @@ -33,7 +33,7 @@ do sed -r \ -e 's/([ \t(])(__user|__force|__iomem)[ \t]/\1/g' \ -e 's/__attribute_const__([ \t]|$)/\1/g' \ - -e 's@^#include @@' \ + -e 's@^#include @@' \ -e 's/(^|[^a-zA-Z0-9])__packed([^a-zA-Z0-9_]|$)/\1__attribute__((packed))\2/g' \ -e 's/(^|[ \t(])(inline|asm|volatile)([ \t(]|$)/\1__\2__\3/g' \ -e 's@#(ifndef|define|endif[ \t]*/[*])[ \t]*_UAPI@#\1 @' \ -- cgit v1.2.3 From 76ebbe78f7390aee075a7f3768af197ded1bdfbb Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 24 Oct 2017 11:22:47 +0100 Subject: locking/barriers: Add implicit smp_read_barrier_depends() to READ_ONCE() In preparation for the removal of lockless_dereference(), which is the same as READ_ONCE() on all architectures other than Alpha, add an implicit smp_read_barrier_depends() to READ_ONCE() so that it can be used to head dependency chains on all architectures. Signed-off-by: Will Deacon Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1508840570-22169-3-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 08083186e54f..7d7b77da9716 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -242,6 +242,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s __read_once_size(&(x), __u.__c, sizeof(x)); \ else \ __read_once_size_nocheck(&(x), __u.__c, sizeof(x)); \ + smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \ __u.__val; \ }) #define READ_ONCE(x) __READ_ONCE(x, 1) -- cgit v1.2.3 From 506458efaf153c1ea480591c5602a5a3ba5a3b76 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 24 Oct 2017 11:22:48 +0100 Subject: locking/barriers: Convert users of lockless_dereference() to READ_ONCE() READ_ONCE() now has an implicit smp_read_barrier_depends() call, so it can be used instead of lockless_dereference() without any change in semantics. Signed-off-by: Will Deacon Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1508840570-22169-4-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar --- arch/x86/events/core.c | 2 +- arch/x86/include/asm/mmu_context.h | 4 ++-- arch/x86/kernel/ldt.c | 2 +- drivers/md/dm-mpath.c | 20 ++++++++++---------- fs/dcache.c | 4 ++-- fs/overlayfs/ovl_entry.h | 2 +- fs/overlayfs/readdir.c | 2 +- include/linux/rculist.h | 4 ++-- include/linux/rcupdate.h | 4 ++-- kernel/events/core.c | 4 ++-- kernel/seccomp.c | 2 +- kernel/task_work.c | 2 +- mm/slab.h | 2 +- 13 files changed, 27 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 80534d3c2480..589af1eec7c1 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2371,7 +2371,7 @@ static unsigned long get_segment_base(unsigned int segment) struct ldt_struct *ldt; /* IRQs are off, so this synchronizes with smp_store_release */ - ldt = lockless_dereference(current->active_mm->context.ldt); + ldt = READ_ONCE(current->active_mm->context.ldt); if (!ldt || idx >= ldt->nr_entries) return 0; diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 3c856a15b98e..efc530642f7d 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -72,8 +72,8 @@ static inline void load_mm_ldt(struct mm_struct *mm) #ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; - /* lockless_dereference synchronizes with smp_store_release */ - ldt = lockless_dereference(mm->context.ldt); + /* READ_ONCE synchronizes with smp_store_release */ + ldt = READ_ONCE(mm->context.ldt); /* * Any change to mm->context.ldt is followed by an IPI to all diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index f0e64db18ac8..0a21390642c4 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -101,7 +101,7 @@ static void finalize_ldt_struct(struct ldt_struct *ldt) static void install_ldt(struct mm_struct *current_mm, struct ldt_struct *ldt) { - /* Synchronizes with lockless_dereference in load_mm_ldt. */ + /* Synchronizes with READ_ONCE in load_mm_ldt. */ smp_store_release(¤t_mm->context.ldt, ldt); /* Activate the LDT for all CPUs using current_mm. */ diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 11f273d2f018..3f88c9d32f7e 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -366,7 +366,7 @@ static struct pgpath *choose_path_in_pg(struct multipath *m, pgpath = path_to_pgpath(path); - if (unlikely(lockless_dereference(m->current_pg) != pg)) { + if (unlikely(READ_ONCE(m->current_pg) != pg)) { /* Only update current_pgpath if pg changed */ spin_lock_irqsave(&m->lock, flags); m->current_pgpath = pgpath; @@ -390,7 +390,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes) } /* Were we instructed to switch PG? */ - if (lockless_dereference(m->next_pg)) { + if (READ_ONCE(m->next_pg)) { spin_lock_irqsave(&m->lock, flags); pg = m->next_pg; if (!pg) { @@ -406,7 +406,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes) /* Don't change PG until it has no remaining paths */ check_current_pg: - pg = lockless_dereference(m->current_pg); + pg = READ_ONCE(m->current_pg); if (pg) { pgpath = choose_path_in_pg(m, pg, nr_bytes); if (!IS_ERR_OR_NULL(pgpath)) @@ -473,7 +473,7 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq, struct request *clone; /* Do we need to select a new pgpath? */ - pgpath = lockless_dereference(m->current_pgpath); + pgpath = READ_ONCE(m->current_pgpath); if (!pgpath || !test_bit(MPATHF_QUEUE_IO, &m->flags)) pgpath = choose_pgpath(m, nr_bytes); @@ -535,7 +535,7 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m bool queue_io; /* Do we need to select a new pgpath? */ - pgpath = lockless_dereference(m->current_pgpath); + pgpath = READ_ONCE(m->current_pgpath); queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags); if (!pgpath || !queue_io) pgpath = choose_pgpath(m, nr_bytes); @@ -1804,7 +1804,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti, struct pgpath *current_pgpath; int r; - current_pgpath = lockless_dereference(m->current_pgpath); + current_pgpath = READ_ONCE(m->current_pgpath); if (!current_pgpath) current_pgpath = choose_pgpath(m, 0); @@ -1826,7 +1826,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti, } if (r == -ENOTCONN) { - if (!lockless_dereference(m->current_pg)) { + if (!READ_ONCE(m->current_pg)) { /* Path status changed, redo selection */ (void) choose_pgpath(m, 0); } @@ -1895,9 +1895,9 @@ static int multipath_busy(struct dm_target *ti) return (m->queue_mode != DM_TYPE_MQ_REQUEST_BASED); /* Guess which priority_group will be used at next mapping time */ - pg = lockless_dereference(m->current_pg); - next_pg = lockless_dereference(m->next_pg); - if (unlikely(!lockless_dereference(m->current_pgpath) && next_pg)) + pg = READ_ONCE(m->current_pg); + next_pg = READ_ONCE(m->next_pg); + if (unlikely(!READ_ONCE(m->current_pgpath) && next_pg)) pg = next_pg; if (!pg) { diff --git a/fs/dcache.c b/fs/dcache.c index f90141387f01..34c852af215c 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -231,7 +231,7 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c { /* * Be careful about RCU walk racing with rename: - * use 'lockless_dereference' to fetch the name pointer. + * use 'READ_ONCE' to fetch the name pointer. * * NOTE! Even if a rename will mean that the length * was not loaded atomically, we don't care. The @@ -245,7 +245,7 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c * early because the data cannot match (there can * be no NUL in the ct/tcount data) */ - const unsigned char *cs = lockless_dereference(dentry->d_name.name); + const unsigned char *cs = READ_ONCE(dentry->d_name.name); return dentry_string_cmp(cs, ct, tcount); } diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index 25d9b5adcd42..36b49bd09264 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -77,5 +77,5 @@ static inline struct ovl_inode *OVL_I(struct inode *inode) static inline struct dentry *ovl_upperdentry_dereference(struct ovl_inode *oi) { - return lockless_dereference(oi->__upperdentry); + return READ_ONCE(oi->__upperdentry); } diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 0f85ee9c3268..c67a7703296b 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -754,7 +754,7 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end, if (!od->is_upper && OVL_TYPE_UPPER(ovl_path_type(dentry))) { struct inode *inode = file_inode(file); - realfile = lockless_dereference(od->upperfile); + realfile = READ_ONCE(od->upperfile); if (!realfile) { struct path upperpath; diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 2bea1d5e9930..5ed091c064b2 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -274,7 +274,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ - container_of(lockless_dereference(ptr), type, member) + container_of(READ_ONCE(ptr), type, member) /* * Where are list_empty_rcu() and list_first_entry_rcu()? @@ -367,7 +367,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * example is when items are added to the list, but never deleted. */ #define list_entry_lockless(ptr, type, member) \ - container_of((typeof(ptr))lockless_dereference(ptr), type, member) + container_of((typeof(ptr))READ_ONCE(ptr), type, member) /** * list_for_each_entry_lockless - iterate over rcu list of given type diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 1a9f70d44af9..a6ddc42f87a5 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -346,7 +346,7 @@ static inline void rcu_preempt_sleep_check(void) { } #define __rcu_dereference_check(p, c, space) \ ({ \ /* Dependency order vs. p above. */ \ - typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \ + typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_dereference_sparse(p, space); \ ((typeof(*p) __force __kernel *)(________p1)); \ @@ -360,7 +360,7 @@ static inline void rcu_preempt_sleep_check(void) { } #define rcu_dereference_raw(p) \ ({ \ /* Dependency order vs. p above. */ \ - typeof(p) ________p1 = lockless_dereference(p); \ + typeof(p) ________p1 = READ_ONCE(p); \ ((typeof(*p) __force __kernel *)(________p1)); \ }) diff --git a/kernel/events/core.c b/kernel/events/core.c index 9d93db81fa36..824a583079a1 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4231,7 +4231,7 @@ static void perf_remove_from_owner(struct perf_event *event) * indeed free this event, otherwise we need to serialize on * owner->perf_event_mutex. */ - owner = lockless_dereference(event->owner); + owner = READ_ONCE(event->owner); if (owner) { /* * Since delayed_put_task_struct() also drops the last @@ -4328,7 +4328,7 @@ again: * Cannot change, child events are not migrated, see the * comment with perf_event_ctx_lock_nested(). */ - ctx = lockless_dereference(child->ctx); + ctx = READ_ONCE(child->ctx); /* * Since child_mutex nests inside ctx::mutex, we must jump * through hoops. We start by grabbing a reference on the ctx. diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 0ae832e13b97..8ac79355915b 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -189,7 +189,7 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd, u32 ret = SECCOMP_RET_ALLOW; /* Make sure cross-thread synced filter points somewhere sane. */ struct seccomp_filter *f = - lockless_dereference(current->seccomp.filter); + READ_ONCE(current->seccomp.filter); /* Ensure unexpected behavior doesn't result in failing open. */ if (unlikely(WARN_ON(f == NULL))) diff --git a/kernel/task_work.c b/kernel/task_work.c index 836a72a66fba..9a9f262fc53d 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -67,7 +67,7 @@ task_work_cancel(struct task_struct *task, task_work_func_t func) * we raced with task_work_run(), *pprev == NULL/exited. */ raw_spin_lock_irqsave(&task->pi_lock, flags); - while ((work = lockless_dereference(*pprev))) { + while ((work = READ_ONCE(*pprev))) { if (work->func != func) pprev = &work->next; else if (cmpxchg(pprev, work, work->next) == work) diff --git a/mm/slab.h b/mm/slab.h index 073362816acc..8894f811a89d 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -258,7 +258,7 @@ cache_from_memcg_idx(struct kmem_cache *s, int idx) * memcg_caches issues a write barrier to match this (see * memcg_create_kmem_cache()). */ - cachep = lockless_dereference(arr->entries[idx]); + cachep = READ_ONCE(arr->entries[idx]); rcu_read_unlock(); return cachep; -- cgit v1.2.3 From 59ecbbe7b31cd2d86ff9a9f461a00f7e7533aedc Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 24 Oct 2017 11:22:49 +0100 Subject: locking/barriers: Kill lockless_dereference() lockless_dereference() is a nice idea, but it gained little traction in kernel code since its introduction three years ago. This is partly because it's a pain to type, but also because using READ_ONCE() instead has worked correctly on all architectures apart from Alpha, which is a fully supported but somewhat niche architecture these days. Now that READ_ONCE() has been upgraded to contain an implicit smp_read_barrier_depends() and the few callers of lockless_dereference() have been converted, we can remove lockless_dereference() altogether. Signed-off-by: Will Deacon Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1508840570-22169-5-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar --- Documentation/memory-barriers.txt | 12 ------------ Documentation/translations/ko_KR/memory-barriers.txt | 12 ------------ include/linux/compiler.h | 20 -------------------- 3 files changed, 44 deletions(-) (limited to 'include/linux') diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index b759a60624fd..470a682f3fa4 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -1886,18 +1886,6 @@ There are some more advanced barrier functions: See Documentation/atomic_{t,bitops}.txt for more information. - (*) lockless_dereference(); - - This can be thought of as a pointer-fetch wrapper around the - smp_read_barrier_depends() data-dependency barrier. - - This is also similar to rcu_dereference(), but in cases where - object lifetime is handled by some mechanism other than RCU, for - example, when the objects removed only when the system goes down. - In addition, lockless_dereference() is used in some data structures - that can be used both with and without RCU. - - (*) dma_wmb(); (*) dma_rmb(); diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt index a7a813258013..ec3b46e27b7a 100644 --- a/Documentation/translations/ko_KR/memory-barriers.txt +++ b/Documentation/translations/ko_KR/memory-barriers.txt @@ -1858,18 +1858,6 @@ Mandatory 배리어들은 SMP 시스템에서도 UP 시스템에서도 SMP 효 참고하세요. - (*) lockless_dereference(); - - 이 함수는 smp_read_barrier_depends() 데이터 의존성 배리어를 사용하는 - 포인터 읽어오기 래퍼(wrapper) 함수로 생각될 수 있습니다. - - 객체의 라이프타임이 RCU 외의 메커니즘으로 관리된다는 점을 제외하면 - rcu_dereference() 와도 유사한데, 예를 들면 객체가 시스템이 꺼질 때에만 - 제거되는 경우 등입니다. 또한, lockless_dereference() 은 RCU 와 함께 - 사용될수도, RCU 없이 사용될 수도 있는 일부 데이터 구조에 사용되고 - 있습니다. - - (*) dma_wmb(); (*) dma_rmb(); diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 7d7b77da9716..5a1cab48442c 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -346,24 +346,4 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s (volatile typeof(x) *)&(x); }) #define ACCESS_ONCE(x) (*__ACCESS_ONCE(x)) -/** - * lockless_dereference() - safely load a pointer for later dereference - * @p: The pointer to load - * - * Similar to rcu_dereference(), but for situations where the pointed-to - * object's lifetime is managed by something other than RCU. That - * "something other" might be reference counting or simple immortality. - * - * The seemingly unused variable ___typecheck_p validates that @p is - * indeed a pointer type by using a pointer to typeof(*p) as the type. - * Taking a pointer to typeof(*p) again is needed in case p is void *. - */ -#define lockless_dereference(p) \ -({ \ - typeof(p) _________p1 = READ_ONCE(p); \ - typeof(*(p)) *___typecheck_p __maybe_unused; \ - smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ - (_________p1); \ -}) - #endif /* __LINUX_COMPILER_H */ -- cgit v1.2.3 From 4df714be4dcf40bfb0d4af0f851a6e1977afa02e Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 12 Oct 2017 13:20:48 +0100 Subject: locking/atomic: Add atomic_cond_read_acquire() smp_cond_load_acquire() provides a way to spin on a variable with acquire semantics until some conditional expression involving the variable is satisfied. Architectures such as arm64 can potentially enter a low-power state, waking up only when the value of the variable changes, which reduces the system impact of tight polling loops. This patch makes the same interface available to users of atomic_t, atomic64_t and atomic_long_t, rather than require messy accesses to the structure internals. Signed-off-by: Will Deacon Acked-by: Peter Zijlstra Cc: Boqun Feng Cc: Jeremy.Linton@arm.com Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Thomas Gleixner Cc: Waiman Long Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1507810851-306-3-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar --- include/asm-generic/atomic-long.h | 3 +++ include/linux/atomic.h | 4 ++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h index 288cc9e96395..f2d97b782031 100644 --- a/include/asm-generic/atomic-long.h +++ b/include/asm-generic/atomic-long.h @@ -243,4 +243,7 @@ static inline long atomic_long_add_unless(atomic_long_t *l, long a, long u) #define atomic_long_inc_not_zero(l) \ ATOMIC_LONG_PFX(_inc_not_zero)((ATOMIC_LONG_PFX(_t) *)(l)) +#define atomic_long_cond_read_acquire(v, c) \ + ATOMIC_LONG_PFX(_cond_read_acquire)((ATOMIC_LONG_PFX(_t) *)(v), (c)) + #endif /* _ASM_GENERIC_ATOMIC_LONG_H */ diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 40d6bfec0e0d..0aeb2b3f4578 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -653,6 +653,8 @@ static inline int atomic_dec_if_positive(atomic_t *v) } #endif +#define atomic_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) + #ifdef CONFIG_GENERIC_ATOMIC64 #include #endif @@ -1072,6 +1074,8 @@ static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v } #endif +#define atomic64_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) + #include #endif /* _LINUX_ATOMIC_H */ -- cgit v1.2.3 From 66702eb59064f1077e89cce8e7e3cd48ec4b486c Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 23 Oct 2017 14:07:14 -0700 Subject: locking/atomics, fs/dcache: Convert ACCESS_ONCE() to READ_ONCE()/WRITE_ONCE() For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't currently harmful. However, for some features it is necessary to instrument reads and writes separately, which is not possible with ACCESS_ONCE(). This distinction is critical to correct operation. It's possible to transform the bulk of kernel code using the Coccinelle script below. However, this doesn't handle comments, leaving references to ACCESS_ONCE() instances which have been removed. As a preparatory step, this patch converts the dcache code and comments to use {READ,WRITE}_ONCE() consistently. ---- virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland Signed-off-by: Paul E. McKenney Cc: Al Viro Cc: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: davem@davemloft.net Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-4-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- fs/dcache.c | 18 +++++++++--------- include/linux/dcache.h | 4 ++-- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/fs/dcache.c b/fs/dcache.c index 34c852af215c..bcc9f6981569 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -630,7 +630,7 @@ static inline struct dentry *lock_parent(struct dentry *dentry) rcu_read_lock(); spin_unlock(&dentry->d_lock); again: - parent = ACCESS_ONCE(dentry->d_parent); + parent = READ_ONCE(dentry->d_parent); spin_lock(&parent->d_lock); /* * We can't blindly lock dentry until we are sure @@ -721,7 +721,7 @@ static inline bool fast_dput(struct dentry *dentry) * around with a zero refcount. */ smp_rmb(); - d_flags = ACCESS_ONCE(dentry->d_flags); + d_flags = READ_ONCE(dentry->d_flags); d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST | DCACHE_DISCONNECTED; /* Nothing to do? Dropping the reference was all we needed? */ @@ -850,11 +850,11 @@ struct dentry *dget_parent(struct dentry *dentry) * locking. */ rcu_read_lock(); - ret = ACCESS_ONCE(dentry->d_parent); + ret = READ_ONCE(dentry->d_parent); gotref = lockref_get_not_zero(&ret->d_lockref); rcu_read_unlock(); if (likely(gotref)) { - if (likely(ret == ACCESS_ONCE(dentry->d_parent))) + if (likely(ret == READ_ONCE(dentry->d_parent))) return ret; dput(ret); } @@ -3040,7 +3040,7 @@ static int prepend(char **buffer, int *buflen, const char *str, int namelen) * @buflen: allocated length of the buffer * @name: name string and length qstr structure * - * With RCU path tracing, it may race with d_move(). Use ACCESS_ONCE() to + * With RCU path tracing, it may race with d_move(). Use READ_ONCE() to * make sure that either the old or the new name pointer and length are * fetched. However, there may be mismatch between length and pointer. * The length cannot be trusted, we need to copy it byte-by-byte until @@ -3054,8 +3054,8 @@ static int prepend(char **buffer, int *buflen, const char *str, int namelen) */ static int prepend_name(char **buffer, int *buflen, const struct qstr *name) { - const char *dname = ACCESS_ONCE(name->name); - u32 dlen = ACCESS_ONCE(name->len); + const char *dname = READ_ONCE(name->name); + u32 dlen = READ_ONCE(name->len); char *p; smp_read_barrier_depends(); @@ -3120,7 +3120,7 @@ restart: struct dentry * parent; if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) { - struct mount *parent = ACCESS_ONCE(mnt->mnt_parent); + struct mount *parent = READ_ONCE(mnt->mnt_parent); /* Escaped? */ if (dentry != vfsmnt->mnt_root) { bptr = *buffer; @@ -3130,7 +3130,7 @@ restart: } /* Global root? */ if (mnt != parent) { - dentry = ACCESS_ONCE(mnt->mnt_mountpoint); + dentry = READ_ONCE(mnt->mnt_mountpoint); mnt = parent; vfsmnt = &mnt->mnt; continue; diff --git a/include/linux/dcache.h b/include/linux/dcache.h index ed1a7cf6923a..1d8f5818f647 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -519,7 +519,7 @@ static inline struct inode *d_inode(const struct dentry *dentry) } /** - * d_inode_rcu - Get the actual inode of this dentry with ACCESS_ONCE() + * d_inode_rcu - Get the actual inode of this dentry with READ_ONCE() * @dentry: The dentry to query * * This is the helper normal filesystems should use to get at their own inodes @@ -527,7 +527,7 @@ static inline struct inode *d_inode(const struct dentry *dentry) */ static inline struct inode *d_inode_rcu(const struct dentry *dentry) { - return ACCESS_ONCE(dentry->d_inode); + return READ_ONCE(dentry->d_inode); } /** -- cgit v1.2.3 From 14cd5d4a0125f643350e7fa12f5384f1fc2d3e9d Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 23 Oct 2017 14:07:17 -0700 Subject: locking/atomics, net/netlink/netfilter: Convert ACCESS_ONCE() to READ_ONCE()/WRITE_ONCE() For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't currently harmful. However, for some features it is necessary to instrument reads and writes separately, which is not possible with ACCESS_ONCE(). This distinction is critical to correct operation. It's possible to transform the bulk of kernel code using the Coccinelle script below. However, this doesn't handle comments, leaving references to ACCESS_ONCE() instances which have been removed. As a preparatory step, this patch converts netlink and netfilter code and comments to use {READ,WRITE}_ONCE() consistently. ---- virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland Signed-off-by: Paul E. McKenney Cc: David S. Miller Cc: Florian Westphal Cc: Jozsef Kadlecsik Cc: Linus Torvalds Cc: Pablo Neira Ayuso Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-7-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/linux/genetlink.h | 2 +- include/linux/netfilter/nfnetlink.h | 2 +- include/linux/rtnetlink.h | 2 +- include/net/netfilter/nf_tables.h | 4 ++-- net/netfilter/ipvs/ip_vs_sync.c | 2 +- net/netfilter/nfnetlink_queue.c | 4 ++-- 6 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h index a4c61cbce777..0e694cf62414 100644 --- a/include/linux/genetlink.h +++ b/include/linux/genetlink.h @@ -30,7 +30,7 @@ extern wait_queue_head_t genl_sk_destructing_waitq; * @p: The pointer to read, prior to dereferencing * * Return the value of the specified RCU-protected pointer, but omit - * both the smp_read_barrier_depends() and the ACCESS_ONCE(), because + * both the smp_read_barrier_depends() and the READ_ONCE(), because * caller holds genl mutex. */ #define genl_dereference(p) \ diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 41d04e9d088a..0f47a4aa7fc4 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -66,7 +66,7 @@ static inline bool lockdep_nfnl_is_held(__u8 subsys_id) * @ss: The nfnetlink subsystem ID * * Return the value of the specified RCU-protected pointer, but omit - * both the smp_read_barrier_depends() and the ACCESS_ONCE(), because + * both the smp_read_barrier_depends() and the READ_ONCE(), because * caller holds the NFNL subsystem mutex. */ #define nfnl_dereference(p, ss) \ diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index dea59c8eec54..765f7b915475 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -67,7 +67,7 @@ static inline bool lockdep_rtnl_is_held(void) * @p: The pointer to read, prior to dereferencing * * Return the value of the specified RCU-protected pointer, but omit - * both the smp_read_barrier_depends() and the ACCESS_ONCE(), because + * both the smp_read_barrier_depends() and the READ_ONCE(), because * caller holds RTNL. */ #define rtnl_dereference(p) \ diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 0f5b12a4ad09..5c68e279eaea 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1164,8 +1164,8 @@ static inline u8 nft_genmask_next(const struct net *net) static inline u8 nft_genmask_cur(const struct net *net) { - /* Use ACCESS_ONCE() to prevent refetching the value for atomicity */ - return 1 << ACCESS_ONCE(net->nft.gencursor); + /* Use READ_ONCE() to prevent refetching the value for atomicity */ + return 1 << READ_ONCE(net->nft.gencursor); } #define NFT_GENMASK_ANY ((1 << 0) | (1 << 1)) diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 0e5b64a75da0..1cfffd42d1e2 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -457,7 +457,7 @@ static inline bool in_persistence(struct ip_vs_conn *cp) static int ip_vs_sync_conn_needed(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts) { - unsigned long orig = ACCESS_ONCE(cp->sync_endtime); + unsigned long orig = READ_ONCE(cp->sync_endtime); unsigned long now = jiffies; unsigned long n = (now + cp->timeout) & ~3UL; unsigned int sync_refresh_period; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index c9796629858f..a16356cacec3 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -401,7 +401,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, outdev = entry->state.out; - switch ((enum nfqnl_config_mode)ACCESS_ONCE(queue->copy_mode)) { + switch ((enum nfqnl_config_mode)READ_ONCE(queue->copy_mode)) { case NFQNL_COPY_META: case NFQNL_COPY_NONE: break; @@ -412,7 +412,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, skb_checksum_help(entskb)) return NULL; - data_len = ACCESS_ONCE(queue->copy_range); + data_len = READ_ONCE(queue->copy_range); if (data_len > entskb->len) data_len = entskb->len; -- cgit v1.2.3 From ef4d9af62f47e3070b00c3307a4d8eb5092bb9a2 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 23 Oct 2017 14:07:19 -0700 Subject: locking/atomics, net/average: Convert ACCESS_ONCE() to READ_ONCE()/WRITE_ONCE() For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't currently harmful. However, for some features it is necessary to instrument reads and writes separately, which is not possible with ACCESS_ONCE(). This distinction is critical to correct operation. It's possible to transform the bulk of kernel code using the Coccinelle script below. However, this doesn't pick up some uses, including those in . As a preparatory step, this patch converts the file to use {READ,WRITE}_ONCE() consistently. At the same time, this patch addds missing includes necessary for {READ,WRITE}_ONCE(), *BUG_ON*(), and ilog2(). ---- virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland Signed-off-by: Paul E. McKenney Reviewed-by: Johannes Berg Cc: David S. Miller Cc: Johannes Berg Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-9-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/linux/average.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/average.h b/include/linux/average.h index 7ddaf340d2ac..3f462292269c 100644 --- a/include/linux/average.h +++ b/include/linux/average.h @@ -1,6 +1,10 @@ #ifndef _LINUX_AVERAGE_H #define _LINUX_AVERAGE_H +#include +#include +#include + /* * Exponentially weighted moving average (EWMA) * @@ -48,7 +52,7 @@ static inline void ewma_##name##_add(struct ewma_##name *e, \ unsigned long val) \ { \ - unsigned long internal = ACCESS_ONCE(e->internal); \ + unsigned long internal = READ_ONCE(e->internal); \ unsigned long weight_rcp = ilog2(_weight_rcp); \ unsigned long precision = _precision; \ \ @@ -57,10 +61,10 @@ BUILD_BUG_ON((_precision) > 30); \ BUILD_BUG_ON_NOT_POWER_OF_2(_weight_rcp); \ \ - ACCESS_ONCE(e->internal) = internal ? \ + WRITE_ONCE(e->internal, internal ? \ (((internal << weight_rcp) - internal) + \ (val << precision)) >> weight_rcp : \ - (val << precision); \ + (val << precision)); \ } #endif /* _LINUX_AVERAGE_H */ -- cgit v1.2.3 From 6aa7de059173a986114ac43b8f50b297a86f09a8 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 23 Oct 2017 14:07:29 -0700 Subject: locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE() Please do not apply this to mainline directly, instead please re-run the coccinelle script shown below and apply its output. For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't harmful, and changing them results in churn. However, for some features, the read/write distinction is critical to correct operation. To distinguish these cases, separate read/write accessors must be used. This patch migrates (most) remaining ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following coccinelle script: ---- // Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and // WRITE_ONCE() // $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland Signed-off-by: Paul E. McKenney Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: davem@davemloft.net Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- arch/arc/kernel/smp.c | 2 +- arch/arm/include/asm/spinlock.h | 2 +- arch/arm/mach-tegra/cpuidle-tegra20.c | 2 +- arch/arm/vdso/vgettimeofday.c | 2 +- arch/ia64/include/asm/spinlock.h | 8 ++--- arch/mips/include/asm/vdso.h | 2 +- arch/mips/kernel/pm-cps.c | 2 +- arch/mn10300/kernel/mn10300-serial.c | 4 +-- arch/parisc/include/asm/atomic.h | 2 +- arch/powerpc/platforms/powernv/opal-msglog.c | 2 +- arch/s390/include/asm/spinlock.h | 6 ++-- arch/s390/lib/spinlock.c | 16 +++++----- arch/sparc/include/asm/atomic_32.h | 2 +- arch/tile/gxio/dma_queue.c | 4 +-- arch/tile/include/gxio/dma_queue.h | 2 +- arch/tile/kernel/ptrace.c | 2 +- arch/x86/entry/common.c | 2 +- arch/x86/entry/vdso/vclock_gettime.c | 2 +- arch/x86/events/core.c | 2 +- arch/x86/include/asm/vgtod.h | 2 +- arch/x86/kernel/espfix_64.c | 6 ++-- arch/x86/kernel/nmi.c | 2 +- arch/x86/kvm/mmu.c | 4 +-- arch/x86/kvm/page_track.c | 2 +- arch/x86/xen/p2m.c | 2 +- arch/xtensa/platforms/xtfpga/lcd.c | 14 ++++----- block/blk-wbt.c | 2 +- drivers/base/core.c | 2 +- drivers/base/power/runtime.c | 4 +-- drivers/char/random.c | 4 +-- drivers/clocksource/bcm2835_timer.c | 2 +- drivers/crypto/caam/jr.c | 4 +-- drivers/crypto/nx/nx-842-powernv.c | 2 +- drivers/firewire/ohci.c | 10 +++--- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 4 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 4 +-- drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 2 +- drivers/gpu/drm/radeon/radeon_gem.c | 4 +-- drivers/gpu/drm/vmwgfx/vmwgfx_surface.c | 2 +- drivers/infiniband/hw/hfi1/file_ops.c | 2 +- drivers/infiniband/hw/hfi1/pio.c | 6 ++-- drivers/infiniband/hw/hfi1/ruc.c | 2 +- drivers/infiniband/hw/hfi1/sdma.c | 8 ++--- drivers/infiniband/hw/hfi1/sdma.h | 2 +- drivers/infiniband/hw/hfi1/uc.c | 4 +-- drivers/infiniband/hw/hfi1/ud.c | 4 +-- drivers/infiniband/hw/hfi1/user_sdma.c | 8 ++--- drivers/infiniband/hw/qib/qib_ruc.c | 2 +- drivers/infiniband/hw/qib/qib_uc.c | 4 +-- drivers/infiniband/hw/qib/qib_ud.c | 4 +-- drivers/infiniband/sw/rdmavt/qp.c | 6 ++-- drivers/input/misc/regulator-haptic.c | 2 +- drivers/md/dm-bufio.c | 10 +++--- drivers/md/dm-kcopyd.c | 4 +-- drivers/md/dm-stats.c | 36 +++++++++++----------- drivers/md/dm-switch.c | 2 +- drivers/md/dm-thin.c | 2 +- drivers/md/dm-verity-target.c | 2 +- drivers/md/dm.c | 4 +-- drivers/md/md.c | 2 +- drivers/md/raid5.c | 2 +- drivers/misc/mic/scif/scif_rb.c | 8 ++--- drivers/misc/mic/scif/scif_rma_list.c | 2 +- drivers/net/bonding/bond_alb.c | 2 +- drivers/net/bonding/bond_main.c | 6 ++-- drivers/net/ethernet/chelsio/cxgb4/sge.c | 4 +-- drivers/net/ethernet/emulex/benet/be_main.c | 2 +- drivers/net/ethernet/hisilicon/hip04_eth.c | 4 +-- drivers/net/ethernet/intel/i40e/i40e_debugfs.c | 4 +-- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 4 +-- drivers/net/ethernet/intel/i40e/i40e_ptp.c | 4 +-- drivers/net/ethernet/intel/igb/e1000_regs.h | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_common.h | 4 +-- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 8 ++--- drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c | 4 +-- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 2 +- drivers/net/ethernet/intel/ixgbevf/vf.h | 2 +- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 12 ++++---- drivers/net/ethernet/neterion/vxge/vxge-main.c | 2 +- drivers/net/ethernet/sfc/ef10.c | 10 +++--- drivers/net/ethernet/sfc/efx.c | 4 +-- drivers/net/ethernet/sfc/falcon/efx.c | 4 +-- drivers/net/ethernet/sfc/falcon/falcon.c | 4 +-- drivers/net/ethernet/sfc/falcon/farch.c | 8 ++--- drivers/net/ethernet/sfc/falcon/nic.h | 6 ++-- drivers/net/ethernet/sfc/falcon/tx.c | 6 ++-- drivers/net/ethernet/sfc/farch.c | 8 ++--- drivers/net/ethernet/sfc/nic.h | 6 ++-- drivers/net/ethernet/sfc/ptp.c | 10 +++--- drivers/net/ethernet/sfc/tx.c | 6 ++-- drivers/net/ethernet/sun/niu.c | 4 +-- drivers/net/tap.c | 2 +- drivers/net/tun.c | 4 +-- drivers/net/wireless/ath/ath5k/desc.c | 8 ++--- .../wireless/broadcom/brcm80211/brcmfmac/sdio.c | 2 +- drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 2 +- drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 4 +-- drivers/net/wireless/intel/iwlwifi/pcie/rx.c | 2 +- drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 10 +++--- drivers/net/wireless/mac80211_hwsim.c | 4 +-- drivers/scsi/qla2xxx/qla_target.c | 2 +- drivers/target/target_core_user.c | 2 +- drivers/usb/class/cdc-wdm.c | 2 +- drivers/usb/core/devio.c | 2 +- drivers/usb/core/sysfs.c | 4 +-- drivers/usb/gadget/udc/gr_udc.c | 4 +-- drivers/usb/host/ohci-hcd.c | 2 +- drivers/usb/host/uhci-hcd.h | 4 +-- drivers/vfio/vfio.c | 2 +- drivers/vhost/scsi.c | 2 +- fs/aio.c | 2 +- fs/buffer.c | 3 +- fs/crypto/keyinfo.c | 2 +- fs/direct-io.c | 2 +- fs/exec.c | 2 +- fs/fcntl.c | 2 +- fs/fs_pin.c | 4 +-- fs/fuse/dev.c | 2 +- fs/inode.c | 2 +- fs/namei.c | 4 +-- fs/namespace.c | 2 +- fs/nfs/dir.c | 8 ++--- fs/proc/array.c | 2 +- fs/proc_namespace.c | 2 +- fs/splice.c | 2 +- fs/userfaultfd.c | 8 ++--- fs/xfs/xfs_log_priv.h | 4 +-- include/linux/bitops.h | 4 +-- include/linux/dynamic_queue_limits.h | 2 +- include/linux/huge_mm.h | 2 +- include/linux/if_team.h | 2 +- include/linux/llist.h | 2 +- include/linux/pm_runtime.h | 2 +- include/net/ip_vs.h | 6 ++-- kernel/acct.c | 4 +-- kernel/events/core.c | 6 ++-- kernel/events/ring_buffer.c | 2 +- kernel/exit.c | 2 +- kernel/trace/ring_buffer.c | 2 +- kernel/trace/trace.h | 2 +- kernel/trace/trace_stack.c | 2 +- kernel/user_namespace.c | 2 +- lib/assoc_array.c | 20 ++++++------ lib/dynamic_queue_limits.c | 2 +- lib/llist.c | 2 +- lib/vsprintf.c | 4 +-- mm/huge_memory.c | 2 +- net/core/dev.c | 2 +- net/core/pktgen.c | 2 +- net/ipv4/inet_fragment.c | 2 +- net/ipv4/route.c | 2 +- net/ipv4/tcp_output.c | 2 +- net/ipv4/udp.c | 4 +-- net/ipv6/ip6_tunnel.c | 8 ++--- net/ipv6/udp.c | 4 +-- net/llc/llc_input.c | 4 +-- net/mac80211/sta_info.c | 2 +- net/netlabel/netlabel_calipso.c | 2 +- net/wireless/nl80211.c | 2 +- sound/firewire/amdtp-am824.c | 6 ++-- sound/firewire/amdtp-stream.c | 23 +++++++------- sound/firewire/amdtp-stream.h | 2 +- sound/firewire/digi00x/amdtp-dot.c | 6 ++-- sound/firewire/fireface/amdtp-ff.c | 4 +-- sound/firewire/fireface/ff-midi.c | 10 +++--- sound/firewire/fireface/ff-transaction.c | 8 ++--- sound/firewire/isight.c | 18 +++++------ sound/firewire/motu/amdtp-motu.c | 4 +-- sound/firewire/oxfw/oxfw-scs1x.c | 12 ++++---- sound/firewire/tascam/amdtp-tascam.c | 4 +-- sound/firewire/tascam/tascam-transaction.c | 6 ++-- sound/soc/xtensa/xtfpga-i2s.c | 6 ++-- sound/usb/bcd2000/bcd2000.c | 4 +-- tools/arch/x86/include/asm/atomic.h | 2 +- tools/include/asm-generic/atomic-gcc.h | 2 +- tools/perf/util/auxtrace.h | 4 +-- tools/perf/util/session.h | 2 +- virt/kvm/kvm_main.c | 2 +- 180 files changed, 383 insertions(+), 385 deletions(-) (limited to 'include/linux') diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index f46267153ec2..94cabe73664b 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -245,7 +245,7 @@ static void ipi_send_msg_one(int cpu, enum ipi_msg_type msg) * and read back old value */ do { - new = old = ACCESS_ONCE(*ipi_data_ptr); + new = old = READ_ONCE(*ipi_data_ptr); new |= 1U << msg; } while (cmpxchg(ipi_data_ptr, old, new) != old); diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index daa87212c9a1..77f50ae0aeb4 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -71,7 +71,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) while (lockval.tickets.next != lockval.tickets.owner) { wfe(); - lockval.tickets.owner = ACCESS_ONCE(lock->tickets.owner); + lockval.tickets.owner = READ_ONCE(lock->tickets.owner); } smp_mb(); diff --git a/arch/arm/mach-tegra/cpuidle-tegra20.c b/arch/arm/mach-tegra/cpuidle-tegra20.c index 76e4c83cd5c8..3f24addd7972 100644 --- a/arch/arm/mach-tegra/cpuidle-tegra20.c +++ b/arch/arm/mach-tegra/cpuidle-tegra20.c @@ -179,7 +179,7 @@ static int tegra20_idle_lp2_coupled(struct cpuidle_device *dev, bool entered_lp2 = false; if (tegra_pending_sgi()) - ACCESS_ONCE(abort_flag) = true; + WRITE_ONCE(abort_flag, true); cpuidle_coupled_parallel_barrier(dev, &abort_barrier); diff --git a/arch/arm/vdso/vgettimeofday.c b/arch/arm/vdso/vgettimeofday.c index 79214d5ff097..a9dd619c6c29 100644 --- a/arch/arm/vdso/vgettimeofday.c +++ b/arch/arm/vdso/vgettimeofday.c @@ -35,7 +35,7 @@ static notrace u32 __vdso_read_begin(const struct vdso_data *vdata) { u32 seq; repeat: - seq = ACCESS_ONCE(vdata->seq_count); + seq = READ_ONCE(vdata->seq_count); if (seq & 1) { cpu_relax(); goto repeat; diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h index 35b31884863b..e98775be112d 100644 --- a/arch/ia64/include/asm/spinlock.h +++ b/arch/ia64/include/asm/spinlock.h @@ -61,7 +61,7 @@ static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock) static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock) { - int tmp = ACCESS_ONCE(lock->lock); + int tmp = READ_ONCE(lock->lock); if (!(((tmp >> TICKET_SHIFT) ^ tmp) & TICKET_MASK)) return ia64_cmpxchg(acq, &lock->lock, tmp, tmp + 1, sizeof (tmp)) == tmp; @@ -73,19 +73,19 @@ static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) unsigned short *p = (unsigned short *)&lock->lock + 1, tmp; asm volatile ("ld2.bias %0=[%1]" : "=r"(tmp) : "r"(p)); - ACCESS_ONCE(*p) = (tmp + 2) & ~1; + WRITE_ONCE(*p, (tmp + 2) & ~1); } static inline int __ticket_spin_is_locked(arch_spinlock_t *lock) { - long tmp = ACCESS_ONCE(lock->lock); + long tmp = READ_ONCE(lock->lock); return !!(((tmp >> TICKET_SHIFT) ^ tmp) & TICKET_MASK); } static inline int __ticket_spin_is_contended(arch_spinlock_t *lock) { - long tmp = ACCESS_ONCE(lock->lock); + long tmp = READ_ONCE(lock->lock); return ((tmp - (tmp >> TICKET_SHIFT)) & TICKET_MASK) > 1; } diff --git a/arch/mips/include/asm/vdso.h b/arch/mips/include/asm/vdso.h index b7cd6cf77b83..91bf0c2c265c 100644 --- a/arch/mips/include/asm/vdso.h +++ b/arch/mips/include/asm/vdso.h @@ -99,7 +99,7 @@ static inline u32 vdso_data_read_begin(const union mips_vdso_data *data) u32 seq; while (true) { - seq = ACCESS_ONCE(data->seq_count); + seq = READ_ONCE(data->seq_count); if (likely(!(seq & 1))) { /* Paired with smp_wmb() in vdso_data_write_*(). */ smp_rmb(); diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c index 4655017f2377..1d2996cd58da 100644 --- a/arch/mips/kernel/pm-cps.c +++ b/arch/mips/kernel/pm-cps.c @@ -166,7 +166,7 @@ int cps_pm_enter_state(enum cps_pm_state state) nc_core_ready_count = nc_addr; /* Ensure ready_count is zero-initialised before the assembly runs */ - ACCESS_ONCE(*nc_core_ready_count) = 0; + WRITE_ONCE(*nc_core_ready_count, 0); coupled_barrier(&per_cpu(pm_barrier, core), online); /* Run the generated entry code */ diff --git a/arch/mn10300/kernel/mn10300-serial.c b/arch/mn10300/kernel/mn10300-serial.c index 7ecf69879e2d..d7ef1232a82a 100644 --- a/arch/mn10300/kernel/mn10300-serial.c +++ b/arch/mn10300/kernel/mn10300-serial.c @@ -543,7 +543,7 @@ static void mn10300_serial_receive_interrupt(struct mn10300_serial_port *port) try_again: /* pull chars out of the hat */ - ix = ACCESS_ONCE(port->rx_outp); + ix = READ_ONCE(port->rx_outp); if (CIRC_CNT(port->rx_inp, ix, MNSC_BUFFER_SIZE) == 0) { if (push && !tport->low_latency) tty_flip_buffer_push(tport); @@ -1724,7 +1724,7 @@ static int mn10300_serial_poll_get_char(struct uart_port *_port) if (mn10300_serial_int_tbl[port->rx_irq].port != NULL) { do { /* pull chars out of the hat */ - ix = ACCESS_ONCE(port->rx_outp); + ix = READ_ONCE(port->rx_outp); if (CIRC_CNT(port->rx_inp, ix, MNSC_BUFFER_SIZE) == 0) return NO_POLL_CHAR; diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 17b98a87e5e2..c57d4e8307f2 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -260,7 +260,7 @@ atomic64_set(atomic64_t *v, s64 i) static __inline__ s64 atomic64_read(const atomic64_t *v) { - return ACCESS_ONCE((v)->counter); + return READ_ONCE((v)->counter); } #define atomic64_inc(v) (atomic64_add( 1,(v))) diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c index 7a9cde0cfbd1..acd3206dfae3 100644 --- a/arch/powerpc/platforms/powernv/opal-msglog.c +++ b/arch/powerpc/platforms/powernv/opal-msglog.c @@ -43,7 +43,7 @@ ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count) if (!opal_memcons) return -ENODEV; - out_pos = be32_to_cpu(ACCESS_ONCE(opal_memcons->out_pos)); + out_pos = be32_to_cpu(READ_ONCE(opal_memcons->out_pos)); /* Now we've read out_pos, put a barrier in before reading the new * data it points to in conbuf. */ diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 9fa855f91e55..66f4160010ef 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -117,14 +117,14 @@ extern int _raw_write_trylock_retry(arch_rwlock_t *lp); static inline int arch_read_trylock_once(arch_rwlock_t *rw) { - int old = ACCESS_ONCE(rw->lock); + int old = READ_ONCE(rw->lock); return likely(old >= 0 && __atomic_cmpxchg_bool(&rw->lock, old, old + 1)); } static inline int arch_write_trylock_once(arch_rwlock_t *rw) { - int old = ACCESS_ONCE(rw->lock); + int old = READ_ONCE(rw->lock); return likely(old == 0 && __atomic_cmpxchg_bool(&rw->lock, 0, 0x80000000)); } @@ -211,7 +211,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw) int old; do { - old = ACCESS_ONCE(rw->lock); + old = READ_ONCE(rw->lock); } while (!__atomic_cmpxchg_bool(&rw->lock, old, old - 1)); } diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index b12663d653d8..34e30b9ea234 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -162,8 +162,8 @@ void _raw_read_lock_wait(arch_rwlock_t *rw) smp_yield_cpu(~owner); count = spin_retry; } - old = ACCESS_ONCE(rw->lock); - owner = ACCESS_ONCE(rw->owner); + old = READ_ONCE(rw->lock); + owner = READ_ONCE(rw->owner); if (old < 0) continue; if (__atomic_cmpxchg_bool(&rw->lock, old, old + 1)) @@ -178,7 +178,7 @@ int _raw_read_trylock_retry(arch_rwlock_t *rw) int old; while (count-- > 0) { - old = ACCESS_ONCE(rw->lock); + old = READ_ONCE(rw->lock); if (old < 0) continue; if (__atomic_cmpxchg_bool(&rw->lock, old, old + 1)) @@ -202,8 +202,8 @@ void _raw_write_lock_wait(arch_rwlock_t *rw, int prev) smp_yield_cpu(~owner); count = spin_retry; } - old = ACCESS_ONCE(rw->lock); - owner = ACCESS_ONCE(rw->owner); + old = READ_ONCE(rw->lock); + owner = READ_ONCE(rw->owner); smp_mb(); if (old >= 0) { prev = __RAW_LOCK(&rw->lock, 0x80000000, __RAW_OP_OR); @@ -230,8 +230,8 @@ void _raw_write_lock_wait(arch_rwlock_t *rw) smp_yield_cpu(~owner); count = spin_retry; } - old = ACCESS_ONCE(rw->lock); - owner = ACCESS_ONCE(rw->owner); + old = READ_ONCE(rw->lock); + owner = READ_ONCE(rw->owner); if (old >= 0 && __atomic_cmpxchg_bool(&rw->lock, old, old | 0x80000000)) prev = old; @@ -251,7 +251,7 @@ int _raw_write_trylock_retry(arch_rwlock_t *rw) int old; while (count-- > 0) { - old = ACCESS_ONCE(rw->lock); + old = READ_ONCE(rw->lock); if (old) continue; if (__atomic_cmpxchg_bool(&rw->lock, 0, 0x80000000)) diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index 7643e979e333..e2f398e9456c 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -31,7 +31,7 @@ void atomic_set(atomic_t *, int); #define atomic_set_release(v, i) atomic_set((v), (i)) -#define atomic_read(v) ACCESS_ONCE((v)->counter) +#define atomic_read(v) READ_ONCE((v)->counter) #define atomic_add(i, v) ((void)atomic_add_return( (int)(i), (v))) #define atomic_sub(i, v) ((void)atomic_add_return(-(int)(i), (v))) diff --git a/arch/tile/gxio/dma_queue.c b/arch/tile/gxio/dma_queue.c index baa60357f8ba..b7ba577d82ca 100644 --- a/arch/tile/gxio/dma_queue.c +++ b/arch/tile/gxio/dma_queue.c @@ -163,14 +163,14 @@ int __gxio_dma_queue_is_complete(__gxio_dma_queue_t *dma_queue, int64_t completion_slot, int update) { if (update) { - if (ACCESS_ONCE(dma_queue->hw_complete_count) > + if (READ_ONCE(dma_queue->hw_complete_count) > completion_slot) return 1; __gxio_dma_queue_update_credits(dma_queue); } - return ACCESS_ONCE(dma_queue->hw_complete_count) > completion_slot; + return READ_ONCE(dma_queue->hw_complete_count) > completion_slot; } EXPORT_SYMBOL_GPL(__gxio_dma_queue_is_complete); diff --git a/arch/tile/include/gxio/dma_queue.h b/arch/tile/include/gxio/dma_queue.h index b9e45e37649e..c8fd47edba30 100644 --- a/arch/tile/include/gxio/dma_queue.h +++ b/arch/tile/include/gxio/dma_queue.h @@ -121,7 +121,7 @@ static inline int64_t __gxio_dma_queue_reserve(__gxio_dma_queue_t *dma_queue, * if the result is LESS than "hw_complete_count". */ uint64_t complete; - complete = ACCESS_ONCE(dma_queue->hw_complete_count); + complete = READ_ONCE(dma_queue->hw_complete_count); slot |= (complete & 0xffffffffff000000); if (slot < complete) slot += 0x1000000; diff --git a/arch/tile/kernel/ptrace.c b/arch/tile/kernel/ptrace.c index e1a078e6828e..d516d61751c2 100644 --- a/arch/tile/kernel/ptrace.c +++ b/arch/tile/kernel/ptrace.c @@ -255,7 +255,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, int do_syscall_trace_enter(struct pt_regs *regs) { - u32 work = ACCESS_ONCE(current_thread_info()->flags); + u32 work = READ_ONCE(current_thread_info()->flags); if ((work & _TIF_SYSCALL_TRACE) && tracehook_report_syscall_entry(regs)) { diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 03505ffbe1b6..eaa0ba66cf96 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -75,7 +75,7 @@ static long syscall_trace_enter(struct pt_regs *regs) if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) BUG_ON(regs != task_pt_regs(current)); - work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; + work = READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; if (unlikely(work & _TIF_SYSCALL_EMU)) emulated = true; diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index fa8dbfcf7ed3..11b13c4b43d5 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -318,7 +318,7 @@ int gettimeofday(struct timeval *, struct timezone *) notrace time_t __vdso_time(time_t *t) { /* This is atomic on x86 so we don't need any locks. */ - time_t result = ACCESS_ONCE(gtod->wall_time_sec); + time_t result = READ_ONCE(gtod->wall_time_sec); if (t) *t = result; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 589af1eec7c1..140d33288e78 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2118,7 +2118,7 @@ static int x86_pmu_event_init(struct perf_event *event) event->destroy(event); } - if (ACCESS_ONCE(x86_pmu.attr_rdpmc)) + if (READ_ONCE(x86_pmu.attr_rdpmc)) event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED; return err; diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index 022e59714562..53dd162576a8 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -48,7 +48,7 @@ static inline unsigned gtod_read_begin(const struct vsyscall_gtod_data *s) unsigned ret; repeat: - ret = ACCESS_ONCE(s->seq); + ret = READ_ONCE(s->seq); if (unlikely(ret & 1)) { cpu_relax(); goto repeat; diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 9c4e7ba6870c..7d7715dde901 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -155,14 +155,14 @@ void init_espfix_ap(int cpu) page = cpu/ESPFIX_STACKS_PER_PAGE; /* Did another CPU already set this up? */ - stack_page = ACCESS_ONCE(espfix_pages[page]); + stack_page = READ_ONCE(espfix_pages[page]); if (likely(stack_page)) goto done; mutex_lock(&espfix_init_mutex); /* Did we race on the lock? */ - stack_page = ACCESS_ONCE(espfix_pages[page]); + stack_page = READ_ONCE(espfix_pages[page]); if (stack_page) goto unlock_done; @@ -200,7 +200,7 @@ void init_espfix_ap(int cpu) set_pte(&pte_p[n*PTE_STRIDE], pte); /* Job is done for this CPU and any CPU which shares this page */ - ACCESS_ONCE(espfix_pages[page]) = stack_page; + WRITE_ONCE(espfix_pages[page], stack_page); unlock_done: mutex_unlock(&espfix_init_mutex); diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 35aafc95e4b8..18bc9b51ac9b 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -105,7 +105,7 @@ static void nmi_max_handler(struct irq_work *w) { struct nmiaction *a = container_of(w, struct nmiaction, irq_work); int remainder_ns, decimal_msecs; - u64 whole_msecs = ACCESS_ONCE(a->max_duration); + u64 whole_msecs = READ_ONCE(a->max_duration); remainder_ns = do_div(whole_msecs, (1000 * 1000)); decimal_msecs = remainder_ns / 1000; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7a69cf053711..a119b361b8b7 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -443,7 +443,7 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) static u64 __get_spte_lockless(u64 *sptep) { - return ACCESS_ONCE(*sptep); + return READ_ONCE(*sptep); } #else union split_spte { @@ -4819,7 +4819,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, * If we don't have indirect shadow pages, it means no page is * write-protected, so we can exit simply. */ - if (!ACCESS_ONCE(vcpu->kvm->arch.indirect_shadow_pages)) + if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages)) return; remote_flush = local_flush = false; diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c index ea67dc876316..01c1371f39f8 100644 --- a/arch/x86/kvm/page_track.c +++ b/arch/x86/kvm/page_track.c @@ -157,7 +157,7 @@ bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn, return false; index = gfn_to_index(gfn, slot->base_gfn, PT_PAGE_TABLE_LEVEL); - return !!ACCESS_ONCE(slot->arch.gfn_track[mode][index]); + return !!READ_ONCE(slot->arch.gfn_track[mode][index]); } void kvm_page_track_cleanup(struct kvm *kvm) diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 6083ba462f35..13b4f19b9131 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -547,7 +547,7 @@ int xen_alloc_p2m_entry(unsigned long pfn) if (p2m_top_mfn && pfn < MAX_P2M_PFN) { topidx = p2m_top_index(pfn); top_mfn_p = &p2m_top_mfn[topidx]; - mid_mfn = ACCESS_ONCE(p2m_top_mfn_p[topidx]); + mid_mfn = READ_ONCE(p2m_top_mfn_p[topidx]); BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p); diff --git a/arch/xtensa/platforms/xtfpga/lcd.c b/arch/xtensa/platforms/xtfpga/lcd.c index 4dc0c1b43f4b..2f7eb66c23ec 100644 --- a/arch/xtensa/platforms/xtfpga/lcd.c +++ b/arch/xtensa/platforms/xtfpga/lcd.c @@ -34,23 +34,23 @@ static void lcd_put_byte(u8 *addr, u8 data) { #ifdef CONFIG_XTFPGA_LCD_8BIT_ACCESS - ACCESS_ONCE(*addr) = data; + WRITE_ONCE(*addr, data); #else - ACCESS_ONCE(*addr) = data & 0xf0; - ACCESS_ONCE(*addr) = (data << 4) & 0xf0; + WRITE_ONCE(*addr, data & 0xf0); + WRITE_ONCE(*addr, (data << 4) & 0xf0); #endif } static int __init lcd_init(void) { - ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT; + WRITE_ONCE(*LCD_INSTR_ADDR, LCD_DISPLAY_MODE8BIT); mdelay(5); - ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT; + WRITE_ONCE(*LCD_INSTR_ADDR, LCD_DISPLAY_MODE8BIT); udelay(200); - ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT; + WRITE_ONCE(*LCD_INSTR_ADDR, LCD_DISPLAY_MODE8BIT); udelay(50); #ifndef CONFIG_XTFPGA_LCD_8BIT_ACCESS - ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE4BIT; + WRITE_ONCE(*LCD_INSTR_ADDR, LCD_DISPLAY_MODE4BIT); udelay(50); lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_MODE4BIT); udelay(50); diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 6a9a0f03a67b..d822530e6aea 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -261,7 +261,7 @@ static inline bool stat_sample_valid(struct blk_rq_stat *stat) static u64 rwb_sync_issue_lat(struct rq_wb *rwb) { - u64 now, issue = ACCESS_ONCE(rwb->sync_issue); + u64 now, issue = READ_ONCE(rwb->sync_issue); if (!issue || !rwb->sync_cookie) return 0; diff --git a/drivers/base/core.c b/drivers/base/core.c index 12ebd055724c..4b8ba2a75a4d 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -668,7 +668,7 @@ const char *dev_driver_string(const struct device *dev) * so be careful about accessing it. dev->bus and dev->class should * never change once they are set, so they don't need special care. */ - drv = ACCESS_ONCE(dev->driver); + drv = READ_ONCE(dev->driver); return drv ? drv->name : (dev->bus ? dev->bus->name : (dev->class ? dev->class->name : "")); diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 7bcf80fa9ada..41d7c2b99f69 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -134,11 +134,11 @@ unsigned long pm_runtime_autosuspend_expiration(struct device *dev) if (!dev->power.use_autosuspend) goto out; - autosuspend_delay = ACCESS_ONCE(dev->power.autosuspend_delay); + autosuspend_delay = READ_ONCE(dev->power.autosuspend_delay); if (autosuspend_delay < 0) goto out; - last_busy = ACCESS_ONCE(dev->power.last_busy); + last_busy = READ_ONCE(dev->power.last_busy); elapsed = jiffies - last_busy; if (elapsed < 0) goto out; /* jiffies has wrapped around. */ diff --git a/drivers/char/random.c b/drivers/char/random.c index 8ad92707e45f..6c7ccac2679e 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -641,7 +641,7 @@ static void credit_entropy_bits(struct entropy_store *r, int nbits) return; retry: - entropy_count = orig = ACCESS_ONCE(r->entropy_count); + entropy_count = orig = READ_ONCE(r->entropy_count); if (nfrac < 0) { /* Debit */ entropy_count += nfrac; @@ -1265,7 +1265,7 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min, /* Can we pull enough? */ retry: - entropy_count = orig = ACCESS_ONCE(r->entropy_count); + entropy_count = orig = READ_ONCE(r->entropy_count); ibytes = nbytes; /* never pull more than available */ have_bytes = entropy_count >> (ENTROPY_SHIFT + 3); diff --git a/drivers/clocksource/bcm2835_timer.c b/drivers/clocksource/bcm2835_timer.c index 39e489a96ad7..60da2537bef9 100644 --- a/drivers/clocksource/bcm2835_timer.c +++ b/drivers/clocksource/bcm2835_timer.c @@ -71,7 +71,7 @@ static irqreturn_t bcm2835_time_interrupt(int irq, void *dev_id) if (readl_relaxed(timer->control) & timer->match_mask) { writel_relaxed(timer->match_mask, timer->control); - event_handler = ACCESS_ONCE(timer->evt.event_handler); + event_handler = READ_ONCE(timer->evt.event_handler); if (event_handler) event_handler(&timer->evt); return IRQ_HANDLED; diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c index d258953ff488..f4f258075b89 100644 --- a/drivers/crypto/caam/jr.c +++ b/drivers/crypto/caam/jr.c @@ -172,7 +172,7 @@ static void caam_jr_dequeue(unsigned long devarg) while (rd_reg32(&jrp->rregs->outring_used)) { - head = ACCESS_ONCE(jrp->head); + head = READ_ONCE(jrp->head); spin_lock(&jrp->outlock); @@ -341,7 +341,7 @@ int caam_jr_enqueue(struct device *dev, u32 *desc, spin_lock_bh(&jrp->inplock); head = jrp->head; - tail = ACCESS_ONCE(jrp->tail); + tail = READ_ONCE(jrp->tail); if (!rd_reg32(&jrp->rregs->inpring_avail) || CIRC_SPACE(head, tail, JOBR_DEPTH) <= 0) { diff --git a/drivers/crypto/nx/nx-842-powernv.c b/drivers/crypto/nx/nx-842-powernv.c index 874ddf5e9087..0f20f5ec9617 100644 --- a/drivers/crypto/nx/nx-842-powernv.c +++ b/drivers/crypto/nx/nx-842-powernv.c @@ -193,7 +193,7 @@ static int wait_for_csb(struct nx842_workmem *wmem, ktime_t start = wmem->start, now = ktime_get(); ktime_t timeout = ktime_add_ms(start, CSB_WAIT_MAX); - while (!(ACCESS_ONCE(csb->flags) & CSB_V)) { + while (!(READ_ONCE(csb->flags) & CSB_V)) { cpu_relax(); now = ktime_get(); if (ktime_after(now, timeout)) diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 8bf89267dc25..ccf52368a073 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -734,7 +734,7 @@ static unsigned int ar_search_last_active_buffer(struct ar_context *ctx, __le16 res_count, next_res_count; i = ar_first_buffer_index(ctx); - res_count = ACCESS_ONCE(ctx->descriptors[i].res_count); + res_count = READ_ONCE(ctx->descriptors[i].res_count); /* A buffer that is not yet completely filled must be the last one. */ while (i != last && res_count == 0) { @@ -742,8 +742,7 @@ static unsigned int ar_search_last_active_buffer(struct ar_context *ctx, /* Peek at the next descriptor. */ next_i = ar_next_buffer_index(i); rmb(); /* read descriptors in order */ - next_res_count = ACCESS_ONCE( - ctx->descriptors[next_i].res_count); + next_res_count = READ_ONCE(ctx->descriptors[next_i].res_count); /* * If the next descriptor is still empty, we must stop at this * descriptor. @@ -759,8 +758,7 @@ static unsigned int ar_search_last_active_buffer(struct ar_context *ctx, if (MAX_AR_PACKET_SIZE > PAGE_SIZE && i != last) { next_i = ar_next_buffer_index(next_i); rmb(); - next_res_count = ACCESS_ONCE( - ctx->descriptors[next_i].res_count); + next_res_count = READ_ONCE(ctx->descriptors[next_i].res_count); if (next_res_count != cpu_to_le16(PAGE_SIZE)) goto next_buffer_is_active; } @@ -2812,7 +2810,7 @@ static int handle_ir_buffer_fill(struct context *context, u32 buffer_dma; req_count = le16_to_cpu(last->req_count); - res_count = le16_to_cpu(ACCESS_ONCE(last->res_count)); + res_count = le16_to_cpu(READ_ONCE(last->res_count)); completed = req_count - res_count; buffer_dma = le32_to_cpu(last->data_address); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 333bad749067..303b5e099a98 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -260,7 +260,7 @@ static void amdgpu_fence_fallback(unsigned long arg) */ int amdgpu_fence_wait_empty(struct amdgpu_ring *ring) { - uint64_t seq = ACCESS_ONCE(ring->fence_drv.sync_seq); + uint64_t seq = READ_ONCE(ring->fence_drv.sync_seq); struct dma_fence *fence, **ptr; int r; @@ -300,7 +300,7 @@ unsigned amdgpu_fence_count_emitted(struct amdgpu_ring *ring) amdgpu_fence_process(ring); emitted = 0x100000000ull; emitted -= atomic_read(&ring->fence_drv.last_seq); - emitted += ACCESS_ONCE(ring->fence_drv.sync_seq); + emitted += READ_ONCE(ring->fence_drv.sync_seq); return lower_32_bits(emitted); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 7171968f261e..6149a47fe63d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -788,11 +788,11 @@ static int amdgpu_debugfs_gem_bo_info(int id, void *ptr, void *data) seq_printf(m, "\t0x%08x: %12ld byte %s", id, amdgpu_bo_size(bo), placement); - offset = ACCESS_ONCE(bo->tbo.mem.start); + offset = READ_ONCE(bo->tbo.mem.start); if (offset != AMDGPU_BO_INVALID_OFFSET) seq_printf(m, " @ 0x%010Lx", offset); - pin_count = ACCESS_ONCE(bo->pin_count); + pin_count = READ_ONCE(bo->pin_count); if (pin_count) seq_printf(m, " pin count %d", pin_count); seq_printf(m, "\n"); diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c index 38cea6fb25a8..a25f6c72f219 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c @@ -187,7 +187,7 @@ static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity) if (kfifo_is_empty(&entity->job_queue)) return false; - if (ACCESS_ONCE(entity->dependency)) + if (READ_ONCE(entity->dependency)) return false; return true; diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 3386452bd2f0..cf3deb283da5 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -451,7 +451,7 @@ int radeon_gem_busy_ioctl(struct drm_device *dev, void *data, else r = 0; - cur_placement = ACCESS_ONCE(robj->tbo.mem.mem_type); + cur_placement = READ_ONCE(robj->tbo.mem.mem_type); args->domain = radeon_mem_type_to_domain(cur_placement); drm_gem_object_put_unlocked(gobj); return r; @@ -481,7 +481,7 @@ int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data, r = ret; /* Flush HDP cache via MMIO if necessary */ - cur_placement = ACCESS_ONCE(robj->tbo.mem.mem_type); + cur_placement = READ_ONCE(robj->tbo.mem.mem_type); if (rdev->asic->mmio_hdp_flush && radeon_mem_type_to_domain(cur_placement) == RADEON_GEM_DOMAIN_VRAM) robj->rdev->asic->mmio_hdp_flush(rdev); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index a552e4ea5440..6ac094ee8983 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -904,7 +904,7 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv, if (unlikely(drm_is_render_client(file_priv))) require_exist = true; - if (ACCESS_ONCE(vmw_fpriv(file_priv)->locked_master)) { + if (READ_ONCE(vmw_fpriv(file_priv)->locked_master)) { DRM_ERROR("Locked master refused legacy " "surface reference.\n"); return -EACCES; diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index d9a1e9893136..97bea2e1aa6a 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -380,7 +380,7 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, if (sc->flags & SCF_FROZEN) { wait_event_interruptible_timeout( dd->event_queue, - !(ACCESS_ONCE(dd->flags) & HFI1_FROZEN), + !(READ_ONCE(dd->flags) & HFI1_FROZEN), msecs_to_jiffies(SEND_CTXT_HALT_TIMEOUT)); if (dd->flags & HFI1_FROZEN) return -ENOLCK; diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index 7108a4b5e94c..75e740780285 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -1423,14 +1423,14 @@ retry: goto done; } /* copy from receiver cache line and recalculate */ - sc->alloc_free = ACCESS_ONCE(sc->free); + sc->alloc_free = READ_ONCE(sc->free); avail = (unsigned long)sc->credits - (sc->fill - sc->alloc_free); if (blocks > avail) { /* still no room, actively update */ sc_release_update(sc); - sc->alloc_free = ACCESS_ONCE(sc->free); + sc->alloc_free = READ_ONCE(sc->free); trycount++; goto retry; } @@ -1667,7 +1667,7 @@ void sc_release_update(struct send_context *sc) /* call sent buffer callbacks */ code = -1; /* code not yet set */ - head = ACCESS_ONCE(sc->sr_head); /* snapshot the head */ + head = READ_ONCE(sc->sr_head); /* snapshot the head */ tail = sc->sr_tail; while (head != tail) { pbuf = &sc->sr[tail].pbuf; diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c index b3291f0fde9a..a7fc664f0d4e 100644 --- a/drivers/infiniband/hw/hfi1/ruc.c +++ b/drivers/infiniband/hw/hfi1/ruc.c @@ -363,7 +363,7 @@ static void ruc_loopback(struct rvt_qp *sqp) again: smp_read_barrier_depends(); /* see post_one_send() */ - if (sqp->s_last == ACCESS_ONCE(sqp->s_head)) + if (sqp->s_last == READ_ONCE(sqp->s_head)) goto clr_busy; wqe = rvt_get_swqe_ptr(sqp, sqp->s_last); diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 6781bcdb10b3..08346d25441c 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -1725,7 +1725,7 @@ retry: swhead = sde->descq_head & sde->sdma_mask; /* this code is really bad for cache line trading */ - swtail = ACCESS_ONCE(sde->descq_tail) & sde->sdma_mask; + swtail = READ_ONCE(sde->descq_tail) & sde->sdma_mask; cnt = sde->descq_cnt; if (swhead < swtail) @@ -1872,7 +1872,7 @@ retry: if ((status & sde->idle_mask) && !idle_check_done) { u16 swtail; - swtail = ACCESS_ONCE(sde->descq_tail) & sde->sdma_mask; + swtail = READ_ONCE(sde->descq_tail) & sde->sdma_mask; if (swtail != hwhead) { hwhead = (u16)read_sde_csr(sde, SD(HEAD)); idle_check_done = 1; @@ -2222,7 +2222,7 @@ void sdma_seqfile_dump_sde(struct seq_file *s, struct sdma_engine *sde) u16 len; head = sde->descq_head & sde->sdma_mask; - tail = ACCESS_ONCE(sde->descq_tail) & sde->sdma_mask; + tail = READ_ONCE(sde->descq_tail) & sde->sdma_mask; seq_printf(s, SDE_FMT, sde->this_idx, sde->cpu, sdma_state_name(sde->state.current_state), @@ -3305,7 +3305,7 @@ int sdma_ahg_alloc(struct sdma_engine *sde) return -EINVAL; } while (1) { - nr = ffz(ACCESS_ONCE(sde->ahg_bits)); + nr = ffz(READ_ONCE(sde->ahg_bits)); if (nr > 31) { trace_hfi1_ahg_allocate(sde, -ENOSPC); return -ENOSPC; diff --git a/drivers/infiniband/hw/hfi1/sdma.h b/drivers/infiniband/hw/hfi1/sdma.h index 107011d8613b..374c59784950 100644 --- a/drivers/infiniband/hw/hfi1/sdma.h +++ b/drivers/infiniband/hw/hfi1/sdma.h @@ -445,7 +445,7 @@ static inline u16 sdma_descq_freecnt(struct sdma_engine *sde) { return sde->descq_cnt - (sde->descq_tail - - ACCESS_ONCE(sde->descq_head)) - 1; + READ_ONCE(sde->descq_head)) - 1; } static inline u16 sdma_descq_inprocess(struct sdma_engine *sde) diff --git a/drivers/infiniband/hw/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c index 0b646173ca22..9a31c585427f 100644 --- a/drivers/infiniband/hw/hfi1/uc.c +++ b/drivers/infiniband/hw/hfi1/uc.c @@ -80,7 +80,7 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) goto bail; /* We are in the error state, flush the work request. */ smp_read_barrier_depends(); /* see post_one_send() */ - if (qp->s_last == ACCESS_ONCE(qp->s_head)) + if (qp->s_last == READ_ONCE(qp->s_head)) goto bail; /* If DMAs are in progress, we can't flush immediately. */ if (iowait_sdma_pending(&priv->s_iowait)) { @@ -121,7 +121,7 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) goto bail; /* Check if send work queue is empty. */ smp_read_barrier_depends(); /* see post_one_send() */ - if (qp->s_cur == ACCESS_ONCE(qp->s_head)) { + if (qp->s_cur == READ_ONCE(qp->s_head)) { clear_ahg(qp); goto bail; } diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c index 2ba74fdd6f15..7fec6b984e3e 100644 --- a/drivers/infiniband/hw/hfi1/ud.c +++ b/drivers/infiniband/hw/hfi1/ud.c @@ -487,7 +487,7 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) goto bail; /* We are in the error state, flush the work request. */ smp_read_barrier_depends(); /* see post_one_send */ - if (qp->s_last == ACCESS_ONCE(qp->s_head)) + if (qp->s_last == READ_ONCE(qp->s_head)) goto bail; /* If DMAs are in progress, we can't flush immediately. */ if (iowait_sdma_pending(&priv->s_iowait)) { @@ -501,7 +501,7 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) /* see post_one_send() */ smp_read_barrier_depends(); - if (qp->s_cur == ACCESS_ONCE(qp->s_head)) + if (qp->s_cur == READ_ONCE(qp->s_head)) goto bail; wqe = rvt_get_swqe_ptr(qp, qp->s_cur); diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index c0c0e0445cbf..8ec6e8a8d6f7 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -276,7 +276,7 @@ int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd, /* Wait until all requests have been freed. */ wait_event_interruptible( pq->wait, - (ACCESS_ONCE(pq->state) == SDMA_PKT_Q_INACTIVE)); + (READ_ONCE(pq->state) == SDMA_PKT_Q_INACTIVE)); kfree(pq->reqs); kfree(pq->req_in_use); kmem_cache_destroy(pq->txreq_cache); @@ -591,7 +591,7 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, if (ret != -EBUSY) { req->status = ret; WRITE_ONCE(req->has_error, 1); - if (ACCESS_ONCE(req->seqcomp) == + if (READ_ONCE(req->seqcomp) == req->seqsubmitted - 1) goto free_req; return ret; @@ -825,7 +825,7 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts) */ if (req->data_len) { iovec = &req->iovs[req->iov_idx]; - if (ACCESS_ONCE(iovec->offset) == iovec->iov.iov_len) { + if (READ_ONCE(iovec->offset) == iovec->iov.iov_len) { if (++req->iov_idx == req->data_iovs) { ret = -EFAULT; goto free_txreq; @@ -1390,7 +1390,7 @@ static void user_sdma_txreq_cb(struct sdma_txreq *txreq, int status) } else { if (status != SDMA_TXREQ_S_OK) req->status = status; - if (req->seqcomp == (ACCESS_ONCE(req->seqsubmitted) - 1) && + if (req->seqcomp == (READ_ONCE(req->seqsubmitted) - 1) && (READ_ONCE(req->done) || READ_ONCE(req->has_error))) { user_sdma_free_request(req, false); diff --git a/drivers/infiniband/hw/qib/qib_ruc.c b/drivers/infiniband/hw/qib/qib_ruc.c index 53efbb0b40c4..9a37e844d4c8 100644 --- a/drivers/infiniband/hw/qib/qib_ruc.c +++ b/drivers/infiniband/hw/qib/qib_ruc.c @@ -368,7 +368,7 @@ static void qib_ruc_loopback(struct rvt_qp *sqp) again: smp_read_barrier_depends(); /* see post_one_send() */ - if (sqp->s_last == ACCESS_ONCE(sqp->s_head)) + if (sqp->s_last == READ_ONCE(sqp->s_head)) goto clr_busy; wqe = rvt_get_swqe_ptr(sqp, sqp->s_last); diff --git a/drivers/infiniband/hw/qib/qib_uc.c b/drivers/infiniband/hw/qib/qib_uc.c index 498e2202e72c..bddcc37ace44 100644 --- a/drivers/infiniband/hw/qib/qib_uc.c +++ b/drivers/infiniband/hw/qib/qib_uc.c @@ -61,7 +61,7 @@ int qib_make_uc_req(struct rvt_qp *qp, unsigned long *flags) goto bail; /* We are in the error state, flush the work request. */ smp_read_barrier_depends(); /* see post_one_send() */ - if (qp->s_last == ACCESS_ONCE(qp->s_head)) + if (qp->s_last == READ_ONCE(qp->s_head)) goto bail; /* If DMAs are in progress, we can't flush immediately. */ if (atomic_read(&priv->s_dma_busy)) { @@ -91,7 +91,7 @@ int qib_make_uc_req(struct rvt_qp *qp, unsigned long *flags) goto bail; /* Check if send work queue is empty. */ smp_read_barrier_depends(); /* see post_one_send() */ - if (qp->s_cur == ACCESS_ONCE(qp->s_head)) + if (qp->s_cur == READ_ONCE(qp->s_head)) goto bail; /* * Start a new request. diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c index be4907453ac4..15962ed193ce 100644 --- a/drivers/infiniband/hw/qib/qib_ud.c +++ b/drivers/infiniband/hw/qib/qib_ud.c @@ -253,7 +253,7 @@ int qib_make_ud_req(struct rvt_qp *qp, unsigned long *flags) goto bail; /* We are in the error state, flush the work request. */ smp_read_barrier_depends(); /* see post_one_send */ - if (qp->s_last == ACCESS_ONCE(qp->s_head)) + if (qp->s_last == READ_ONCE(qp->s_head)) goto bail; /* If DMAs are in progress, we can't flush immediately. */ if (atomic_read(&priv->s_dma_busy)) { @@ -267,7 +267,7 @@ int qib_make_ud_req(struct rvt_qp *qp, unsigned long *flags) /* see post_one_send() */ smp_read_barrier_depends(); - if (qp->s_cur == ACCESS_ONCE(qp->s_head)) + if (qp->s_cur == READ_ONCE(qp->s_head)) goto bail; wqe = rvt_get_swqe_ptr(qp, qp->s_cur); diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 22df09ae809e..b670cb9d2006 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -1073,7 +1073,7 @@ int rvt_error_qp(struct rvt_qp *qp, enum ib_wc_status err) rdi->driver_f.notify_error_qp(qp); /* Schedule the sending tasklet to drain the send work queue. */ - if (ACCESS_ONCE(qp->s_last) != qp->s_head) + if (READ_ONCE(qp->s_last) != qp->s_head) rdi->driver_f.schedule_send(qp); rvt_clear_mr_refs(qp, 0); @@ -1686,7 +1686,7 @@ static inline int rvt_qp_is_avail( if (likely(qp->s_avail)) return 0; smp_read_barrier_depends(); /* see rc.c */ - slast = ACCESS_ONCE(qp->s_last); + slast = READ_ONCE(qp->s_last); if (qp->s_head >= slast) avail = qp->s_size - (qp->s_head - slast); else @@ -1917,7 +1917,7 @@ int rvt_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, * ahead and kick the send engine into gear. Otherwise we will always * just schedule the send to happen later. */ - call_send = qp->s_head == ACCESS_ONCE(qp->s_last) && !wr->next; + call_send = qp->s_head == READ_ONCE(qp->s_last) && !wr->next; for (; wr; wr = wr->next) { err = rvt_post_one_wr(qp, wr, &call_send); diff --git a/drivers/input/misc/regulator-haptic.c b/drivers/input/misc/regulator-haptic.c index 2e8f801932be..a1db1e5040dc 100644 --- a/drivers/input/misc/regulator-haptic.c +++ b/drivers/input/misc/regulator-haptic.c @@ -233,7 +233,7 @@ static int __maybe_unused regulator_haptic_resume(struct device *dev) haptic->suspended = false; - magnitude = ACCESS_ONCE(haptic->magnitude); + magnitude = READ_ONCE(haptic->magnitude); if (magnitude) regulator_haptic_set_voltage(haptic, magnitude); diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index d216a8f7bc22..33bb074d6941 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -347,7 +347,7 @@ static void __cache_size_refresh(void) BUG_ON(!mutex_is_locked(&dm_bufio_clients_lock)); BUG_ON(dm_bufio_client_count < 0); - dm_bufio_cache_size_latch = ACCESS_ONCE(dm_bufio_cache_size); + dm_bufio_cache_size_latch = READ_ONCE(dm_bufio_cache_size); /* * Use default if set to 0 and report the actual cache size used. @@ -960,7 +960,7 @@ static void __get_memory_limit(struct dm_bufio_client *c, { unsigned long buffers; - if (unlikely(ACCESS_ONCE(dm_bufio_cache_size) != dm_bufio_cache_size_latch)) { + if (unlikely(READ_ONCE(dm_bufio_cache_size) != dm_bufio_cache_size_latch)) { if (mutex_trylock(&dm_bufio_clients_lock)) { __cache_size_refresh(); mutex_unlock(&dm_bufio_clients_lock); @@ -1600,7 +1600,7 @@ static bool __try_evict_buffer(struct dm_buffer *b, gfp_t gfp) static unsigned long get_retain_buffers(struct dm_bufio_client *c) { - unsigned long retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes); + unsigned long retain_bytes = READ_ONCE(dm_bufio_retain_bytes); return retain_bytes >> (c->sectors_per_block_bits + SECTOR_SHIFT); } @@ -1647,7 +1647,7 @@ dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { struct dm_bufio_client *c = container_of(shrink, struct dm_bufio_client, shrinker); - return ACCESS_ONCE(c->n_buffers[LIST_CLEAN]) + ACCESS_ONCE(c->n_buffers[LIST_DIRTY]); + return READ_ONCE(c->n_buffers[LIST_CLEAN]) + READ_ONCE(c->n_buffers[LIST_DIRTY]); } /* @@ -1818,7 +1818,7 @@ EXPORT_SYMBOL_GPL(dm_bufio_set_sector_offset); static unsigned get_max_age_hz(void) { - unsigned max_age = ACCESS_ONCE(dm_bufio_max_age); + unsigned max_age = READ_ONCE(dm_bufio_max_age); if (max_age > UINT_MAX / HZ) max_age = UINT_MAX / HZ; diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index cf2c67e35eaf..eb45cc3df31d 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -107,7 +107,7 @@ static void io_job_start(struct dm_kcopyd_throttle *t) try_again: spin_lock_irq(&throttle_spinlock); - throttle = ACCESS_ONCE(t->throttle); + throttle = READ_ONCE(t->throttle); if (likely(throttle >= 100)) goto skip_limit; @@ -157,7 +157,7 @@ static void io_job_finish(struct dm_kcopyd_throttle *t) t->num_io_jobs--; - if (likely(ACCESS_ONCE(t->throttle) >= 100)) + if (likely(READ_ONCE(t->throttle) >= 100)) goto skip_limit; if (!t->num_io_jobs) { diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index 6028d8247f58..a1a5eec783cc 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -431,7 +431,7 @@ do_sync_free: synchronize_rcu_expedited(); dm_stat_free(&s->rcu_head); } else { - ACCESS_ONCE(dm_stat_need_rcu_barrier) = 1; + WRITE_ONCE(dm_stat_need_rcu_barrier, 1); call_rcu(&s->rcu_head, dm_stat_free); } return 0; @@ -639,12 +639,12 @@ void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw, */ last = raw_cpu_ptr(stats->last); stats_aux->merged = - (bi_sector == (ACCESS_ONCE(last->last_sector) && + (bi_sector == (READ_ONCE(last->last_sector) && ((bi_rw == WRITE) == - (ACCESS_ONCE(last->last_rw) == WRITE)) + (READ_ONCE(last->last_rw) == WRITE)) )); - ACCESS_ONCE(last->last_sector) = end_sector; - ACCESS_ONCE(last->last_rw) = bi_rw; + WRITE_ONCE(last->last_sector, end_sector); + WRITE_ONCE(last->last_rw, bi_rw); } rcu_read_lock(); @@ -693,22 +693,22 @@ static void __dm_stat_init_temporary_percpu_totals(struct dm_stat_shared *shared for_each_possible_cpu(cpu) { p = &s->stat_percpu[cpu][x]; - shared->tmp.sectors[READ] += ACCESS_ONCE(p->sectors[READ]); - shared->tmp.sectors[WRITE] += ACCESS_ONCE(p->sectors[WRITE]); - shared->tmp.ios[READ] += ACCESS_ONCE(p->ios[READ]); - shared->tmp.ios[WRITE] += ACCESS_ONCE(p->ios[WRITE]); - shared->tmp.merges[READ] += ACCESS_ONCE(p->merges[READ]); - shared->tmp.merges[WRITE] += ACCESS_ONCE(p->merges[WRITE]); - shared->tmp.ticks[READ] += ACCESS_ONCE(p->ticks[READ]); - shared->tmp.ticks[WRITE] += ACCESS_ONCE(p->ticks[WRITE]); - shared->tmp.io_ticks[READ] += ACCESS_ONCE(p->io_ticks[READ]); - shared->tmp.io_ticks[WRITE] += ACCESS_ONCE(p->io_ticks[WRITE]); - shared->tmp.io_ticks_total += ACCESS_ONCE(p->io_ticks_total); - shared->tmp.time_in_queue += ACCESS_ONCE(p->time_in_queue); + shared->tmp.sectors[READ] += READ_ONCE(p->sectors[READ]); + shared->tmp.sectors[WRITE] += READ_ONCE(p->sectors[WRITE]); + shared->tmp.ios[READ] += READ_ONCE(p->ios[READ]); + shared->tmp.ios[WRITE] += READ_ONCE(p->ios[WRITE]); + shared->tmp.merges[READ] += READ_ONCE(p->merges[READ]); + shared->tmp.merges[WRITE] += READ_ONCE(p->merges[WRITE]); + shared->tmp.ticks[READ] += READ_ONCE(p->ticks[READ]); + shared->tmp.ticks[WRITE] += READ_ONCE(p->ticks[WRITE]); + shared->tmp.io_ticks[READ] += READ_ONCE(p->io_ticks[READ]); + shared->tmp.io_ticks[WRITE] += READ_ONCE(p->io_ticks[WRITE]); + shared->tmp.io_ticks_total += READ_ONCE(p->io_ticks_total); + shared->tmp.time_in_queue += READ_ONCE(p->time_in_queue); if (s->n_histogram_entries) { unsigned i; for (i = 0; i < s->n_histogram_entries + 1; i++) - shared->tmp.histogram[i] += ACCESS_ONCE(p->histogram[i]); + shared->tmp.histogram[i] += READ_ONCE(p->histogram[i]); } } } diff --git a/drivers/md/dm-switch.c b/drivers/md/dm-switch.c index 4c8de1ff78ca..8d0ba879777e 100644 --- a/drivers/md/dm-switch.c +++ b/drivers/md/dm-switch.c @@ -144,7 +144,7 @@ static unsigned switch_region_table_read(struct switch_ctx *sctx, unsigned long switch_get_position(sctx, region_nr, ®ion_index, &bit); - return (ACCESS_ONCE(sctx->region_table[region_index]) >> bit) & + return (READ_ONCE(sctx->region_table[region_index]) >> bit) & ((1 << sctx->region_table_entry_bits) - 1); } diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 1e25705209c2..89e5dff9b4cf 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2431,7 +2431,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) struct pool_c *pt = pool->ti->private; bool needs_check = dm_pool_metadata_needs_check(pool->pmd); enum pool_mode old_mode = get_pool_mode(pool); - unsigned long no_space_timeout = ACCESS_ONCE(no_space_timeout_secs) * HZ; + unsigned long no_space_timeout = READ_ONCE(no_space_timeout_secs) * HZ; /* * Never allow the pool to transition to PM_WRITE mode if user diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index bda3caca23ca..fba93237a780 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -589,7 +589,7 @@ static void verity_prefetch_io(struct work_struct *work) verity_hash_at_level(v, pw->block, i, &hash_block_start, NULL); verity_hash_at_level(v, pw->block + pw->n_blocks - 1, i, &hash_block_end, NULL); if (!i) { - unsigned cluster = ACCESS_ONCE(dm_verity_prefetch_cluster); + unsigned cluster = READ_ONCE(dm_verity_prefetch_cluster); cluster >>= v->data_dev_block_bits; if (unlikely(!cluster)) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 4be85324f44d..8aaffa19b29a 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -114,7 +114,7 @@ static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS; static int __dm_get_module_param_int(int *module_param, int min, int max) { - int param = ACCESS_ONCE(*module_param); + int param = READ_ONCE(*module_param); int modified_param = 0; bool modified = true; @@ -136,7 +136,7 @@ static int __dm_get_module_param_int(int *module_param, int min, int max) unsigned __dm_get_module_param(unsigned *module_param, unsigned def, unsigned max) { - unsigned param = ACCESS_ONCE(*module_param); + unsigned param = READ_ONCE(*module_param); unsigned modified_param = 0; if (!param) diff --git a/drivers/md/md.c b/drivers/md/md.c index 0ff1bbf6c90e..447ddcbc9566 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2651,7 +2651,7 @@ state_show(struct md_rdev *rdev, char *page) { char *sep = ","; size_t len = 0; - unsigned long flags = ACCESS_ONCE(rdev->flags); + unsigned long flags = READ_ONCE(rdev->flags); if (test_bit(Faulty, &flags) || (!test_bit(ExternalBbl, &flags) && diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 928e24a07133..7d9a50eed9db 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6072,7 +6072,7 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n */ rcu_read_lock(); for (i = 0; i < conf->raid_disks; i++) { - struct md_rdev *rdev = ACCESS_ONCE(conf->disks[i].rdev); + struct md_rdev *rdev = READ_ONCE(conf->disks[i].rdev); if (rdev == NULL || test_bit(Faulty, &rdev->flags)) still_degraded = 1; diff --git a/drivers/misc/mic/scif/scif_rb.c b/drivers/misc/mic/scif/scif_rb.c index 637cc4686742..b665757ca89a 100644 --- a/drivers/misc/mic/scif/scif_rb.c +++ b/drivers/misc/mic/scif/scif_rb.c @@ -138,7 +138,7 @@ void scif_rb_commit(struct scif_rb *rb) * the read barrier in scif_rb_count(..) */ wmb(); - ACCESS_ONCE(*rb->write_ptr) = rb->current_write_offset; + WRITE_ONCE(*rb->write_ptr, rb->current_write_offset); #ifdef CONFIG_INTEL_MIC_CARD /* * X100 Si bug: For the case where a Core is performing an EXT_WR @@ -147,7 +147,7 @@ void scif_rb_commit(struct scif_rb *rb) * This way, if ordering is violated for the Interrupt Message, it will * fall just behind the first Posted associated with the first EXT_WR. */ - ACCESS_ONCE(*rb->write_ptr) = rb->current_write_offset; + WRITE_ONCE(*rb->write_ptr, rb->current_write_offset); #endif } @@ -210,7 +210,7 @@ void scif_rb_update_read_ptr(struct scif_rb *rb) * scif_rb_space(..) */ mb(); - ACCESS_ONCE(*rb->read_ptr) = new_offset; + WRITE_ONCE(*rb->read_ptr, new_offset); #ifdef CONFIG_INTEL_MIC_CARD /* * X100 Si Bug: For the case where a Core is performing an EXT_WR @@ -219,7 +219,7 @@ void scif_rb_update_read_ptr(struct scif_rb *rb) * This way, if ordering is violated for the Interrupt Message, it will * fall just behind the first Posted associated with the first EXT_WR. */ - ACCESS_ONCE(*rb->read_ptr) = new_offset; + WRITE_ONCE(*rb->read_ptr, new_offset); #endif } diff --git a/drivers/misc/mic/scif/scif_rma_list.c b/drivers/misc/mic/scif/scif_rma_list.c index e1ef8daedd5a..a036dbb4101e 100644 --- a/drivers/misc/mic/scif/scif_rma_list.c +++ b/drivers/misc/mic/scif/scif_rma_list.c @@ -277,7 +277,7 @@ retry: * Need to restart list traversal if there has been * an asynchronous list entry deletion. */ - if (ACCESS_ONCE(ep->rma_info.async_list_del)) + if (READ_ONCE(ep->rma_info.async_list_del)) goto retry; } mutex_unlock(&ep->rma_info.rma_lock); diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index c02cc817a490..1ed9529e7bd1 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1378,7 +1378,7 @@ int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev) unsigned int count; slaves = rcu_dereference(bond->slave_arr); - count = slaves ? ACCESS_ONCE(slaves->count) : 0; + count = slaves ? READ_ONCE(slaves->count) : 0; if (likely(count)) tx_slave = slaves->arr[hash_index % count]; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c99dc59d729b..af51b90cecbb 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1167,7 +1167,7 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) slave = bond_slave_get_rcu(skb->dev); bond = slave->bond; - recv_probe = ACCESS_ONCE(bond->recv_probe); + recv_probe = READ_ONCE(bond->recv_probe); if (recv_probe) { ret = recv_probe(skb, bond, slave); if (ret == RX_HANDLER_CONSUMED) { @@ -3810,7 +3810,7 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev else bond_xmit_slave_id(bond, skb, 0); } else { - int slave_cnt = ACCESS_ONCE(bond->slave_cnt); + int slave_cnt = READ_ONCE(bond->slave_cnt); if (likely(slave_cnt)) { slave_id = bond_rr_gen_slave_id(bond); @@ -3972,7 +3972,7 @@ static int bond_3ad_xor_xmit(struct sk_buff *skb, struct net_device *dev) unsigned int count; slaves = rcu_dereference(bond->slave_arr); - count = slaves ? ACCESS_ONCE(slaves->count) : 0; + count = slaves ? READ_ONCE(slaves->count) : 0; if (likely(count)) { slave = slaves->arr[bond_xmit_hash(bond, skb) % count]; bond_dev_queue_xmit(bond, skb, slave->dev); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 4ef68f69b58c..43f52a8fe708 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -405,7 +405,7 @@ void free_tx_desc(struct adapter *adap, struct sge_txq *q, */ static inline int reclaimable(const struct sge_txq *q) { - int hw_cidx = ntohs(ACCESS_ONCE(q->stat->cidx)); + int hw_cidx = ntohs(READ_ONCE(q->stat->cidx)); hw_cidx -= q->cidx; return hw_cidx < 0 ? hw_cidx + q->size : hw_cidx; } @@ -1375,7 +1375,7 @@ out_free: dev_kfree_skb_any(skb); */ static inline void reclaim_completed_tx_imm(struct sge_txq *q) { - int hw_cidx = ntohs(ACCESS_ONCE(q->stat->cidx)); + int hw_cidx = ntohs(READ_ONCE(q->stat->cidx)); int reclaim = hw_cidx - q->cidx; if (reclaim < 0) diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 0e3d9f39a807..c6e859a27ee6 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -605,7 +605,7 @@ static void accumulate_16bit_val(u32 *acc, u16 val) if (wrapped) newacc += 65536; - ACCESS_ONCE(*acc) = newacc; + WRITE_ONCE(*acc, newacc); } static void populate_erx_stats(struct be_adapter *adapter, diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 0cec06bec63e..340e28211135 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -373,7 +373,7 @@ static int hip04_tx_reclaim(struct net_device *ndev, bool force) unsigned int count; smp_rmb(); - count = tx_count(ACCESS_ONCE(priv->tx_head), tx_tail); + count = tx_count(READ_ONCE(priv->tx_head), tx_tail); if (count == 0) goto out; @@ -431,7 +431,7 @@ static int hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) dma_addr_t phys; smp_rmb(); - count = tx_count(tx_head, ACCESS_ONCE(priv->tx_tail)); + count = tx_count(tx_head, READ_ONCE(priv->tx_tail)); if (count == (TX_DESC_NUM - 1)) { netif_stop_queue(ndev); return NETDEV_TX_BUSY; diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 8f326f87a815..2cb9539c931e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -264,7 +264,7 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) vsi->rx_buf_failed, vsi->rx_page_failed); rcu_read_lock(); for (i = 0; i < vsi->num_queue_pairs; i++) { - struct i40e_ring *rx_ring = ACCESS_ONCE(vsi->rx_rings[i]); + struct i40e_ring *rx_ring = READ_ONCE(vsi->rx_rings[i]); if (!rx_ring) continue; @@ -320,7 +320,7 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) ITR_IS_DYNAMIC(rx_ring->rx_itr_setting) ? "dynamic" : "fixed"); } for (i = 0; i < vsi->num_queue_pairs; i++) { - struct i40e_ring *tx_ring = ACCESS_ONCE(vsi->tx_rings[i]); + struct i40e_ring *tx_ring = READ_ONCE(vsi->tx_rings[i]); if (!tx_ring) continue; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 05e89864f781..e9e04a485e0a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -1570,7 +1570,7 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, } rcu_read_lock(); for (j = 0; j < vsi->num_queue_pairs; j++) { - tx_ring = ACCESS_ONCE(vsi->tx_rings[j]); + tx_ring = READ_ONCE(vsi->tx_rings[j]); if (!tx_ring) continue; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 6498da8806cb..de1fcac7834d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -455,7 +455,7 @@ static void i40e_get_netdev_stats_struct(struct net_device *netdev, u64 bytes, packets; unsigned int start; - tx_ring = ACCESS_ONCE(vsi->tx_rings[i]); + tx_ring = READ_ONCE(vsi->tx_rings[i]); if (!tx_ring) continue; i40e_get_netdev_stats_struct_tx(tx_ring, stats); @@ -791,7 +791,7 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) rcu_read_lock(); for (q = 0; q < vsi->num_queue_pairs; q++) { /* locate Tx ring */ - p = ACCESS_ONCE(vsi->tx_rings[q]); + p = READ_ONCE(vsi->tx_rings[q]); do { start = u64_stats_fetch_begin_irq(&p->syncp); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index d8456c381c99..97381238eb7c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -130,7 +130,7 @@ static int i40e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) } smp_mb(); /* Force any pending update before accessing. */ - adj = ACCESS_ONCE(pf->ptp_base_adj); + adj = READ_ONCE(pf->ptp_base_adj); freq = adj; freq *= ppb; @@ -499,7 +499,7 @@ void i40e_ptp_set_increment(struct i40e_pf *pf) wr32(hw, I40E_PRTTSYN_INC_H, incval >> 32); /* Update the base adjustement value. */ - ACCESS_ONCE(pf->ptp_base_adj) = incval; + WRITE_ONCE(pf->ptp_base_adj, incval); smp_mb(); /* Force the above update. */ } diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h index 58adbf234e07..31a3f09df9f7 100644 --- a/drivers/net/ethernet/intel/igb/e1000_regs.h +++ b/drivers/net/ethernet/intel/igb/e1000_regs.h @@ -375,7 +375,7 @@ u32 igb_rd32(struct e1000_hw *hw, u32 reg); /* write operations, indexed using DWORDS */ #define wr32(reg, val) \ do { \ - u8 __iomem *hw_addr = ACCESS_ONCE((hw)->hw_addr); \ + u8 __iomem *hw_addr = READ_ONCE((hw)->hw_addr); \ if (!E1000_REMOVED(hw_addr)) \ writel((val), &hw_addr[(reg)]); \ } while (0) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index fd4a46b03cc8..6bccc2be2b91 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -750,7 +750,7 @@ static void igb_cache_ring_register(struct igb_adapter *adapter) u32 igb_rd32(struct e1000_hw *hw, u32 reg) { struct igb_adapter *igb = container_of(hw, struct igb_adapter, hw); - u8 __iomem *hw_addr = ACCESS_ONCE(hw->hw_addr); + u8 __iomem *hw_addr = READ_ONCE(hw->hw_addr); u32 value = 0; if (E1000_REMOVED(hw_addr)) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h index e083732adf64..a01409e2e06c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h @@ -161,7 +161,7 @@ static inline bool ixgbe_removed(void __iomem *addr) static inline void ixgbe_write_reg(struct ixgbe_hw *hw, u32 reg, u32 value) { - u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr); + u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr); if (ixgbe_removed(reg_addr)) return; @@ -180,7 +180,7 @@ static inline void writeq(u64 val, void __iomem *addr) static inline void ixgbe_write_reg64(struct ixgbe_hw *hw, u32 reg, u64 value) { - u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr); + u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr); if (ixgbe_removed(reg_addr)) return; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 4d76afd13868..2224e691ee07 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -380,7 +380,7 @@ static void ixgbe_check_remove(struct ixgbe_hw *hw, u32 reg) */ u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg) { - u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr); + u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr); u32 value; if (ixgbe_removed(reg_addr)) @@ -8630,7 +8630,7 @@ static void ixgbe_get_stats64(struct net_device *netdev, rcu_read_lock(); for (i = 0; i < adapter->num_rx_queues; i++) { - struct ixgbe_ring *ring = ACCESS_ONCE(adapter->rx_ring[i]); + struct ixgbe_ring *ring = READ_ONCE(adapter->rx_ring[i]); u64 bytes, packets; unsigned int start; @@ -8646,12 +8646,12 @@ static void ixgbe_get_stats64(struct net_device *netdev, } for (i = 0; i < adapter->num_tx_queues; i++) { - struct ixgbe_ring *ring = ACCESS_ONCE(adapter->tx_ring[i]); + struct ixgbe_ring *ring = READ_ONCE(adapter->tx_ring[i]); ixgbe_get_ring_stats64(stats, ring); } for (i = 0; i < adapter->num_xdp_queues; i++) { - struct ixgbe_ring *ring = ACCESS_ONCE(adapter->xdp_ring[i]); + struct ixgbe_ring *ring = READ_ONCE(adapter->xdp_ring[i]); ixgbe_get_ring_stats64(stats, ring); } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 86d6924a2b71..ae312c45696a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -378,7 +378,7 @@ static int ixgbe_ptp_adjfreq_82599(struct ptp_clock_info *ptp, s32 ppb) } smp_mb(); - incval = ACCESS_ONCE(adapter->base_incval); + incval = READ_ONCE(adapter->base_incval); freq = incval; freq *= ppb; @@ -1159,7 +1159,7 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) } /* update the base incval used to calculate frequency adjustment */ - ACCESS_ONCE(adapter->base_incval) = incval; + WRITE_ONCE(adapter->base_incval, incval); smp_mb(); /* need lock to prevent incorrect read while modifying cyclecounter */ diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 032f8ac06357..cacb30682434 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -164,7 +164,7 @@ static void ixgbevf_check_remove(struct ixgbe_hw *hw, u32 reg) u32 ixgbevf_read_reg(struct ixgbe_hw *hw, u32 reg) { - u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr); + u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr); u32 value; if (IXGBE_REMOVED(reg_addr)) diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.h b/drivers/net/ethernet/intel/ixgbevf/vf.h index 04d8d4ee4f04..c651fefcc3d2 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.h +++ b/drivers/net/ethernet/intel/ixgbevf/vf.h @@ -182,7 +182,7 @@ struct ixgbevf_info { static inline void ixgbe_write_reg(struct ixgbe_hw *hw, u32 reg, u32 value) { - u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr); + u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr); if (IXGBE_REMOVED(reg_addr)) return; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 8a32a8f7f9c0..3541a7f9d12e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -414,8 +414,8 @@ bool mlx4_en_process_tx_cq(struct net_device *dev, index = cons_index & size_mask; cqe = mlx4_en_get_cqe(buf, index, priv->cqe_size) + factor; - last_nr_txbb = ACCESS_ONCE(ring->last_nr_txbb); - ring_cons = ACCESS_ONCE(ring->cons); + last_nr_txbb = READ_ONCE(ring->last_nr_txbb); + ring_cons = READ_ONCE(ring->cons); ring_index = ring_cons & size_mask; stamp_index = ring_index; @@ -479,8 +479,8 @@ bool mlx4_en_process_tx_cq(struct net_device *dev, wmb(); /* we want to dirty this cache line once */ - ACCESS_ONCE(ring->last_nr_txbb) = last_nr_txbb; - ACCESS_ONCE(ring->cons) = ring_cons + txbbs_skipped; + WRITE_ONCE(ring->last_nr_txbb, last_nr_txbb); + WRITE_ONCE(ring->cons, ring_cons + txbbs_skipped); if (cq->type == TX_XDP) return done < budget; @@ -858,7 +858,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_drop; /* fetch ring->cons far ahead before needing it to avoid stall */ - ring_cons = ACCESS_ONCE(ring->cons); + ring_cons = READ_ONCE(ring->cons); real_size = get_real_size(skb, shinfo, dev, &lso_header_size, &inline_ok, &fragptr); @@ -1066,7 +1066,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) */ smp_rmb(); - ring_cons = ACCESS_ONCE(ring->cons); + ring_cons = READ_ONCE(ring->cons); if (unlikely(!mlx4_en_is_tx_ring_full(ring))) { netif_tx_wake_queue(ring->tx_queue); ring->wake_queue++; diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 50ea69d88480..5dd5f61e1114 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -2629,7 +2629,7 @@ static void vxge_poll_vp_lockup(unsigned long data) ring = &vdev->vpaths[i].ring; /* Truncated to machine word size number of frames */ - rx_frms = ACCESS_ONCE(ring->stats.rx_frms); + rx_frms = READ_ONCE(ring->stats.rx_frms); /* Did this vpath received any packets */ if (ring->stats.prev_rx_frms == rx_frms) { diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 13f72f5b18d2..a95a46bcd339 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -2073,7 +2073,7 @@ static irqreturn_t efx_ef10_msi_interrupt(int irq, void *dev_id) netif_vdbg(efx, intr, efx->net_dev, "IRQ %d on CPU %d\n", irq, raw_smp_processor_id()); - if (likely(ACCESS_ONCE(efx->irq_soft_enabled))) { + if (likely(READ_ONCE(efx->irq_soft_enabled))) { /* Note test interrupts */ if (context->index == efx->irq_level) efx->last_irq_cpu = raw_smp_processor_id(); @@ -2088,7 +2088,7 @@ static irqreturn_t efx_ef10_msi_interrupt(int irq, void *dev_id) static irqreturn_t efx_ef10_legacy_interrupt(int irq, void *dev_id) { struct efx_nic *efx = dev_id; - bool soft_enabled = ACCESS_ONCE(efx->irq_soft_enabled); + bool soft_enabled = READ_ONCE(efx->irq_soft_enabled); struct efx_channel *channel; efx_dword_t reg; u32 queues; @@ -3291,7 +3291,7 @@ static int efx_ef10_handle_rx_event(struct efx_channel *channel, bool rx_cont; u16 flags = 0; - if (unlikely(ACCESS_ONCE(efx->reset_pending))) + if (unlikely(READ_ONCE(efx->reset_pending))) return 0; /* Basic packet information */ @@ -3428,7 +3428,7 @@ efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) unsigned int tx_ev_q_label; int tx_descs = 0; - if (unlikely(ACCESS_ONCE(efx->reset_pending))) + if (unlikely(READ_ONCE(efx->reset_pending))) return 0; if (unlikely(EFX_QWORD_FIELD(*event, ESF_DZ_TX_DROP_EVENT))) @@ -5316,7 +5316,7 @@ static void efx_ef10_filter_remove_old(struct efx_nic *efx) int i; for (i = 0; i < HUNT_FILTER_TBL_ROWS; i++) { - if (ACCESS_ONCE(table->entry[i].spec) & + if (READ_ONCE(table->entry[i].spec) & EFX_EF10_FILTER_FLAG_AUTO_OLD) { rc = efx_ef10_filter_remove_internal(efx, 1U << EFX_FILTER_PRI_AUTO, i, true); diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index b9cb697b2818..016616a63880 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -2809,7 +2809,7 @@ static void efx_reset_work(struct work_struct *data) unsigned long pending; enum reset_type method; - pending = ACCESS_ONCE(efx->reset_pending); + pending = READ_ONCE(efx->reset_pending); method = fls(pending) - 1; if (method == RESET_TYPE_MC_BIST) @@ -2874,7 +2874,7 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type) /* If we're not READY then just leave the flags set as the cue * to abort probing or reschedule the reset later. */ - if (ACCESS_ONCE(efx->state) != STATE_READY) + if (READ_ONCE(efx->state) != STATE_READY) return; /* efx_process_channel() will no longer read events once a diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c index 29614da91cbf..7263275fde4a 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.c +++ b/drivers/net/ethernet/sfc/falcon/efx.c @@ -2545,7 +2545,7 @@ static void ef4_reset_work(struct work_struct *data) unsigned long pending; enum reset_type method; - pending = ACCESS_ONCE(efx->reset_pending); + pending = READ_ONCE(efx->reset_pending); method = fls(pending) - 1; if ((method == RESET_TYPE_RECOVER_OR_DISABLE || @@ -2605,7 +2605,7 @@ void ef4_schedule_reset(struct ef4_nic *efx, enum reset_type type) /* If we're not READY then just leave the flags set as the cue * to abort probing or reschedule the reset later. */ - if (ACCESS_ONCE(efx->state) != STATE_READY) + if (READ_ONCE(efx->state) != STATE_READY) return; queue_work(reset_workqueue, &efx->reset_work); diff --git a/drivers/net/ethernet/sfc/falcon/falcon.c b/drivers/net/ethernet/sfc/falcon/falcon.c index 93c713c1f627..cd8bb472d758 100644 --- a/drivers/net/ethernet/sfc/falcon/falcon.c +++ b/drivers/net/ethernet/sfc/falcon/falcon.c @@ -452,7 +452,7 @@ static irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id) "IRQ %d on CPU %d status " EF4_OWORD_FMT "\n", irq, raw_smp_processor_id(), EF4_OWORD_VAL(*int_ker)); - if (!likely(ACCESS_ONCE(efx->irq_soft_enabled))) + if (!likely(READ_ONCE(efx->irq_soft_enabled))) return IRQ_HANDLED; /* Check to see if we have a serious error condition */ @@ -1372,7 +1372,7 @@ static void falcon_reconfigure_mac_wrapper(struct ef4_nic *efx) ef4_oword_t reg; int link_speed, isolate; - isolate = !!ACCESS_ONCE(efx->reset_pending); + isolate = !!READ_ONCE(efx->reset_pending); switch (link_state->speed) { case 10000: link_speed = 3; break; diff --git a/drivers/net/ethernet/sfc/falcon/farch.c b/drivers/net/ethernet/sfc/falcon/farch.c index 05916c710d8c..494884f6af4a 100644 --- a/drivers/net/ethernet/sfc/falcon/farch.c +++ b/drivers/net/ethernet/sfc/falcon/farch.c @@ -834,7 +834,7 @@ ef4_farch_handle_tx_event(struct ef4_channel *channel, ef4_qword_t *event) struct ef4_nic *efx = channel->efx; int tx_packets = 0; - if (unlikely(ACCESS_ONCE(efx->reset_pending))) + if (unlikely(READ_ONCE(efx->reset_pending))) return 0; if (likely(EF4_QWORD_FIELD(*event, FSF_AZ_TX_EV_COMP))) { @@ -990,7 +990,7 @@ ef4_farch_handle_rx_event(struct ef4_channel *channel, const ef4_qword_t *event) struct ef4_rx_queue *rx_queue; struct ef4_nic *efx = channel->efx; - if (unlikely(ACCESS_ONCE(efx->reset_pending))) + if (unlikely(READ_ONCE(efx->reset_pending))) return; rx_ev_cont = EF4_QWORD_FIELD(*event, FSF_AZ_RX_EV_JUMBO_CONT); @@ -1504,7 +1504,7 @@ irqreturn_t ef4_farch_fatal_interrupt(struct ef4_nic *efx) irqreturn_t ef4_farch_legacy_interrupt(int irq, void *dev_id) { struct ef4_nic *efx = dev_id; - bool soft_enabled = ACCESS_ONCE(efx->irq_soft_enabled); + bool soft_enabled = READ_ONCE(efx->irq_soft_enabled); ef4_oword_t *int_ker = efx->irq_status.addr; irqreturn_t result = IRQ_NONE; struct ef4_channel *channel; @@ -1596,7 +1596,7 @@ irqreturn_t ef4_farch_msi_interrupt(int irq, void *dev_id) "IRQ %d on CPU %d status " EF4_OWORD_FMT "\n", irq, raw_smp_processor_id(), EF4_OWORD_VAL(*int_ker)); - if (!likely(ACCESS_ONCE(efx->irq_soft_enabled))) + if (!likely(READ_ONCE(efx->irq_soft_enabled))) return IRQ_HANDLED; /* Handle non-event-queue sources */ diff --git a/drivers/net/ethernet/sfc/falcon/nic.h b/drivers/net/ethernet/sfc/falcon/nic.h index a4c4592f6023..54ca457cdb15 100644 --- a/drivers/net/ethernet/sfc/falcon/nic.h +++ b/drivers/net/ethernet/sfc/falcon/nic.h @@ -83,7 +83,7 @@ static inline struct ef4_tx_queue *ef4_tx_queue_partner(struct ef4_tx_queue *tx_ static inline bool __ef4_nic_tx_is_empty(struct ef4_tx_queue *tx_queue, unsigned int write_count) { - unsigned int empty_read_count = ACCESS_ONCE(tx_queue->empty_read_count); + unsigned int empty_read_count = READ_ONCE(tx_queue->empty_read_count); if (empty_read_count == 0) return false; @@ -464,11 +464,11 @@ irqreturn_t ef4_farch_fatal_interrupt(struct ef4_nic *efx); static inline int ef4_nic_event_test_irq_cpu(struct ef4_channel *channel) { - return ACCESS_ONCE(channel->event_test_cpu); + return READ_ONCE(channel->event_test_cpu); } static inline int ef4_nic_irq_test_irq_cpu(struct ef4_nic *efx) { - return ACCESS_ONCE(efx->last_irq_cpu); + return READ_ONCE(efx->last_irq_cpu); } /* Global Resources */ diff --git a/drivers/net/ethernet/sfc/falcon/tx.c b/drivers/net/ethernet/sfc/falcon/tx.c index 6a75f4140a4b..6486814e97dc 100644 --- a/drivers/net/ethernet/sfc/falcon/tx.c +++ b/drivers/net/ethernet/sfc/falcon/tx.c @@ -134,8 +134,8 @@ static void ef4_tx_maybe_stop_queue(struct ef4_tx_queue *txq1) */ netif_tx_stop_queue(txq1->core_txq); smp_mb(); - txq1->old_read_count = ACCESS_ONCE(txq1->read_count); - txq2->old_read_count = ACCESS_ONCE(txq2->read_count); + txq1->old_read_count = READ_ONCE(txq1->read_count); + txq2->old_read_count = READ_ONCE(txq2->read_count); fill_level = max(txq1->insert_count - txq1->old_read_count, txq2->insert_count - txq2->old_read_count); @@ -524,7 +524,7 @@ void ef4_xmit_done(struct ef4_tx_queue *tx_queue, unsigned int index) /* Check whether the hardware queue is now empty */ if ((int)(tx_queue->read_count - tx_queue->old_write_count) >= 0) { - tx_queue->old_write_count = ACCESS_ONCE(tx_queue->write_count); + tx_queue->old_write_count = READ_ONCE(tx_queue->write_count); if (tx_queue->read_count == tx_queue->old_write_count) { smp_mb(); tx_queue->empty_read_count = diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c index ba45150f53c7..86454d25a405 100644 --- a/drivers/net/ethernet/sfc/farch.c +++ b/drivers/net/ethernet/sfc/farch.c @@ -827,7 +827,7 @@ efx_farch_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) struct efx_nic *efx = channel->efx; int tx_packets = 0; - if (unlikely(ACCESS_ONCE(efx->reset_pending))) + if (unlikely(READ_ONCE(efx->reset_pending))) return 0; if (likely(EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_COMP))) { @@ -979,7 +979,7 @@ efx_farch_handle_rx_event(struct efx_channel *channel, const efx_qword_t *event) struct efx_rx_queue *rx_queue; struct efx_nic *efx = channel->efx; - if (unlikely(ACCESS_ONCE(efx->reset_pending))) + if (unlikely(READ_ONCE(efx->reset_pending))) return; rx_ev_cont = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_JUMBO_CONT); @@ -1520,7 +1520,7 @@ irqreturn_t efx_farch_fatal_interrupt(struct efx_nic *efx) irqreturn_t efx_farch_legacy_interrupt(int irq, void *dev_id) { struct efx_nic *efx = dev_id; - bool soft_enabled = ACCESS_ONCE(efx->irq_soft_enabled); + bool soft_enabled = READ_ONCE(efx->irq_soft_enabled); efx_oword_t *int_ker = efx->irq_status.addr; irqreturn_t result = IRQ_NONE; struct efx_channel *channel; @@ -1612,7 +1612,7 @@ irqreturn_t efx_farch_msi_interrupt(int irq, void *dev_id) "IRQ %d on CPU %d status " EFX_OWORD_FMT "\n", irq, raw_smp_processor_id(), EFX_OWORD_VAL(*int_ker)); - if (!likely(ACCESS_ONCE(efx->irq_soft_enabled))) + if (!likely(READ_ONCE(efx->irq_soft_enabled))) return IRQ_HANDLED; /* Handle non-event-queue sources */ diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h index 4d7fb8af880d..7b51b6371724 100644 --- a/drivers/net/ethernet/sfc/nic.h +++ b/drivers/net/ethernet/sfc/nic.h @@ -81,7 +81,7 @@ static struct efx_tx_queue *efx_tx_queue_partner(struct efx_tx_queue *tx_queue) static inline bool __efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue, unsigned int write_count) { - unsigned int empty_read_count = ACCESS_ONCE(tx_queue->empty_read_count); + unsigned int empty_read_count = READ_ONCE(tx_queue->empty_read_count); if (empty_read_count == 0) return false; @@ -617,11 +617,11 @@ irqreturn_t efx_farch_fatal_interrupt(struct efx_nic *efx); static inline int efx_nic_event_test_irq_cpu(struct efx_channel *channel) { - return ACCESS_ONCE(channel->event_test_cpu); + return READ_ONCE(channel->event_test_cpu); } static inline int efx_nic_irq_test_irq_cpu(struct efx_nic *efx) { - return ACCESS_ONCE(efx->last_irq_cpu); + return READ_ONCE(efx->last_irq_cpu); } /* Global Resources */ diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index 60cdb97f58e2..56c2db398def 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -658,7 +658,7 @@ static void efx_ptp_send_times(struct efx_nic *efx, /* Write host time for specified period or until MC is done */ while ((timespec64_compare(&now.ts_real, &limit) < 0) && - ACCESS_ONCE(*mc_running)) { + READ_ONCE(*mc_running)) { struct timespec64 update_time; unsigned int host_time; @@ -668,7 +668,7 @@ static void efx_ptp_send_times(struct efx_nic *efx, do { pps_get_ts(&now); } while ((timespec64_compare(&now.ts_real, &update_time) < 0) && - ACCESS_ONCE(*mc_running)); + READ_ONCE(*mc_running)); /* Synchronise NIC with single word of time only */ host_time = (now.ts_real.tv_sec << MC_NANOSECOND_BITS | @@ -832,14 +832,14 @@ static int efx_ptp_synchronize(struct efx_nic *efx, unsigned int num_readings) ptp->start.dma_addr); /* Clear flag that signals MC ready */ - ACCESS_ONCE(*start) = 0; + WRITE_ONCE(*start, 0); rc = efx_mcdi_rpc_start(efx, MC_CMD_PTP, synch_buf, MC_CMD_PTP_IN_SYNCHRONIZE_LEN); EFX_WARN_ON_ONCE_PARANOID(rc); /* Wait for start from MCDI (or timeout) */ timeout = jiffies + msecs_to_jiffies(MAX_SYNCHRONISE_WAIT_MS); - while (!ACCESS_ONCE(*start) && (time_before(jiffies, timeout))) { + while (!READ_ONCE(*start) && (time_before(jiffies, timeout))) { udelay(20); /* Usually start MCDI execution quickly */ loops++; } @@ -849,7 +849,7 @@ static int efx_ptp_synchronize(struct efx_nic *efx, unsigned int num_readings) if (!time_before(jiffies, timeout)) ++ptp->sync_timeouts; - if (ACCESS_ONCE(*start)) + if (READ_ONCE(*start)) efx_ptp_send_times(efx, &last_time); /* Collect results */ diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 32bf1fecf864..efb66ea21f27 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -136,8 +136,8 @@ static void efx_tx_maybe_stop_queue(struct efx_tx_queue *txq1) */ netif_tx_stop_queue(txq1->core_txq); smp_mb(); - txq1->old_read_count = ACCESS_ONCE(txq1->read_count); - txq2->old_read_count = ACCESS_ONCE(txq2->read_count); + txq1->old_read_count = READ_ONCE(txq1->read_count); + txq2->old_read_count = READ_ONCE(txq2->read_count); fill_level = max(txq1->insert_count - txq1->old_read_count, txq2->insert_count - txq2->old_read_count); @@ -752,7 +752,7 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index) /* Check whether the hardware queue is now empty */ if ((int)(tx_queue->read_count - tx_queue->old_write_count) >= 0) { - tx_queue->old_write_count = ACCESS_ONCE(tx_queue->write_count); + tx_queue->old_write_count = READ_ONCE(tx_queue->write_count); if (tx_queue->read_count == tx_queue->old_write_count) { smp_mb(); tx_queue->empty_read_count = diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 6a4e8e1bbd90..8ab0fb6892d5 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -6245,7 +6245,7 @@ static void niu_get_rx_stats(struct niu *np, pkts = dropped = errors = bytes = 0; - rx_rings = ACCESS_ONCE(np->rx_rings); + rx_rings = READ_ONCE(np->rx_rings); if (!rx_rings) goto no_rings; @@ -6276,7 +6276,7 @@ static void niu_get_tx_stats(struct niu *np, pkts = errors = bytes = 0; - tx_rings = ACCESS_ONCE(np->tx_rings); + tx_rings = READ_ONCE(np->tx_rings); if (!tx_rings) goto no_rings; diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 21b71ae947fd..b55b29b90b88 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -257,7 +257,7 @@ static struct tap_queue *tap_get_queue(struct tap_dev *tap, * and validate that the result isn't NULL - in case we are * racing against queue removal. */ - int numvtaps = ACCESS_ONCE(tap->numvtaps); + int numvtaps = READ_ONCE(tap->numvtaps); __u32 rxq; if (!numvtaps) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index e21bf90b819f..27cd50c5bc9e 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -469,7 +469,7 @@ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, u32 numqueues = 0; rcu_read_lock(); - numqueues = ACCESS_ONCE(tun->numqueues); + numqueues = READ_ONCE(tun->numqueues); txq = __skb_get_hash_symmetric(skb); if (txq) { @@ -864,7 +864,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); tfile = rcu_dereference(tun->tfiles[txq]); - numqueues = ACCESS_ONCE(tun->numqueues); + numqueues = READ_ONCE(tun->numqueues); /* Drop packet if interface is not attached */ if (txq >= numqueues) diff --git a/drivers/net/wireless/ath/ath5k/desc.c b/drivers/net/wireless/ath/ath5k/desc.c index bd8d4392d68b..80f75139495f 100644 --- a/drivers/net/wireless/ath/ath5k/desc.c +++ b/drivers/net/wireless/ath/ath5k/desc.c @@ -500,13 +500,13 @@ ath5k_hw_proc_4word_tx_status(struct ath5k_hw *ah, tx_status = &desc->ud.ds_tx5212.tx_stat; - txstat1 = ACCESS_ONCE(tx_status->tx_status_1); + txstat1 = READ_ONCE(tx_status->tx_status_1); /* No frame has been send or error */ if (unlikely(!(txstat1 & AR5K_DESC_TX_STATUS1_DONE))) return -EINPROGRESS; - txstat0 = ACCESS_ONCE(tx_status->tx_status_0); + txstat0 = READ_ONCE(tx_status->tx_status_0); /* * Get descriptor status @@ -700,14 +700,14 @@ ath5k_hw_proc_5212_rx_status(struct ath5k_hw *ah, u32 rxstat0, rxstat1; rx_status = &desc->ud.ds_rx.rx_stat; - rxstat1 = ACCESS_ONCE(rx_status->rx_status_1); + rxstat1 = READ_ONCE(rx_status->rx_status_1); /* No frame received / not ready */ if (unlikely(!(rxstat1 & AR5K_5212_RX_DESC_STATUS1_DONE))) return -EINPROGRESS; memset(rs, 0, sizeof(struct ath5k_rx_status)); - rxstat0 = ACCESS_ONCE(rx_status->rx_status_0); + rxstat0 = READ_ONCE(rx_status->rx_status_0); /* * Frame receive status diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index 613caca7dc02..785a0f33b7e6 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -3628,7 +3628,7 @@ static void brcmf_sdio_dataworker(struct work_struct *work) bus->dpc_running = true; wmb(); - while (ACCESS_ONCE(bus->dpc_triggered)) { + while (READ_ONCE(bus->dpc_triggered)) { bus->dpc_triggered = false; brcmf_sdio_dpc(bus); bus->idlecount = 0; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index 231878969332..0f45f34e39d3 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -1118,7 +1118,7 @@ void iwl_mvm_set_hw_ctkill_state(struct iwl_mvm *mvm, bool state) static bool iwl_mvm_set_hw_rfkill_state(struct iwl_op_mode *op_mode, bool state) { struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode); - bool calibrating = ACCESS_ONCE(mvm->calibrating); + bool calibrating = READ_ONCE(mvm->calibrating); if (state) set_bit(IWL_MVM_STATUS_HW_RFKILL, &mvm->status); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 6f2e2af23219..6e9d3289b9d0 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -652,7 +652,7 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) return -1; } else if (info.control.vif->type == NL80211_IFTYPE_STATION && is_multicast_ether_addr(hdr->addr1)) { - u8 ap_sta_id = ACCESS_ONCE(mvmvif->ap_sta_id); + u8 ap_sta_id = READ_ONCE(mvmvif->ap_sta_id); if (ap_sta_id != IWL_MVM_INVALID_STA) sta_id = ap_sta_id; @@ -700,7 +700,7 @@ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, snap_ip_tcp = 8 + skb_transport_header(skb) - skb_network_header(skb) + tcp_hdrlen(skb); - dbg_max_amsdu_len = ACCESS_ONCE(mvm->max_amsdu_len); + dbg_max_amsdu_len = READ_ONCE(mvm->max_amsdu_len); if (!sta->max_amsdu_len || !ieee80211_is_data_qos(hdr->frame_control) || diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c index a06b6612b658..f25ce3a1ea50 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -1247,7 +1247,7 @@ restart: spin_lock(&rxq->lock); /* uCode's read index (stored in shared DRAM) indicates the last Rx * buffer that the driver may process (last buffer filled by ucode). */ - r = le16_to_cpu(ACCESS_ONCE(rxq->rb_stts->closed_rb_num)) & 0x0FFF; + r = le16_to_cpu(READ_ONCE(rxq->rb_stts->closed_rb_num)) & 0x0FFF; i = rxq->read; /* W/A 9000 device step A0 wrap-around bug */ diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index 2e3e013ec95a..9ad3f4fe5894 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -2076,12 +2076,12 @@ static int iwl_trans_pcie_wait_txq_empty(struct iwl_trans *trans, int txq_idx) IWL_DEBUG_TX_QUEUES(trans, "Emptying queue %d...\n", txq_idx); txq = trans_pcie->txq[txq_idx]; - wr_ptr = ACCESS_ONCE(txq->write_ptr); + wr_ptr = READ_ONCE(txq->write_ptr); - while (txq->read_ptr != ACCESS_ONCE(txq->write_ptr) && + while (txq->read_ptr != READ_ONCE(txq->write_ptr) && !time_after(jiffies, now + msecs_to_jiffies(IWL_FLUSH_WAIT_MS))) { - u8 write_ptr = ACCESS_ONCE(txq->write_ptr); + u8 write_ptr = READ_ONCE(txq->write_ptr); if (WARN_ONCE(wr_ptr != write_ptr, "WR pointer moved while flushing %d -> %d\n", @@ -2553,7 +2553,7 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans, spin_lock(&rxq->lock); - r = le16_to_cpu(ACCESS_ONCE(rxq->rb_stts->closed_rb_num)) & 0x0FFF; + r = le16_to_cpu(READ_ONCE(rxq->rb_stts->closed_rb_num)) & 0x0FFF; for (i = rxq->read, j = 0; i != r && j < allocated_rb_nums; @@ -2814,7 +2814,7 @@ static struct iwl_trans_dump_data /* Dump RBs is supported only for pre-9000 devices (1 queue) */ struct iwl_rxq *rxq = &trans_pcie->rxq[0]; /* RBs */ - num_rbs = le16_to_cpu(ACCESS_ONCE(rxq->rb_stts->closed_rb_num)) + num_rbs = le16_to_cpu(READ_ONCE(rxq->rb_stts->closed_rb_num)) & 0x0FFF; num_rbs = (num_rbs - rxq->read) & RX_QUEUE_MASK; len += num_rbs * (sizeof(*data) + diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 6467ffac9811..d2b3d6177a55 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1380,7 +1380,7 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw, mac80211_hwsim_monitor_rx(hw, skb, channel); /* wmediumd mode check */ - _portid = ACCESS_ONCE(data->wmediumd); + _portid = READ_ONCE(data->wmediumd); if (_portid) return mac80211_hwsim_tx_frame_nl(hw, skb, _portid); @@ -1477,7 +1477,7 @@ static void mac80211_hwsim_tx_frame(struct ieee80211_hw *hw, struct ieee80211_channel *chan) { struct mac80211_hwsim_data *data = hw->priv; - u32 _pid = ACCESS_ONCE(data->wmediumd); + u32 _pid = READ_ONCE(data->wmediumd); if (ieee80211_hw_check(hw, SUPPORTS_RC_TABLE)) { struct ieee80211_tx_info *txi = IEEE80211_SKB_CB(skb); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index f05cfc83c9c8..f946bf889015 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -996,7 +996,7 @@ static void qlt_free_session_done(struct work_struct *work) if (logout_started) { bool traced = false; - while (!ACCESS_ONCE(sess->logout_completed)) { + while (!READ_ONCE(sess->logout_completed)) { if (!traced) { ql_dbg(ql_dbg_tgt_mgt, vha, 0xf086, "%s: waiting for sess %p logout\n", diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 942d094269fb..9469695f5871 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -985,7 +985,7 @@ static unsigned int tcmu_handle_completions(struct tcmu_dev *udev) mb = udev->mb_addr; tcmu_flush_dcache_range(mb, sizeof(*mb)); - while (udev->cmdr_last_cleaned != ACCESS_ONCE(mb->cmd_tail)) { + while (udev->cmdr_last_cleaned != READ_ONCE(mb->cmd_tail)) { struct tcmu_cmd_entry *entry = (void *) mb + CMDR_OFF + udev->cmdr_last_cleaned; struct tcmu_cmd *cmd; diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 3e865dbf878c..fbaa2a90d25d 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -483,7 +483,7 @@ static ssize_t wdm_read if (rv < 0) return -ERESTARTSYS; - cntr = ACCESS_ONCE(desc->length); + cntr = READ_ONCE(desc->length); if (cntr == 0) { desc->read = 0; retry: diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index e9326f31db8d..4ae667d8c238 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -150,7 +150,7 @@ static int usbfs_increase_memory_usage(u64 amount) { u64 lim; - lim = ACCESS_ONCE(usbfs_memory_mb); + lim = READ_ONCE(usbfs_memory_mb); lim <<= 20; atomic64_add(amount, &usbfs_memory_usage); diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c index d930bfda4010..58d59c5f8592 100644 --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -973,7 +973,7 @@ static ssize_t interface_show(struct device *dev, struct device_attribute *attr, char *string; intf = to_usb_interface(dev); - string = ACCESS_ONCE(intf->cur_altsetting->string); + string = READ_ONCE(intf->cur_altsetting->string); if (!string) return 0; return sprintf(buf, "%s\n", string); @@ -989,7 +989,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, intf = to_usb_interface(dev); udev = interface_to_usbdev(intf); - alt = ACCESS_ONCE(intf->cur_altsetting); + alt = READ_ONCE(intf->cur_altsetting); return sprintf(buf, "usb:v%04Xp%04Xd%04Xdc%02Xdsc%02Xdp%02X" "ic%02Xisc%02Xip%02Xin%02X\n", diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c index 1f9941145746..0b59fa50aa30 100644 --- a/drivers/usb/gadget/udc/gr_udc.c +++ b/drivers/usb/gadget/udc/gr_udc.c @@ -1261,7 +1261,7 @@ static int gr_handle_in_ep(struct gr_ep *ep) if (!req->last_desc) return 0; - if (ACCESS_ONCE(req->last_desc->ctrl) & GR_DESC_IN_CTRL_EN) + if (READ_ONCE(req->last_desc->ctrl) & GR_DESC_IN_CTRL_EN) return 0; /* Not put in hardware buffers yet */ if (gr_read32(&ep->regs->epstat) & (GR_EPSTAT_B1 | GR_EPSTAT_B0)) @@ -1290,7 +1290,7 @@ static int gr_handle_out_ep(struct gr_ep *ep) if (!req->curr_desc) return 0; - ctrl = ACCESS_ONCE(req->curr_desc->ctrl); + ctrl = READ_ONCE(req->curr_desc->ctrl); if (ctrl & GR_DESC_OUT_CTRL_EN) return 0; /* Not received yet */ diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index 44924824fa41..c86f89babd57 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -785,7 +785,7 @@ static void io_watchdog_func(unsigned long _ohci) } /* find the last TD processed by the controller. */ - head = hc32_to_cpu(ohci, ACCESS_ONCE(ed->hwHeadP)) & TD_MASK; + head = hc32_to_cpu(ohci, READ_ONCE(ed->hwHeadP)) & TD_MASK; td_start = td; td_next = list_prepare_entry(td, &ed->td_list, td_list); list_for_each_entry_continue(td_next, &ed->td_list, td_list) { diff --git a/drivers/usb/host/uhci-hcd.h b/drivers/usb/host/uhci-hcd.h index 91b22b2ea3aa..09a2a259941b 100644 --- a/drivers/usb/host/uhci-hcd.h +++ b/drivers/usb/host/uhci-hcd.h @@ -186,7 +186,7 @@ struct uhci_qh { * We need a special accessor for the element pointer because it is * subject to asynchronous updates by the controller. */ -#define qh_element(qh) ACCESS_ONCE((qh)->element) +#define qh_element(qh) READ_ONCE((qh)->element) #define LINK_TO_QH(uhci, qh) (UHCI_PTR_QH((uhci)) | \ cpu_to_hc32((uhci), (qh)->dma_handle)) @@ -274,7 +274,7 @@ struct uhci_td { * subject to asynchronous updates by the controller. */ #define td_status(uhci, td) hc32_to_cpu((uhci), \ - ACCESS_ONCE((td)->status)) + READ_ONCE((td)->status)) #define LINK_TO_TD(uhci, td) (cpu_to_hc32((uhci), (td)->dma_handle)) diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index f5a86f651f38..2bc3705a99bd 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -665,7 +665,7 @@ static int vfio_dev_viable(struct device *dev, void *data) { struct vfio_group *group = data; struct vfio_device *device; - struct device_driver *drv = ACCESS_ONCE(dev->driver); + struct device_driver *drv = READ_ONCE(dev->driver); struct vfio_unbound_dev *unbound; int ret = -EINVAL; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 046f6d280af5..35e929f132e8 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -929,7 +929,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) continue; } - tpg = ACCESS_ONCE(vs_tpg[*target]); + tpg = READ_ONCE(vs_tpg[*target]); if (unlikely(!tpg)) { /* Target does not exist, fail the request */ vhost_scsi_send_bad_target(vs, vq, head, out); diff --git a/fs/aio.c b/fs/aio.c index 5a2487217072..e6de7715228c 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -576,7 +576,7 @@ static int kiocb_cancel(struct aio_kiocb *kiocb) * actually has a cancel function, hence the cmpxchg() */ - cancel = ACCESS_ONCE(kiocb->ki_cancel); + cancel = READ_ONCE(kiocb->ki_cancel); do { if (!cancel || cancel == KIOCB_CANCELLED) return -EINVAL; diff --git a/fs/buffer.c b/fs/buffer.c index 170df856bdb9..32ce01f0f95f 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1692,7 +1692,8 @@ static struct buffer_head *create_page_buffers(struct page *page, struct inode * BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) - create_empty_buffers(page, 1 << ACCESS_ONCE(inode->i_blkbits), b_state); + create_empty_buffers(page, 1 << READ_ONCE(inode->i_blkbits), + b_state); return page_buffers(page); } diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 8e704d12a1cf..0083bd4fcaa5 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -373,7 +373,7 @@ void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci) struct fscrypt_info *prev; if (ci == NULL) - ci = ACCESS_ONCE(inode->i_crypt_info); + ci = READ_ONCE(inode->i_crypt_info); if (ci == NULL) return; diff --git a/fs/direct-io.c b/fs/direct-io.c index b53e66d9abd7..98fe1325da9d 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1152,7 +1152,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, get_block_t get_block, dio_iodone_t end_io, dio_submit_t submit_io, int flags) { - unsigned i_blkbits = ACCESS_ONCE(inode->i_blkbits); + unsigned i_blkbits = READ_ONCE(inode->i_blkbits); unsigned blkbits = i_blkbits; unsigned blocksize_mask = (1 << blkbits) - 1; ssize_t retval = -EINVAL; diff --git a/fs/exec.c b/fs/exec.c index 3e14ba25f678..1d6243d9f2b6 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1911,7 +1911,7 @@ void set_dumpable(struct mm_struct *mm, int value) return; do { - old = ACCESS_ONCE(mm->flags); + old = READ_ONCE(mm->flags); new = (old & ~MMF_DUMPABLE_MASK) | value; } while (cmpxchg(&mm->flags, old, new) != old); } diff --git a/fs/fcntl.c b/fs/fcntl.c index 448a1119f0be..57bf2964bb83 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -724,7 +724,7 @@ static void send_sigio_to_task(struct task_struct *p, * F_SETSIG can change ->signum lockless in parallel, make * sure we read it once and use the same value throughout. */ - int signum = ACCESS_ONCE(fown->signum); + int signum = READ_ONCE(fown->signum); if (!sigio_perm(p, fown, signum)) return; diff --git a/fs/fs_pin.c b/fs/fs_pin.c index e747b3d720ee..2d07f292b625 100644 --- a/fs/fs_pin.c +++ b/fs/fs_pin.c @@ -78,7 +78,7 @@ void mnt_pin_kill(struct mount *m) while (1) { struct hlist_node *p; rcu_read_lock(); - p = ACCESS_ONCE(m->mnt_pins.first); + p = READ_ONCE(m->mnt_pins.first); if (!p) { rcu_read_unlock(); break; @@ -92,7 +92,7 @@ void group_pin_kill(struct hlist_head *p) while (1) { struct hlist_node *q; rcu_read_lock(); - q = ACCESS_ONCE(p->first); + q = READ_ONCE(p->first); if (!q) { rcu_read_unlock(); break; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 13c65dd2d37d..a42d89371748 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -33,7 +33,7 @@ static struct fuse_dev *fuse_get_dev(struct file *file) * Lockless access is OK, because file->private data is set * once during mount and is valid until the file is released. */ - return ACCESS_ONCE(file->private_data); + return READ_ONCE(file->private_data); } static void fuse_request_init(struct fuse_req *req, struct page **pages, diff --git a/fs/inode.c b/fs/inode.c index d1e35b53bb23..fd401028a309 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2090,7 +2090,7 @@ void inode_set_flags(struct inode *inode, unsigned int flags, WARN_ON_ONCE(flags & ~mask); do { - old_flags = ACCESS_ONCE(inode->i_flags); + old_flags = READ_ONCE(inode->i_flags); new_flags = (old_flags & ~mask) | flags; } while (unlikely(cmpxchg(&inode->i_flags, old_flags, new_flags) != old_flags)); diff --git a/fs/namei.c b/fs/namei.c index c75ea03ca147..40a0f34bf990 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1209,7 +1209,7 @@ static int follow_managed(struct path *path, struct nameidata *nd) /* Given that we're not holding a lock here, we retain the value in a * local variable for each dentry as we look at it so that we don't see * the components of that value change under us */ - while (managed = ACCESS_ONCE(path->dentry->d_flags), + while (managed = READ_ONCE(path->dentry->d_flags), managed &= DCACHE_MANAGED_DENTRY, unlikely(managed != 0)) { /* Allow the filesystem to manage the transit without i_mutex @@ -1394,7 +1394,7 @@ int follow_down(struct path *path) unsigned managed; int ret; - while (managed = ACCESS_ONCE(path->dentry->d_flags), + while (managed = READ_ONCE(path->dentry->d_flags), unlikely(managed & DCACHE_MANAGED_DENTRY)) { /* Allow the filesystem to manage the transit without i_mutex * being held. diff --git a/fs/namespace.c b/fs/namespace.c index d18deb4c410b..e158ec6b527b 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -353,7 +353,7 @@ int __mnt_want_write(struct vfsmount *m) * incremented count after it has set MNT_WRITE_HOLD. */ smp_mb(); - while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) + while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) cpu_relax(); /* * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 5ceaeb1f6fb6..f439f1c45008 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1081,7 +1081,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) int error; if (flags & LOOKUP_RCU) { - parent = ACCESS_ONCE(dentry->d_parent); + parent = READ_ONCE(dentry->d_parent); dir = d_inode_rcu(parent); if (!dir) return -ECHILD; @@ -1168,7 +1168,7 @@ out_set_verifier: nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); out_valid: if (flags & LOOKUP_RCU) { - if (parent != ACCESS_ONCE(dentry->d_parent)) + if (parent != READ_ONCE(dentry->d_parent)) return -ECHILD; } else dput(parent); @@ -1582,7 +1582,7 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) struct inode *dir; if (flags & LOOKUP_RCU) { - parent = ACCESS_ONCE(dentry->d_parent); + parent = READ_ONCE(dentry->d_parent); dir = d_inode_rcu(parent); if (!dir) return -ECHILD; @@ -1596,7 +1596,7 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) ret = -ECHILD; if (!(flags & LOOKUP_RCU)) dput(parent); - else if (parent != ACCESS_ONCE(dentry->d_parent)) + else if (parent != READ_ONCE(dentry->d_parent)) return -ECHILD; goto out; } diff --git a/fs/proc/array.c b/fs/proc/array.c index 77a8eacbe032..375e8bf0dd24 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -453,7 +453,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, cutime = sig->cutime; cstime = sig->cstime; cgtime = sig->cgtime; - rsslim = ACCESS_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur); + rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur); /* add up live thread stats at the group level */ if (whole) { diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 99dff222fe67..03afd5150916 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -27,7 +27,7 @@ static unsigned mounts_poll(struct file *file, poll_table *wait) poll_wait(file, &p->ns->poll, wait); - event = ACCESS_ONCE(ns->event); + event = READ_ONCE(ns->event); if (m->poll_event != event) { m->poll_event = event; res |= POLLERR | POLLPRI; diff --git a/fs/splice.c b/fs/splice.c index f3084cce0ea6..39e2dc01ac12 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -253,7 +253,7 @@ EXPORT_SYMBOL(add_to_pipe); */ int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { - unsigned int buffers = ACCESS_ONCE(pipe->buffers); + unsigned int buffers = READ_ONCE(pipe->buffers); spd->nr_pages_max = buffers; if (buffers <= PIPE_DEF_BUFFERS) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 1c713fd5b3e6..f46d133c0949 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -381,7 +381,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) * in __get_user_pages if userfaultfd_release waits on the * caller of handle_userfault to release the mmap_sem. */ - if (unlikely(ACCESS_ONCE(ctx->released))) { + if (unlikely(READ_ONCE(ctx->released))) { /* * Don't return VM_FAULT_SIGBUS in this case, so a non * cooperative manager can close the uffd after the @@ -477,7 +477,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) vmf->flags, reason); up_read(&mm->mmap_sem); - if (likely(must_wait && !ACCESS_ONCE(ctx->released) && + if (likely(must_wait && !READ_ONCE(ctx->released) && (return_to_userland ? !signal_pending(current) : !fatal_signal_pending(current)))) { wake_up_poll(&ctx->fd_wqh, POLLIN); @@ -586,7 +586,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, set_current_state(TASK_KILLABLE); if (ewq->msg.event == 0) break; - if (ACCESS_ONCE(ctx->released) || + if (READ_ONCE(ctx->released) || fatal_signal_pending(current)) { /* * &ewq->wq may be queued in fork_event, but @@ -833,7 +833,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) struct userfaultfd_wake_range range = { .len = 0, }; unsigned long new_flags; - ACCESS_ONCE(ctx->released) = true; + WRITE_ONCE(ctx->released, true); if (!mmget_not_zero(mm)) goto wakeup; diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 51bf7b827387..129975970d99 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -592,9 +592,9 @@ xlog_valid_lsn( * a transiently forward state. Instead, we can see the LSN in a * transiently behind state if we happen to race with a cycle wrap. */ - cur_cycle = ACCESS_ONCE(log->l_curr_cycle); + cur_cycle = READ_ONCE(log->l_curr_cycle); smp_rmb(); - cur_block = ACCESS_ONCE(log->l_curr_block); + cur_block = READ_ONCE(log->l_curr_block); if ((CYCLE_LSN(lsn) > cur_cycle) || (CYCLE_LSN(lsn) == cur_cycle && BLOCK_LSN(lsn) > cur_block)) { diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 8fbe259b197c..0a7ce668f8e0 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -236,7 +236,7 @@ static inline unsigned long __ffs64(u64 word) typeof(*ptr) old, new; \ \ do { \ - old = ACCESS_ONCE(*ptr); \ + old = READ_ONCE(*ptr); \ new = (old & ~mask) | bits; \ } while (cmpxchg(ptr, old, new) != old); \ \ @@ -251,7 +251,7 @@ static inline unsigned long __ffs64(u64 word) typeof(*ptr) old, new; \ \ do { \ - old = ACCESS_ONCE(*ptr); \ + old = READ_ONCE(*ptr); \ new = old & ~clear; \ } while (!(old & test) && \ cmpxchg(ptr, old, new) != old); \ diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h index a4be70398ce1..36dd4ffb5715 100644 --- a/include/linux/dynamic_queue_limits.h +++ b/include/linux/dynamic_queue_limits.h @@ -88,7 +88,7 @@ static inline void dql_queued(struct dql *dql, unsigned int count) /* Returns how many objects can be queued, < 0 indicates over limit. */ static inline int dql_avail(const struct dql *dql) { - return ACCESS_ONCE(dql->adj_limit) - ACCESS_ONCE(dql->num_queued); + return READ_ONCE(dql->adj_limit) - READ_ONCE(dql->num_queued); } /* Record number of completed objects and recalculate the limit. */ diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 14bc21c2ee7f..785a00ca4628 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -221,7 +221,7 @@ extern struct page *huge_zero_page; static inline bool is_huge_zero_page(struct page *page) { - return ACCESS_ONCE(huge_zero_page) == page; + return READ_ONCE(huge_zero_page) == page; } static inline bool is_huge_zero_pmd(pmd_t pmd) diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 30294603526f..d95cae09dea0 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -247,7 +247,7 @@ static inline struct team_port *team_get_port_by_index(struct team *team, static inline int team_num_to_port_index(struct team *team, unsigned int num) { - int en_port_count = ACCESS_ONCE(team->en_port_count); + int en_port_count = READ_ONCE(team->en_port_count); if (unlikely(!en_port_count)) return 0; diff --git a/include/linux/llist.h b/include/linux/llist.h index 1957635e6d5f..85abc2915e8d 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -198,7 +198,7 @@ static inline void init_llist_head(struct llist_head *list) */ static inline bool llist_empty(const struct llist_head *head) { - return ACCESS_ONCE(head->first) == NULL; + return READ_ONCE(head->first) == NULL; } static inline struct llist_node *llist_next(struct llist_node *node) diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 2efb08a60e63..f0fc4700b6ff 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -105,7 +105,7 @@ static inline bool pm_runtime_callbacks_present(struct device *dev) static inline void pm_runtime_mark_last_busy(struct device *dev) { - ACCESS_ONCE(dev->power.last_busy) = jiffies; + WRITE_ONCE(dev->power.last_busy, jiffies); } static inline bool pm_runtime_is_irq_safe(struct device *dev) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 4f4f786255ef..3fadb6f9982b 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -983,12 +983,12 @@ static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) static inline int sysctl_sync_period(struct netns_ipvs *ipvs) { - return ACCESS_ONCE(ipvs->sysctl_sync_threshold[1]); + return READ_ONCE(ipvs->sysctl_sync_threshold[1]); } static inline unsigned int sysctl_sync_refresh_period(struct netns_ipvs *ipvs) { - return ACCESS_ONCE(ipvs->sysctl_sync_refresh_period); + return READ_ONCE(ipvs->sysctl_sync_refresh_period); } static inline int sysctl_sync_retries(struct netns_ipvs *ipvs) @@ -1013,7 +1013,7 @@ static inline int sysctl_sloppy_sctp(struct netns_ipvs *ipvs) static inline int sysctl_sync_ports(struct netns_ipvs *ipvs) { - return ACCESS_ONCE(ipvs->sysctl_sync_ports); + return READ_ONCE(ipvs->sysctl_sync_ports); } static inline int sysctl_sync_persist_mode(struct netns_ipvs *ipvs) diff --git a/kernel/acct.c b/kernel/acct.c index 5e72af29ab73..21eedd0dd81a 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -146,7 +146,7 @@ static struct bsd_acct_struct *acct_get(struct pid_namespace *ns) again: smp_rmb(); rcu_read_lock(); - res = to_acct(ACCESS_ONCE(ns->bacct)); + res = to_acct(READ_ONCE(ns->bacct)); if (!res) { rcu_read_unlock(); return NULL; @@ -158,7 +158,7 @@ again: } rcu_read_unlock(); mutex_lock(&res->lock); - if (res != to_acct(ACCESS_ONCE(ns->bacct))) { + if (res != to_acct(READ_ONCE(ns->bacct))) { mutex_unlock(&res->lock); acct_put(res); goto again; diff --git a/kernel/events/core.c b/kernel/events/core.c index 824a583079a1..8fd2f2d1358a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1200,7 +1200,7 @@ perf_event_ctx_lock_nested(struct perf_event *event, int nesting) again: rcu_read_lock(); - ctx = ACCESS_ONCE(event->ctx); + ctx = READ_ONCE(event->ctx); if (!atomic_inc_not_zero(&ctx->refcount)) { rcu_read_unlock(); goto again; @@ -5302,8 +5302,8 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) if (!rb) goto aux_unlock; - aux_offset = ACCESS_ONCE(rb->user_page->aux_offset); - aux_size = ACCESS_ONCE(rb->user_page->aux_size); + aux_offset = READ_ONCE(rb->user_page->aux_offset); + aux_size = READ_ONCE(rb->user_page->aux_size); if (aux_offset < perf_data_size(rb) + PAGE_SIZE) goto aux_unlock; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index f684d8e5fa2b..f3e37971c842 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -381,7 +381,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle, * (B) <-> (C) ordering is still observed by the pmu driver. */ if (!rb->aux_overwrite) { - aux_tail = ACCESS_ONCE(rb->user_page->aux_tail); + aux_tail = READ_ONCE(rb->user_page->aux_tail); handle->wakeup = rb->aux_wakeup + rb->aux_watermark; if (aux_head - aux_tail < perf_aux_size(rb)) handle->size = CIRC_SPACE(aux_head, aux_tail, perf_aux_size(rb)); diff --git a/kernel/exit.c b/kernel/exit.c index f6cad39f35df..6b4298a41167 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1339,7 +1339,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace, * Ensure that EXIT_ZOMBIE -> EXIT_DEAD/EXIT_TRACE transition * can't confuse the checks below. */ - int exit_state = ACCESS_ONCE(p->exit_state); + int exit_state = READ_ONCE(p->exit_state); int ret; if (unlikely(exit_state == EXIT_DEAD)) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 81279c6602ff..845f3805c73d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2724,7 +2724,7 @@ rb_reserve_next_event(struct ring_buffer *buffer, * if it happened, we have to fail the write. */ barrier(); - if (unlikely(ACCESS_ONCE(cpu_buffer->buffer) != buffer)) { + if (unlikely(READ_ONCE(cpu_buffer->buffer) != buffer)) { local_dec(&cpu_buffer->committing); local_dec(&cpu_buffer->commits); return NULL; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 652c682707cd..9050c8b3ccde 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1459,7 +1459,7 @@ extern struct trace_event_file *find_event_file(struct trace_array *tr, static inline void *event_file_data(struct file *filp) { - return ACCESS_ONCE(file_inode(filp)->i_private); + return READ_ONCE(file_inode(filp)->i_private); } extern struct mutex event_mutex; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 49cb41412eec..780262210c9a 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -77,7 +77,7 @@ check_stack(unsigned long ip, unsigned long *stack) { unsigned long this_size, flags; unsigned long *p, *top, *start; static int tracer_frame; - int frame_size = ACCESS_ONCE(tracer_frame); + int frame_size = READ_ONCE(tracer_frame); int i, x; this_size = ((unsigned long)stack) & (THREAD_SIZE-1); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index c490f1e4313b..d32b45662fb6 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -894,7 +894,7 @@ static bool new_idmap_permitted(const struct file *file, int proc_setgroups_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; - unsigned long userns_flags = ACCESS_ONCE(ns->flags); + unsigned long userns_flags = READ_ONCE(ns->flags); seq_printf(seq, "%s\n", (userns_flags & USERNS_SETGROUPS_ALLOWED) ? diff --git a/lib/assoc_array.c b/lib/assoc_array.c index 155c55d8db5f..fe7953aead82 100644 --- a/lib/assoc_array.c +++ b/lib/assoc_array.c @@ -39,7 +39,7 @@ begin_node: /* Descend through a shortcut */ shortcut = assoc_array_ptr_to_shortcut(cursor); smp_read_barrier_depends(); - cursor = ACCESS_ONCE(shortcut->next_node); + cursor = READ_ONCE(shortcut->next_node); } node = assoc_array_ptr_to_node(cursor); @@ -55,7 +55,7 @@ begin_node: */ has_meta = 0; for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { - ptr = ACCESS_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); has_meta |= (unsigned long)ptr; if (ptr && assoc_array_ptr_is_leaf(ptr)) { /* We need a barrier between the read of the pointer @@ -89,7 +89,7 @@ continue_node: smp_read_barrier_depends(); for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { - ptr = ACCESS_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); if (assoc_array_ptr_is_meta(ptr)) { cursor = ptr; goto begin_node; @@ -98,7 +98,7 @@ continue_node: finished_node: /* Move up to the parent (may need to skip back over a shortcut) */ - parent = ACCESS_ONCE(node->back_pointer); + parent = READ_ONCE(node->back_pointer); slot = node->parent_slot; if (parent == stop) return 0; @@ -107,7 +107,7 @@ finished_node: shortcut = assoc_array_ptr_to_shortcut(parent); smp_read_barrier_depends(); cursor = parent; - parent = ACCESS_ONCE(shortcut->back_pointer); + parent = READ_ONCE(shortcut->back_pointer); slot = shortcut->parent_slot; if (parent == stop) return 0; @@ -147,7 +147,7 @@ int assoc_array_iterate(const struct assoc_array *array, void *iterator_data), void *iterator_data) { - struct assoc_array_ptr *root = ACCESS_ONCE(array->root); + struct assoc_array_ptr *root = READ_ONCE(array->root); if (!root) return 0; @@ -194,7 +194,7 @@ assoc_array_walk(const struct assoc_array *array, pr_devel("-->%s()\n", __func__); - cursor = ACCESS_ONCE(array->root); + cursor = READ_ONCE(array->root); if (!cursor) return assoc_array_walk_tree_empty; @@ -220,7 +220,7 @@ consider_node: slot = segments >> (level & ASSOC_ARRAY_KEY_CHUNK_MASK); slot &= ASSOC_ARRAY_FAN_MASK; - ptr = ACCESS_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); pr_devel("consider slot %x [ix=%d type=%lu]\n", slot, level, (unsigned long)ptr & 3); @@ -294,7 +294,7 @@ follow_shortcut: } while (sc_level < shortcut->skip_to_level); /* The shortcut matches the leaf's index to this point. */ - cursor = ACCESS_ONCE(shortcut->next_node); + cursor = READ_ONCE(shortcut->next_node); if (((level ^ sc_level) & ~ASSOC_ARRAY_KEY_CHUNK_MASK) != 0) { level = sc_level; goto jumped; @@ -337,7 +337,7 @@ void *assoc_array_find(const struct assoc_array *array, * the terminal node. */ for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) { - ptr = ACCESS_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); if (ptr && assoc_array_ptr_is_leaf(ptr)) { /* We need a barrier between the read of the pointer * and dereferencing the pointer - but only if we are diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c index f346715e2255..81770a55cb16 100644 --- a/lib/dynamic_queue_limits.c +++ b/lib/dynamic_queue_limits.c @@ -20,7 +20,7 @@ void dql_completed(struct dql *dql, unsigned int count) unsigned int ovlimit, completed, num_queued; bool all_prev_completed; - num_queued = ACCESS_ONCE(dql->num_queued); + num_queued = READ_ONCE(dql->num_queued); /* Can't complete more than what's in queue */ BUG_ON(count > num_queued - dql->num_completed); diff --git a/lib/llist.c b/lib/llist.c index ae5872b1df0c..7062e931a7bb 100644 --- a/lib/llist.c +++ b/lib/llist.c @@ -41,7 +41,7 @@ bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, struct llist_node *first; do { - new_last->next = first = ACCESS_ONCE(head->first); + new_last->next = first = READ_ONCE(head->first); } while (cmpxchg(&head->first, first, new_first) != first); return !first; diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 86c3385b9eb3..1746bae94d41 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -620,8 +620,8 @@ char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_sp rcu_read_lock(); for (i = 0; i < depth; i++, d = p) { - p = ACCESS_ONCE(d->d_parent); - array[i] = ACCESS_ONCE(d->d_name.name); + p = READ_ONCE(d->d_parent); + array[i] = READ_ONCE(d->d_name.name); if (p == d) { if (i) array[i] = ""; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 269b5df58543..c3bf907a03ee 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2715,7 +2715,7 @@ static unsigned long deferred_split_count(struct shrinker *shrink, struct shrink_control *sc) { struct pglist_data *pgdata = NODE_DATA(sc->nid); - return ACCESS_ONCE(pgdata->split_queue_len); + return READ_ONCE(pgdata->split_queue_len); } static unsigned long deferred_split_scan(struct shrinker *shrink, diff --git a/net/core/dev.c b/net/core/dev.c index 11596a302a26..61559ca3980b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3725,7 +3725,7 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, flow_table = rcu_dereference(rxqueue->rps_flow_table); if (flow_table && flow_id <= flow_table->mask) { rflow = &flow_table->flows[flow_id]; - cpu = ACCESS_ONCE(rflow->cpu); + cpu = READ_ONCE(rflow->cpu); if (rflow->filter == filter_id && cpu < nr_cpu_ids && ((int)(per_cpu(softnet_data, cpu).input_queue_head - rflow->last_qtail) < diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 6e1e10ff433a..3b2034f6d49d 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3377,7 +3377,7 @@ static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev) static void pktgen_xmit(struct pktgen_dev *pkt_dev) { - unsigned int burst = ACCESS_ONCE(pkt_dev->burst); + unsigned int burst = READ_ONCE(pkt_dev->burst); struct net_device *odev = pkt_dev->odev; struct netdev_queue *txq; struct sk_buff *skb; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index af74d0433453..f9597ba26599 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -164,7 +164,7 @@ static void inet_frag_worker(struct work_struct *work) local_bh_disable(); - for (i = ACCESS_ONCE(f->next_bucket); budget; --budget) { + for (i = READ_ONCE(f->next_bucket); budget; --budget) { evicted += inet_evict_bucket(f, &f->hash[i]); i = (i + 1) & (INETFRAGS_HASHSZ - 1); if (evicted > INETFRAGS_EVICT_MAX) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3d9f1c2f81c5..c0864562083b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -495,7 +495,7 @@ u32 ip_idents_reserve(u32 hash, int segs) { u32 *p_tstamp = ip_tstamps + hash % IP_IDENTS_SZ; atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ; - u32 old = ACCESS_ONCE(*p_tstamp); + u32 old = READ_ONCE(*p_tstamp); u32 now = (u32)jiffies; u32 new, delta = 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 0bc9e46a5369..48531da1aba6 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1908,7 +1908,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len)) goto send_now; - win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor); + win_divisor = READ_ONCE(sysctl_tcp_tso_win_divisor); if (win_divisor) { u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ebfbccae62fd..02ec9a349303 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1853,7 +1853,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ /* if we're overly short, let UDP handle it */ - encap_rcv = ACCESS_ONCE(up->encap_rcv); + encap_rcv = READ_ONCE(up->encap_rcv); if (encap_rcv) { int ret; @@ -2298,7 +2298,7 @@ void udp_destroy_sock(struct sock *sk) unlock_sock_fast(sk, slow); if (static_key_false(&udp_encap_needed) && up->encap_type) { void (*encap_destroy)(struct sock *sk); - encap_destroy = ACCESS_ONCE(up->encap_destroy); + encap_destroy = READ_ONCE(up->encap_destroy); if (encap_destroy) encap_destroy(sk); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a1c24443cd9e..dab946554157 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -490,7 +490,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, if (!t) goto out; - tproto = ACCESS_ONCE(t->parms.proto); + tproto = READ_ONCE(t->parms.proto); if (tproto != ipproto && tproto != 0) goto out; @@ -899,7 +899,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto, t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr); if (t) { - u8 tproto = ACCESS_ONCE(t->parms.proto); + u8 tproto = READ_ONCE(t->parms.proto); if (tproto != ipproto && tproto != 0) goto drop; @@ -1233,7 +1233,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - tproto = ACCESS_ONCE(t->parms.proto); + tproto = READ_ONCE(t->parms.proto); if (tproto != IPPROTO_IPIP && tproto != 0) return -1; @@ -1303,7 +1303,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; - tproto = ACCESS_ONCE(t->parms.proto); + tproto = READ_ONCE(t->parms.proto); if ((tproto != IPPROTO_IPV6 && tproto != 0) || ip6_tnl_addr_conflict(t, ipv6h)) return -1; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 40d7234c27b9..3f30fa313bf2 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -606,7 +606,7 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ /* if we're overly short, let UDP handle it */ - encap_rcv = ACCESS_ONCE(up->encap_rcv); + encap_rcv = READ_ONCE(up->encap_rcv); if (encap_rcv) { int ret; @@ -1432,7 +1432,7 @@ void udpv6_destroy_sock(struct sock *sk) if (static_key_false(&udpv6_encap_needed) && up->encap_type) { void (*encap_destroy)(struct sock *sk); - encap_destroy = ACCESS_ONCE(up->encap_destroy); + encap_destroy = READ_ONCE(up->encap_destroy); if (encap_destroy) encap_destroy(sk); } diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index dd3e83328ad5..82cb93f66b9b 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -193,7 +193,7 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev, */ rcv = rcu_dereference(sap->rcv_func); dest = llc_pdu_type(skb); - sap_handler = dest ? ACCESS_ONCE(llc_type_handlers[dest - 1]) : NULL; + sap_handler = dest ? READ_ONCE(llc_type_handlers[dest - 1]) : NULL; if (unlikely(!sap_handler)) { if (rcv) rcv(skb, dev, pt, orig_dev); @@ -214,7 +214,7 @@ drop: kfree_skb(skb); goto out; handle_station: - sta_handler = ACCESS_ONCE(llc_station_handler); + sta_handler = READ_ONCE(llc_station_handler); if (!sta_handler) goto drop; sta_handler(skb); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 69615016d5bf..214d2ba02877 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -2008,7 +2008,7 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate, static int sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo) { - u16 rate = ACCESS_ONCE(sta_get_last_rx_stats(sta)->last_rate); + u16 rate = READ_ONCE(sta_get_last_rx_stats(sta)->last_rate); if (rate == STA_STATS_RATE_INVALID) return -EINVAL; diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c index d177dd066504..4d748975117d 100644 --- a/net/netlabel/netlabel_calipso.c +++ b/net/netlabel/netlabel_calipso.c @@ -393,7 +393,7 @@ EXPORT_SYMBOL(netlbl_calipso_ops_register); static const struct netlbl_calipso_ops *netlbl_calipso_ops_get(void) { - return ACCESS_ONCE(calipso_ops); + return READ_ONCE(calipso_ops); } /** diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d396cb61a280..eb866647a27a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -14201,7 +14201,7 @@ static bool __nl80211_unexpected_frame(struct net_device *dev, u8 cmd, struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct sk_buff *msg; void *hdr; - u32 nlportid = ACCESS_ONCE(wdev->ap_unexpected_nlportid); + u32 nlportid = READ_ONCE(wdev->ap_unexpected_nlportid); if (!nlportid) return false; diff --git a/sound/firewire/amdtp-am824.c b/sound/firewire/amdtp-am824.c index 23ccddb20de1..4210e5c6262e 100644 --- a/sound/firewire/amdtp-am824.c +++ b/sound/firewire/amdtp-am824.c @@ -247,7 +247,7 @@ void amdtp_am824_midi_trigger(struct amdtp_stream *s, unsigned int port, struct amdtp_am824 *p = s->protocol; if (port < p->midi_ports) - ACCESS_ONCE(p->midi[port]) = midi; + WRITE_ONCE(p->midi[port], midi); } EXPORT_SYMBOL_GPL(amdtp_am824_midi_trigger); @@ -336,7 +336,7 @@ static unsigned int process_rx_data_blocks(struct amdtp_stream *s, __be32 *buffe unsigned int data_blocks, unsigned int *syt) { struct amdtp_am824 *p = s->protocol; - struct snd_pcm_substream *pcm = ACCESS_ONCE(s->pcm); + struct snd_pcm_substream *pcm = READ_ONCE(s->pcm); unsigned int pcm_frames; if (pcm) { @@ -357,7 +357,7 @@ static unsigned int process_tx_data_blocks(struct amdtp_stream *s, __be32 *buffe unsigned int data_blocks, unsigned int *syt) { struct amdtp_am824 *p = s->protocol; - struct snd_pcm_substream *pcm = ACCESS_ONCE(s->pcm); + struct snd_pcm_substream *pcm = READ_ONCE(s->pcm); unsigned int pcm_frames; if (pcm) { diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index 3fc581a5ad62..4a1dc145327b 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -376,7 +376,7 @@ static void update_pcm_pointers(struct amdtp_stream *s, ptr = s->pcm_buffer_pointer + frames; if (ptr >= pcm->runtime->buffer_size) ptr -= pcm->runtime->buffer_size; - ACCESS_ONCE(s->pcm_buffer_pointer) = ptr; + WRITE_ONCE(s->pcm_buffer_pointer, ptr); s->pcm_period_pointer += frames; if (s->pcm_period_pointer >= pcm->runtime->period_size) { @@ -388,7 +388,7 @@ static void update_pcm_pointers(struct amdtp_stream *s, static void pcm_period_tasklet(unsigned long data) { struct amdtp_stream *s = (void *)data; - struct snd_pcm_substream *pcm = ACCESS_ONCE(s->pcm); + struct snd_pcm_substream *pcm = READ_ONCE(s->pcm); if (pcm) snd_pcm_period_elapsed(pcm); @@ -453,7 +453,7 @@ static int handle_out_packet(struct amdtp_stream *s, s->data_block_counter = (s->data_block_counter + data_blocks) & 0xff; - buffer[0] = cpu_to_be32(ACCESS_ONCE(s->source_node_id_field) | + buffer[0] = cpu_to_be32(READ_ONCE(s->source_node_id_field) | (s->data_block_quadlets << CIP_DBS_SHIFT) | ((s->sph << CIP_SPH_SHIFT) & CIP_SPH_MASK) | s->data_block_counter); @@ -472,7 +472,7 @@ static int handle_out_packet(struct amdtp_stream *s, if (queue_out_packet(s, payload_length) < 0) return -EIO; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm && pcm_frames > 0) update_pcm_pointers(s, pcm, pcm_frames); @@ -504,7 +504,7 @@ static int handle_out_packet_without_header(struct amdtp_stream *s, if (queue_out_packet(s, payload_length) < 0) return -EIO; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm && pcm_frames > 0) update_pcm_pointers(s, pcm, pcm_frames); @@ -621,7 +621,7 @@ end: if (queue_in_packet(s) < 0) return -EIO; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm && pcm_frames > 0) update_pcm_pointers(s, pcm, pcm_frames); @@ -649,7 +649,7 @@ static int handle_in_packet_without_header(struct amdtp_stream *s, if (queue_in_packet(s) < 0) return -EIO; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm && pcm_frames > 0) update_pcm_pointers(s, pcm, pcm_frames); @@ -947,7 +947,7 @@ unsigned long amdtp_stream_pcm_pointer(struct amdtp_stream *s) if (!in_interrupt() && amdtp_stream_running(s)) fw_iso_context_flush_completions(s->context); - return ACCESS_ONCE(s->pcm_buffer_pointer); + return READ_ONCE(s->pcm_buffer_pointer); } EXPORT_SYMBOL(amdtp_stream_pcm_pointer); @@ -977,9 +977,8 @@ EXPORT_SYMBOL(amdtp_stream_pcm_ack); void amdtp_stream_update(struct amdtp_stream *s) { /* Precomputing. */ - ACCESS_ONCE(s->source_node_id_field) = - (fw_parent_device(s->unit)->card->node_id << CIP_SID_SHIFT) & - CIP_SID_MASK; + WRITE_ONCE(s->source_node_id_field, + (fw_parent_device(s->unit)->card->node_id << CIP_SID_SHIFT) & CIP_SID_MASK); } EXPORT_SYMBOL(amdtp_stream_update); @@ -1022,7 +1021,7 @@ void amdtp_stream_pcm_abort(struct amdtp_stream *s) { struct snd_pcm_substream *pcm; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm) snd_pcm_stop_xrun(pcm); } diff --git a/sound/firewire/amdtp-stream.h b/sound/firewire/amdtp-stream.h index ed6eafd10992..f9abd8b07ce6 100644 --- a/sound/firewire/amdtp-stream.h +++ b/sound/firewire/amdtp-stream.h @@ -220,7 +220,7 @@ static inline bool amdtp_stream_pcm_running(struct amdtp_stream *s) static inline void amdtp_stream_pcm_trigger(struct amdtp_stream *s, struct snd_pcm_substream *pcm) { - ACCESS_ONCE(s->pcm) = pcm; + WRITE_ONCE(s->pcm, pcm); } static inline bool cip_sfc_is_base_44100(enum cip_sfc sfc) diff --git a/sound/firewire/digi00x/amdtp-dot.c b/sound/firewire/digi00x/amdtp-dot.c index 1453c34ce99f..4a884a335248 100644 --- a/sound/firewire/digi00x/amdtp-dot.c +++ b/sound/firewire/digi00x/amdtp-dot.c @@ -327,7 +327,7 @@ void amdtp_dot_midi_trigger(struct amdtp_stream *s, unsigned int port, struct amdtp_dot *p = s->protocol; if (port < MAX_MIDI_PORTS) - ACCESS_ONCE(p->midi[port]) = midi; + WRITE_ONCE(p->midi[port], midi); } static unsigned int process_tx_data_blocks(struct amdtp_stream *s, @@ -338,7 +338,7 @@ static unsigned int process_tx_data_blocks(struct amdtp_stream *s, struct snd_pcm_substream *pcm; unsigned int pcm_frames; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm) { read_pcm_s32(s, pcm, buffer, data_blocks); pcm_frames = data_blocks; @@ -359,7 +359,7 @@ static unsigned int process_rx_data_blocks(struct amdtp_stream *s, struct snd_pcm_substream *pcm; unsigned int pcm_frames; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm) { write_pcm_s32(s, pcm, buffer, data_blocks); pcm_frames = data_blocks; diff --git a/sound/firewire/fireface/amdtp-ff.c b/sound/firewire/fireface/amdtp-ff.c index 780da9deb2f0..77c7598b61ab 100644 --- a/sound/firewire/fireface/amdtp-ff.c +++ b/sound/firewire/fireface/amdtp-ff.c @@ -108,7 +108,7 @@ static unsigned int process_rx_data_blocks(struct amdtp_stream *s, unsigned int data_blocks, unsigned int *syt) { - struct snd_pcm_substream *pcm = ACCESS_ONCE(s->pcm); + struct snd_pcm_substream *pcm = READ_ONCE(s->pcm); unsigned int pcm_frames; if (pcm) { @@ -127,7 +127,7 @@ static unsigned int process_tx_data_blocks(struct amdtp_stream *s, unsigned int data_blocks, unsigned int *syt) { - struct snd_pcm_substream *pcm = ACCESS_ONCE(s->pcm); + struct snd_pcm_substream *pcm = READ_ONCE(s->pcm); unsigned int pcm_frames; if (pcm) { diff --git a/sound/firewire/fireface/ff-midi.c b/sound/firewire/fireface/ff-midi.c index 949ee56b4e0e..6a49611ee462 100644 --- a/sound/firewire/fireface/ff-midi.c +++ b/sound/firewire/fireface/ff-midi.c @@ -22,7 +22,7 @@ static int midi_playback_open(struct snd_rawmidi_substream *substream) ff->running_status[substream->number] = 0; ff->rx_midi_error[substream->number] = false; - ACCESS_ONCE(ff->rx_midi_substreams[substream->number]) = substream; + WRITE_ONCE(ff->rx_midi_substreams[substream->number], substream); return 0; } @@ -38,7 +38,7 @@ static int midi_playback_close(struct snd_rawmidi_substream *substream) struct snd_ff *ff = substream->rmidi->private_data; cancel_work_sync(&ff->rx_midi_work[substream->number]); - ACCESS_ONCE(ff->rx_midi_substreams[substream->number]) = NULL; + WRITE_ONCE(ff->rx_midi_substreams[substream->number], NULL); return 0; } @@ -52,10 +52,10 @@ static void midi_capture_trigger(struct snd_rawmidi_substream *substream, spin_lock_irqsave(&ff->lock, flags); if (up) - ACCESS_ONCE(ff->tx_midi_substreams[substream->number]) = - substream; + WRITE_ONCE(ff->tx_midi_substreams[substream->number], + substream); else - ACCESS_ONCE(ff->tx_midi_substreams[substream->number]) = NULL; + WRITE_ONCE(ff->tx_midi_substreams[substream->number], NULL); spin_unlock_irqrestore(&ff->lock, flags); } diff --git a/sound/firewire/fireface/ff-transaction.c b/sound/firewire/fireface/ff-transaction.c index dd6c8e839647..332b29f8ed75 100644 --- a/sound/firewire/fireface/ff-transaction.c +++ b/sound/firewire/fireface/ff-transaction.c @@ -12,7 +12,7 @@ static void finish_transmit_midi_msg(struct snd_ff *ff, unsigned int port, int rcode) { struct snd_rawmidi_substream *substream = - ACCESS_ONCE(ff->rx_midi_substreams[port]); + READ_ONCE(ff->rx_midi_substreams[port]); if (rcode_is_permanent_error(rcode)) { ff->rx_midi_error[port] = true; @@ -60,7 +60,7 @@ static inline void fill_midi_buf(struct snd_ff *ff, unsigned int port, static void transmit_midi_msg(struct snd_ff *ff, unsigned int port) { struct snd_rawmidi_substream *substream = - ACCESS_ONCE(ff->rx_midi_substreams[port]); + READ_ONCE(ff->rx_midi_substreams[port]); u8 *buf = (u8 *)ff->msg_buf[port]; int i, len; @@ -159,7 +159,7 @@ static void handle_midi_msg(struct fw_card *card, struct fw_request *request, */ index = (quad >> 8) & 0xff; if (index > 0) { - substream = ACCESS_ONCE(ff->tx_midi_substreams[0]); + substream = READ_ONCE(ff->tx_midi_substreams[0]); if (substream != NULL) { byte = quad & 0xff; snd_rawmidi_receive(substream, &byte, 1); @@ -169,7 +169,7 @@ static void handle_midi_msg(struct fw_card *card, struct fw_request *request, /* Message in second port. */ index = (quad >> 24) & 0xff; if (index > 0) { - substream = ACCESS_ONCE(ff->tx_midi_substreams[1]); + substream = READ_ONCE(ff->tx_midi_substreams[1]); if (substream != NULL) { byte = (quad >> 16) & 0xff; snd_rawmidi_receive(substream, &byte, 1); diff --git a/sound/firewire/isight.c b/sound/firewire/isight.c index 5826aa8362f1..46092fa3ff9b 100644 --- a/sound/firewire/isight.c +++ b/sound/firewire/isight.c @@ -96,7 +96,7 @@ static void isight_update_pointers(struct isight *isight, unsigned int count) ptr += count; if (ptr >= runtime->buffer_size) ptr -= runtime->buffer_size; - ACCESS_ONCE(isight->buffer_pointer) = ptr; + WRITE_ONCE(isight->buffer_pointer, ptr); isight->period_counter += count; if (isight->period_counter >= runtime->period_size) { @@ -111,7 +111,7 @@ static void isight_samples(struct isight *isight, struct snd_pcm_runtime *runtime; unsigned int count1; - if (!ACCESS_ONCE(isight->pcm_running)) + if (!READ_ONCE(isight->pcm_running)) return; runtime = isight->pcm->runtime; @@ -131,7 +131,7 @@ static void isight_samples(struct isight *isight, static void isight_pcm_abort(struct isight *isight) { - if (ACCESS_ONCE(isight->pcm_active)) + if (READ_ONCE(isight->pcm_active)) snd_pcm_stop_xrun(isight->pcm); } @@ -141,7 +141,7 @@ static void isight_dropped_samples(struct isight *isight, unsigned int total) u32 dropped; unsigned int count1; - if (!ACCESS_ONCE(isight->pcm_running)) + if (!READ_ONCE(isight->pcm_running)) return; runtime = isight->pcm->runtime; @@ -293,7 +293,7 @@ static int isight_hw_params(struct snd_pcm_substream *substream, if (err < 0) return err; - ACCESS_ONCE(isight->pcm_active) = true; + WRITE_ONCE(isight->pcm_active, true); return 0; } @@ -331,7 +331,7 @@ static int isight_hw_free(struct snd_pcm_substream *substream) { struct isight *isight = substream->private_data; - ACCESS_ONCE(isight->pcm_active) = false; + WRITE_ONCE(isight->pcm_active, false); mutex_lock(&isight->mutex); isight_stop_streaming(isight); @@ -424,10 +424,10 @@ static int isight_trigger(struct snd_pcm_substream *substream, int cmd) switch (cmd) { case SNDRV_PCM_TRIGGER_START: - ACCESS_ONCE(isight->pcm_running) = true; + WRITE_ONCE(isight->pcm_running, true); break; case SNDRV_PCM_TRIGGER_STOP: - ACCESS_ONCE(isight->pcm_running) = false; + WRITE_ONCE(isight->pcm_running, false); break; default: return -EINVAL; @@ -439,7 +439,7 @@ static snd_pcm_uframes_t isight_pointer(struct snd_pcm_substream *substream) { struct isight *isight = substream->private_data; - return ACCESS_ONCE(isight->buffer_pointer); + return READ_ONCE(isight->buffer_pointer); } static int isight_create_pcm(struct isight *isight) diff --git a/sound/firewire/motu/amdtp-motu.c b/sound/firewire/motu/amdtp-motu.c index 96f0091144bb..f0555a24d90e 100644 --- a/sound/firewire/motu/amdtp-motu.c +++ b/sound/firewire/motu/amdtp-motu.c @@ -310,7 +310,7 @@ static unsigned int process_tx_data_blocks(struct amdtp_stream *s, if (p->midi_ports) read_midi_messages(s, buffer, data_blocks); - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (data_blocks > 0 && pcm) read_pcm_s32(s, pcm->runtime, buffer, data_blocks); @@ -374,7 +374,7 @@ static unsigned int process_rx_data_blocks(struct amdtp_stream *s, if (p->midi_ports) write_midi_messages(s, buffer, data_blocks); - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm) write_pcm_s32(s, pcm->runtime, buffer, data_blocks); else diff --git a/sound/firewire/oxfw/oxfw-scs1x.c b/sound/firewire/oxfw/oxfw-scs1x.c index 02d595665898..f33497cdc706 100644 --- a/sound/firewire/oxfw/oxfw-scs1x.c +++ b/sound/firewire/oxfw/oxfw-scs1x.c @@ -112,7 +112,7 @@ static void handle_hss(struct fw_card *card, struct fw_request *request, } if (length >= 1) { - stream = ACCESS_ONCE(scs->input); + stream = READ_ONCE(scs->input); if (stream) midi_input_packet(scs, stream, data, length); } @@ -183,7 +183,7 @@ static void scs_output_work(struct work_struct *work) if (scs->transaction_running) return; - stream = ACCESS_ONCE(scs->output); + stream = READ_ONCE(scs->output); if (!stream || scs->error) { scs->output_idle = true; wake_up(&scs->idle_wait); @@ -291,9 +291,9 @@ static void midi_capture_trigger(struct snd_rawmidi_substream *stream, int up) if (up) { scs->input_escape_count = 0; - ACCESS_ONCE(scs->input) = stream; + WRITE_ONCE(scs->input, stream); } else { - ACCESS_ONCE(scs->input) = NULL; + WRITE_ONCE(scs->input, NULL); } } @@ -319,10 +319,10 @@ static void midi_playback_trigger(struct snd_rawmidi_substream *stream, int up) scs->transaction_bytes = 0; scs->error = false; - ACCESS_ONCE(scs->output) = stream; + WRITE_ONCE(scs->output, stream); schedule_work(&scs->work); } else { - ACCESS_ONCE(scs->output) = NULL; + WRITE_ONCE(scs->output, NULL); } } static void midi_playback_drain(struct snd_rawmidi_substream *stream) diff --git a/sound/firewire/tascam/amdtp-tascam.c b/sound/firewire/tascam/amdtp-tascam.c index 6aff1fc1c72d..ab482423c165 100644 --- a/sound/firewire/tascam/amdtp-tascam.c +++ b/sound/firewire/tascam/amdtp-tascam.c @@ -124,7 +124,7 @@ static unsigned int process_tx_data_blocks(struct amdtp_stream *s, { struct snd_pcm_substream *pcm; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (data_blocks > 0 && pcm) read_pcm_s32(s, pcm, buffer, data_blocks); @@ -143,7 +143,7 @@ static unsigned int process_rx_data_blocks(struct amdtp_stream *s, /* This field is not used. */ *syt = 0x0000; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm) write_pcm_s32(s, pcm, buffer, data_blocks); else diff --git a/sound/firewire/tascam/tascam-transaction.c b/sound/firewire/tascam/tascam-transaction.c index 8967c52f5032..2ad692dd4b13 100644 --- a/sound/firewire/tascam/tascam-transaction.c +++ b/sound/firewire/tascam/tascam-transaction.c @@ -148,7 +148,7 @@ static void async_midi_port_callback(struct fw_card *card, int rcode, void *callback_data) { struct snd_fw_async_midi_port *port = callback_data; - struct snd_rawmidi_substream *substream = ACCESS_ONCE(port->substream); + struct snd_rawmidi_substream *substream = READ_ONCE(port->substream); /* This port is closed. */ if (substream == NULL) @@ -173,7 +173,7 @@ static void midi_port_work(struct work_struct *work) { struct snd_fw_async_midi_port *port = container_of(work, struct snd_fw_async_midi_port, work); - struct snd_rawmidi_substream *substream = ACCESS_ONCE(port->substream); + struct snd_rawmidi_substream *substream = READ_ONCE(port->substream); int generation; /* Under transacting or error state. */ @@ -282,7 +282,7 @@ static void handle_midi_tx(struct fw_card *card, struct fw_request *request, bytes = 3; } - substream = ACCESS_ONCE(tscm->tx_midi_substreams[port]); + substream = READ_ONCE(tscm->tx_midi_substreams[port]); if (substream != NULL) snd_rawmidi_receive(substream, b + 1, bytes); } diff --git a/sound/soc/xtensa/xtfpga-i2s.c b/sound/soc/xtensa/xtfpga-i2s.c index 8382ffa3bcaf..2472144b329e 100644 --- a/sound/soc/xtensa/xtfpga-i2s.c +++ b/sound/soc/xtensa/xtfpga-i2s.c @@ -165,7 +165,7 @@ static bool xtfpga_pcm_push_tx(struct xtfpga_i2s *i2s) tx_substream = rcu_dereference(i2s->tx_substream); tx_active = tx_substream && snd_pcm_running(tx_substream); if (tx_active) { - unsigned tx_ptr = ACCESS_ONCE(i2s->tx_ptr); + unsigned tx_ptr = READ_ONCE(i2s->tx_ptr); unsigned new_tx_ptr = i2s->tx_fn(i2s, tx_substream->runtime, tx_ptr); @@ -437,7 +437,7 @@ static int xtfpga_pcm_trigger(struct snd_pcm_substream *substream, int cmd) case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: - ACCESS_ONCE(i2s->tx_ptr) = 0; + WRITE_ONCE(i2s->tx_ptr, 0); rcu_assign_pointer(i2s->tx_substream, substream); xtfpga_pcm_refill_fifo(i2s); break; @@ -459,7 +459,7 @@ static snd_pcm_uframes_t xtfpga_pcm_pointer(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; struct xtfpga_i2s *i2s = runtime->private_data; - snd_pcm_uframes_t pos = ACCESS_ONCE(i2s->tx_ptr); + snd_pcm_uframes_t pos = READ_ONCE(i2s->tx_ptr); return pos < runtime->buffer_size ? pos : 0; } diff --git a/sound/usb/bcd2000/bcd2000.c b/sound/usb/bcd2000/bcd2000.c index 7371e5b06035..fc579f330601 100644 --- a/sound/usb/bcd2000/bcd2000.c +++ b/sound/usb/bcd2000/bcd2000.c @@ -108,7 +108,7 @@ static void bcd2000_midi_handle_input(struct bcd2000 *bcd2k, unsigned int payload_length, tocopy; struct snd_rawmidi_substream *midi_receive_substream; - midi_receive_substream = ACCESS_ONCE(bcd2k->midi_receive_substream); + midi_receive_substream = READ_ONCE(bcd2k->midi_receive_substream); if (!midi_receive_substream) return; @@ -139,7 +139,7 @@ static void bcd2000_midi_send(struct bcd2000 *bcd2k) BUILD_BUG_ON(sizeof(device_cmd_prefix) >= BUFSIZE); - midi_out_substream = ACCESS_ONCE(bcd2k->midi_out_substream); + midi_out_substream = READ_ONCE(bcd2k->midi_out_substream); if (!midi_out_substream) return; diff --git a/tools/arch/x86/include/asm/atomic.h b/tools/arch/x86/include/asm/atomic.h index 328eeceec709..96e2d06cb031 100644 --- a/tools/arch/x86/include/asm/atomic.h +++ b/tools/arch/x86/include/asm/atomic.h @@ -24,7 +24,7 @@ */ static inline int atomic_read(const atomic_t *v) { - return ACCESS_ONCE((v)->counter); + return READ_ONCE((v)->counter); } /** diff --git a/tools/include/asm-generic/atomic-gcc.h b/tools/include/asm-generic/atomic-gcc.h index 5e9738f97bf3..97427e700e3b 100644 --- a/tools/include/asm-generic/atomic-gcc.h +++ b/tools/include/asm-generic/atomic-gcc.h @@ -21,7 +21,7 @@ */ static inline int atomic_read(const atomic_t *v) { - return ACCESS_ONCE((v)->counter); + return READ_ONCE((v)->counter); } /** diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 33b5e6cdf38c..d19e11b68de7 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -378,7 +378,7 @@ struct addr_filters { static inline u64 auxtrace_mmap__read_snapshot_head(struct auxtrace_mmap *mm) { struct perf_event_mmap_page *pc = mm->userpg; - u64 head = ACCESS_ONCE(pc->aux_head); + u64 head = READ_ONCE(pc->aux_head); /* Ensure all reads are done after we read the head */ rmb(); @@ -389,7 +389,7 @@ static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm) { struct perf_event_mmap_page *pc = mm->userpg; #if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT) - u64 head = ACCESS_ONCE(pc->aux_head); + u64 head = READ_ONCE(pc->aux_head); #else u64 head = __sync_val_compare_and_swap(&pc->aux_head, 0, 0); #endif diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 47b5e7dbcb18..aae9645c7122 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -113,7 +113,7 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session, extern volatile int session_done; -#define session_done() ACCESS_ONCE(session_done) +#define session_done() READ_ONCE(session_done) int perf_session__deliver_synth_event(struct perf_session *session, union perf_event *event, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 9deb5a245b83..ce507ae1d4f5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2302,7 +2302,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) continue; } else if (pass && i > last_boosted_vcpu) break; - if (!ACCESS_ONCE(vcpu->preempted)) + if (!READ_ONCE(vcpu->preempted)) continue; if (vcpu == me) continue; -- cgit v1.2.3 From 6f0397d7e100f3b3978d6ebb6b2dea29ee7c4a95 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Wed, 25 Oct 2017 17:55:58 +0900 Subject: locking/lockdep: Provide empty lockdep_map structure for !CONFIG_LOCKDEP After this patch the lockdep_map structure takes no space if lockdep is disabled, reducing the number of #ifdefs in unrelated kernel code. Signed-off-by: Byungchul Park Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: amir73il@gmail.com Cc: axboe@kernel.dk Cc: darrick.wong@oracle.com Cc: david@fromorbit.com Cc: hch@infradead.org Cc: idryomov@gmail.com Cc: johan@kernel.org Cc: johannes.berg@intel.com Cc: kernel-team@lge.com Cc: linux-block@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org Cc: linux-mm@kvack.org Cc: linux-xfs@vger.kernel.org Cc: oleg@redhat.com Cc: tj@kernel.org Link: http://lkml.kernel.org/r/1508921765-15396-3-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index bfa8e0b0d6f1..b6662d05bcda 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -527,6 +527,11 @@ static inline void lockdep_on(void) */ struct lock_class_key { }; +/* + * The lockdep_map takes no space if lockdep is disabled: + */ +struct lockdep_map { }; + #define lockdep_depth(tsk) (0) #define lockdep_is_held_type(l, r) (1) -- cgit v1.2.3 From 24208435e343679b21502fb90786084dfaf15369 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Wed, 25 Oct 2017 17:55:59 +0900 Subject: locking/lockdep, sched/completions: Change the prefix of lock name for completion variables CONFIG_LOCKDEP_COMPLETIONS uses "(complete)" as a prefix of lock name for completion variable. However, what we should use here is a noun - so use "(completion)" instead. Suggested-by: Ingo Molnar Signed-off-by: Byungchul Park Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: amir73il@gmail.com Cc: axboe@kernel.dk Cc: darrick.wong@oracle.com Cc: david@fromorbit.com Cc: hch@infradead.org Cc: idryomov@gmail.com Cc: johan@kernel.org Cc: johannes.berg@intel.com Cc: kernel-team@lge.com Cc: linux-block@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org Cc: linux-mm@kvack.org Cc: linux-xfs@vger.kernel.org Cc: oleg@redhat.com Cc: tj@kernel.org Link: http://lkml.kernel.org/r/1508921765-15396-4-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar --- include/linux/completion.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/completion.h b/include/linux/completion.h index cae5400022a3..91218036b1c8 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -53,7 +53,7 @@ static inline void complete_release_commit(struct completion *x) do { \ static struct lock_class_key __key; \ lockdep_init_map_crosslock((struct lockdep_map *)&(x)->map, \ - "(complete)" #x, \ + "(completion)" #x, \ &__key, 0); \ __init_completion(x); \ } while (0) @@ -67,7 +67,7 @@ static inline void complete_release_commit(struct completion *x) {} #ifdef CONFIG_LOCKDEP_COMPLETIONS #define COMPLETION_INITIALIZER(work) \ { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait), \ - STATIC_CROSS_LOCKDEP_MAP_INIT("(complete)" #work, &(work)) } + STATIC_CROSS_LOCKDEP_MAP_INIT("(completion)" #work, &(work)) } #else #define COMPLETION_INITIALIZER(work) \ { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } -- cgit v1.2.3 From a7967bc31584bd282682981295861e7bcba19e65 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Wed, 25 Oct 2017 17:56:03 +0900 Subject: sched/completions: Add support for initializing completions with lockdep_map Sometimes we want to initialize completions with sparate lockdep maps to assign lock classes as desired. For example, the workqueue code needs to directly manage lockdep maps, since only the code is aware of how to classify lockdep maps properly. Provide additional macros initializing completions in that way. Signed-off-by: Byungchul Park Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: amir73il@gmail.com Cc: axboe@kernel.dk Cc: darrick.wong@oracle.com Cc: david@fromorbit.com Cc: hch@infradead.org Cc: idryomov@gmail.com Cc: johan@kernel.org Cc: johannes.berg@intel.com Cc: kernel-team@lge.com Cc: linux-block@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org Cc: linux-mm@kvack.org Cc: linux-xfs@vger.kernel.org Cc: oleg@redhat.com Cc: tj@kernel.org Link: http://lkml.kernel.org/r/1508921765-15396-8-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar --- include/linux/completion.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/completion.h b/include/linux/completion.h index 91218036b1c8..4da49916ef3f 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -49,6 +49,13 @@ static inline void complete_release_commit(struct completion *x) lock_commit_crosslock((struct lockdep_map *)&x->map); } +#define init_completion_map(x, m) \ +do { \ + lockdep_init_map_crosslock((struct lockdep_map *)&(x)->map, \ + (m)->name, (m)->key, 0); \ + __init_completion(x); \ +} while (0) + #define init_completion(x) \ do { \ static struct lock_class_key __key; \ @@ -58,6 +65,7 @@ do { \ __init_completion(x); \ } while (0) #else +#define init_completion_map(x, m) __init_completion(x) #define init_completion(x) __init_completion(x) static inline void complete_acquire(struct completion *x) {} static inline void complete_release(struct completion *x) {} @@ -73,6 +81,9 @@ static inline void complete_release_commit(struct completion *x) {} { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } #endif +#define COMPLETION_INITIALIZER_ONSTACK_MAP(work, map) \ + (*({ init_completion_map(&(work), &(map)); &(work); })) + #define COMPLETION_INITIALIZER_ONSTACK(work) \ (*({ init_completion(&work); &work; })) @@ -102,8 +113,11 @@ static inline void complete_release_commit(struct completion *x) {} #ifdef CONFIG_LOCKDEP # define DECLARE_COMPLETION_ONSTACK(work) \ struct completion work = COMPLETION_INITIALIZER_ONSTACK(work) +# define DECLARE_COMPLETION_ONSTACK_MAP(work, map) \ + struct completion work = COMPLETION_INITIALIZER_ONSTACK_MAP(work, map) #else # define DECLARE_COMPLETION_ONSTACK(work) DECLARE_COMPLETION(work) +# define DECLARE_COMPLETION_ONSTACK_MAP(work, map) DECLARE_COMPLETION(work) #endif /** -- cgit v1.2.3 From fd1a5b04dfb899f84ddeb8acdaea6b98283df1e5 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Wed, 25 Oct 2017 17:56:04 +0900 Subject: workqueue: Remove now redundant lock acquisitions wrt. workqueue flushes The workqueue code added manual lock acquisition annotations to catch deadlocks. After lockdepcrossrelease was introduced, some of those became redundant, since wait_for_completion() already does the acquisition and tracking. Remove the duplicate annotations. Signed-off-by: Byungchul Park Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: amir73il@gmail.com Cc: axboe@kernel.dk Cc: darrick.wong@oracle.com Cc: david@fromorbit.com Cc: hch@infradead.org Cc: idryomov@gmail.com Cc: johan@kernel.org Cc: johannes.berg@intel.com Cc: kernel-team@lge.com Cc: linux-block@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org Cc: linux-mm@kvack.org Cc: linux-xfs@vger.kernel.org Cc: oleg@redhat.com Cc: tj@kernel.org Link: http://lkml.kernel.org/r/1508921765-15396-9-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar --- include/linux/workqueue.h | 4 ++-- kernel/workqueue.c | 19 +++---------------- 2 files changed, 5 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 1c49431f3121..c8a572cb49be 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -218,7 +218,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ - lockdep_init_map(&(_work)->lockdep_map, #_work, &__key, 0); \ + lockdep_init_map(&(_work)->lockdep_map, "(work_completion)"#_work, &__key, 0); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) @@ -398,7 +398,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, static struct lock_class_key __key; \ const char *__lock_name; \ \ - __lock_name = #fmt#args; \ + __lock_name = "(wq_completion)"#fmt#args; \ \ __alloc_workqueue_key((fmt), (flags), (max_active), \ &__key, __lock_name, ##args); \ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 39831b2f3c5f..160fdc6e839a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2497,15 +2497,8 @@ static void insert_wq_barrier(struct pool_workqueue *pwq, INIT_WORK_ONSTACK(&barr->work, wq_barrier_func); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); - /* - * Explicitly init the crosslock for wq_barrier::done, make its lock - * key a subkey of the corresponding work. As a result we won't - * build a dependency between wq_barrier::done and unrelated work. - */ - lockdep_init_map_crosslock((struct lockdep_map *)&barr->done.map, - "(complete)wq_barr::done", - target->lockdep_map.key, 1); - __init_completion(&barr->done); + init_completion_map(&barr->done, &target->lockdep_map); + barr->task = current; /* @@ -2611,16 +2604,13 @@ void flush_workqueue(struct workqueue_struct *wq) struct wq_flusher this_flusher = { .list = LIST_HEAD_INIT(this_flusher.list), .flush_color = -1, - .done = COMPLETION_INITIALIZER_ONSTACK(this_flusher.done), + .done = COMPLETION_INITIALIZER_ONSTACK_MAP(this_flusher.done, wq->lockdep_map), }; int next_color; if (WARN_ON(!wq_online)) return; - lock_map_acquire(&wq->lockdep_map); - lock_map_release(&wq->lockdep_map); - mutex_lock(&wq->mutex); /* @@ -2883,9 +2873,6 @@ bool flush_work(struct work_struct *work) if (WARN_ON(!wq_online)) return false; - lock_map_acquire(&work->lockdep_map); - lock_map_release(&work->lockdep_map); - if (start_flush_work(work, &barr)) { wait_for_completion(&barr.done); destroy_work_on_stack(&barr.work); -- cgit v1.2.3 From e319e1fbd9d42420ab6eec0bfd75eb9ad7ca63b1 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Wed, 25 Oct 2017 17:56:05 +0900 Subject: block, locking/lockdep: Assign a lock_class per gendisk used for wait_for_completion() Darrick posted the following warning and Dave Chinner analyzed it: > ====================================================== > WARNING: possible circular locking dependency detected > 4.14.0-rc1-fixes #1 Tainted: G W > ------------------------------------------------------ > loop0/31693 is trying to acquire lock: > (&(&ip->i_mmaplock)->mr_lock){++++}, at: [] xfs_ilock+0x23c/0x330 [xfs] > > but now in release context of a crosslock acquired at the following: > ((complete)&ret.event){+.+.}, at: [] submit_bio_wait+0x7f/0xb0 > > which lock already depends on the new lock. > > the existing dependency chain (in reverse order) is: > > -> #2 ((complete)&ret.event){+.+.}: > lock_acquire+0xab/0x200 > wait_for_completion_io+0x4e/0x1a0 > submit_bio_wait+0x7f/0xb0 > blkdev_issue_zeroout+0x71/0xa0 > xfs_bmapi_convert_unwritten+0x11f/0x1d0 [xfs] > xfs_bmapi_write+0x374/0x11f0 [xfs] > xfs_iomap_write_direct+0x2ac/0x430 [xfs] > xfs_file_iomap_begin+0x20d/0xd50 [xfs] > iomap_apply+0x43/0xe0 > dax_iomap_rw+0x89/0xf0 > xfs_file_dax_write+0xcc/0x220 [xfs] > xfs_file_write_iter+0xf0/0x130 [xfs] > __vfs_write+0xd9/0x150 > vfs_write+0xc8/0x1c0 > SyS_write+0x45/0xa0 > entry_SYSCALL_64_fastpath+0x1f/0xbe > > -> #1 (&xfs_nondir_ilock_class){++++}: > lock_acquire+0xab/0x200 > down_write_nested+0x4a/0xb0 > xfs_ilock+0x263/0x330 [xfs] > xfs_setattr_size+0x152/0x370 [xfs] > xfs_vn_setattr+0x6b/0x90 [xfs] > notify_change+0x27d/0x3f0 > do_truncate+0x5b/0x90 > path_openat+0x237/0xa90 > do_filp_open+0x8a/0xf0 > do_sys_open+0x11c/0x1f0 > entry_SYSCALL_64_fastpath+0x1f/0xbe > > -> #0 (&(&ip->i_mmaplock)->mr_lock){++++}: > up_write+0x1c/0x40 > xfs_iunlock+0x1d0/0x310 [xfs] > xfs_file_fallocate+0x8a/0x310 [xfs] > loop_queue_work+0xb7/0x8d0 > kthread_worker_fn+0xb9/0x1f0 > > Chain exists of: > &(&ip->i_mmaplock)->mr_lock --> &xfs_nondir_ilock_class --> (complete)&ret.event > > Possible unsafe locking scenario by crosslock: > > CPU0 CPU1 > ---- ---- > lock(&xfs_nondir_ilock_class); > lock((complete)&ret.event); > lock(&(&ip->i_mmaplock)->mr_lock); > unlock((complete)&ret.event); > > *** DEADLOCK *** The warning is a false positive, caused by the fact that all wait_for_completion()s in submit_bio_wait() are waiting with the same lock class. However, some bios have nothing to do with others, for example in the case of loop devices, there's no direct connection between the bios of an upper device and the bios of a lower device(=loop device). The safest way to assign different lock classes to different devices is to do it for each gendisk. In other words, this patch assigns a lockdep_map per gendisk and uses it when initializing completion in submit_bio_wait(). Analyzed-by: Dave Chinner Reported-by: Darrick J. Wong Signed-off-by: Byungchul Park Reviewed-by: Jens Axboe Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: amir73il@gmail.com Cc: axboe@kernel.dk Cc: david@fromorbit.com Cc: hch@infradead.org Cc: idryomov@gmail.com Cc: johan@kernel.org Cc: johannes.berg@intel.com Cc: kernel-team@lge.com Cc: linux-block@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org Cc: linux-mm@kvack.org Cc: linux-xfs@vger.kernel.org Cc: oleg@redhat.com Cc: tj@kernel.org Link: http://lkml.kernel.org/r/1508921765-15396-10-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar --- block/bio.c | 2 +- block/genhd.c | 10 ++-------- include/linux/genhd.h | 22 ++++++++++++++++++++-- 3 files changed, 23 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index 5e901bfc0576..cc60213e56d8 100644 --- a/block/bio.c +++ b/block/bio.c @@ -935,7 +935,7 @@ static void submit_bio_wait_endio(struct bio *bio) */ int submit_bio_wait(struct bio *bio) { - DECLARE_COMPLETION_ONSTACK(done); + DECLARE_COMPLETION_ONSTACK_MAP(done, bio->bi_disk->lockdep_map); bio->bi_private = &done; bio->bi_end_io = submit_bio_wait_endio; diff --git a/block/genhd.c b/block/genhd.c index dd305c65ffb0..630c0da6cfcf 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1354,13 +1354,7 @@ dev_t blk_lookup_devt(const char *name, int partno) } EXPORT_SYMBOL(blk_lookup_devt); -struct gendisk *alloc_disk(int minors) -{ - return alloc_disk_node(minors, NUMA_NO_NODE); -} -EXPORT_SYMBOL(alloc_disk); - -struct gendisk *alloc_disk_node(int minors, int node_id) +struct gendisk *__alloc_disk_node(int minors, int node_id) { struct gendisk *disk; struct disk_part_tbl *ptbl; @@ -1411,7 +1405,7 @@ struct gendisk *alloc_disk_node(int minors, int node_id) } return disk; } -EXPORT_SYMBOL(alloc_disk_node); +EXPORT_SYMBOL(__alloc_disk_node); struct kobject *get_disk(struct gendisk *disk) { diff --git a/include/linux/genhd.h b/include/linux/genhd.h index ea652bfcd675..19d18710546a 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -206,6 +206,7 @@ struct gendisk { #endif /* CONFIG_BLK_DEV_INTEGRITY */ int node_id; struct badblocks *bb; + struct lockdep_map lockdep_map; }; static inline struct gendisk *part_to_disk(struct hd_struct *part) @@ -590,8 +591,7 @@ extern void __delete_partition(struct percpu_ref *); extern void delete_partition(struct gendisk *, int); extern void printk_all_partitions(void); -extern struct gendisk *alloc_disk_node(int minors, int node_id); -extern struct gendisk *alloc_disk(int minors); +extern struct gendisk *__alloc_disk_node(int minors, int node_id); extern struct kobject *get_disk(struct gendisk *disk); extern void put_disk(struct gendisk *disk); extern void blk_register_region(dev_t devt, unsigned long range, @@ -615,6 +615,24 @@ extern ssize_t part_fail_store(struct device *dev, const char *buf, size_t count); #endif /* CONFIG_FAIL_MAKE_REQUEST */ +#define alloc_disk_node(minors, node_id) \ +({ \ + static struct lock_class_key __key; \ + const char *__name; \ + struct gendisk *__disk; \ + \ + __name = "(gendisk_completion)"#minors"("#node_id")"; \ + \ + __disk = __alloc_disk_node(minors, node_id); \ + \ + if (__disk) \ + lockdep_init_map(&__disk->lockdep_map, __name, &__key, 0); \ + \ + __disk; \ +}) + +#define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE) + static inline int hd_ref_init(struct hd_struct *part) { if (percpu_ref_init(&part->ref, __delete_partition, 0, -- cgit v1.2.3 From 7863406143d8bbbbda07a61285c5f4c217908dfd Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 27 Oct 2017 04:42:28 +0200 Subject: sched/isolation: Move housekeeping related code to its own file The housekeeping code is currently tied to the NOHZ code. As we are planning to make housekeeping independent from it, start with moving the relevant code to its own file. Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Acked-by: Paul E. McKenney Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1509072159-31808-2-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- drivers/net/ethernet/tile/tilegx.c | 2 +- include/linux/sched/isolation.h | 56 ++++++++++++++++++++++++++++++++++++++ include/linux/tick.h | 37 ------------------------- init/main.c | 2 ++ kernel/rcu/tree_plugin.h | 1 + kernel/rcu/update.c | 1 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 1 + kernel/sched/fair.c | 1 + kernel/sched/isolation.c | 33 ++++++++++++++++++++++ kernel/time/tick-sched.c | 18 ------------ kernel/watchdog.c | 1 + 12 files changed, 98 insertions(+), 56 deletions(-) create mode 100644 include/linux/sched/isolation.h create mode 100644 kernel/sched/isolation.c (limited to 'include/linux') diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c index c00102b8145a..27a3272dcd48 100644 --- a/drivers/net/ethernet/tile/tilegx.c +++ b/drivers/net/ethernet/tile/tilegx.c @@ -40,7 +40,7 @@ #include #include #include -#include +#include #include #include diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h new file mode 100644 index 000000000000..b7cfbc46286c --- /dev/null +++ b/include/linux/sched/isolation.h @@ -0,0 +1,56 @@ +#ifndef _LINUX_SCHED_ISOLATION_H +#define _LINUX_SCHED_ISOLATION_H + +#include +#include +#include + +#ifdef CONFIG_NO_HZ_FULL +extern cpumask_var_t housekeeping_mask; + +static inline int housekeeping_any_cpu(void) +{ + return cpumask_any_and(housekeeping_mask, cpu_online_mask); +} + +extern void __init housekeeping_init(void); + +#else + +static inline int housekeeping_any_cpu(void) +{ + return smp_processor_id(); +} + +static inline void housekeeping_init(void) { } +#endif /* CONFIG_NO_HZ_FULL */ + + +static inline const struct cpumask *housekeeping_cpumask(void) +{ +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_enabled()) + return housekeeping_mask; +#endif + return cpu_possible_mask; +} + +static inline bool is_housekeeping_cpu(int cpu) +{ +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_enabled()) + return cpumask_test_cpu(cpu, housekeeping_mask); +#endif + return true; +} + +static inline void housekeeping_affine(struct task_struct *t) +{ +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_enabled()) + set_cpus_allowed_ptr(t, housekeeping_mask); + +#endif +} + +#endif /* _LINUX_SCHED_ISOLATION_H */ diff --git a/include/linux/tick.h b/include/linux/tick.h index fe01e68bf520..68afc09aa8ac 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -137,7 +137,6 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } #ifdef CONFIG_NO_HZ_FULL extern bool tick_nohz_full_running; extern cpumask_var_t tick_nohz_full_mask; -extern cpumask_var_t housekeeping_mask; static inline bool tick_nohz_full_enabled(void) { @@ -161,11 +160,6 @@ static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) cpumask_or(mask, mask, tick_nohz_full_mask); } -static inline int housekeeping_any_cpu(void) -{ - return cpumask_any_and(housekeeping_mask, cpu_online_mask); -} - extern void tick_nohz_dep_set(enum tick_dep_bits bit); extern void tick_nohz_dep_clear(enum tick_dep_bits bit); extern void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit); @@ -235,10 +229,6 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal, extern void tick_nohz_full_kick_cpu(int cpu); extern void __tick_nohz_task_switch(void); #else -static inline int housekeeping_any_cpu(void) -{ - return smp_processor_id(); -} static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { } @@ -260,33 +250,6 @@ static inline void tick_nohz_full_kick_cpu(int cpu) { } static inline void __tick_nohz_task_switch(void) { } #endif -static inline const struct cpumask *housekeeping_cpumask(void) -{ -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_enabled()) - return housekeeping_mask; -#endif - return cpu_possible_mask; -} - -static inline bool is_housekeeping_cpu(int cpu) -{ -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_enabled()) - return cpumask_test_cpu(cpu, housekeeping_mask); -#endif - return true; -} - -static inline void housekeeping_affine(struct task_struct *t) -{ -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_enabled()) - set_cpus_allowed_ptr(t, housekeeping_mask); - -#endif -} - static inline void tick_nohz_task_switch(void) { if (tick_nohz_full_enabled()) diff --git a/init/main.c b/init/main.c index 0ee9c6866ada..4610c99ae306 100644 --- a/init/main.c +++ b/init/main.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #include #include @@ -606,6 +607,7 @@ asmlinkage __visible void __init start_kernel(void) early_irq_init(); init_IRQ(); tick_init(); + housekeeping_init(); rcu_init_nohz(); init_timers(); hrtimers_init(); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index e012b9be777e..c7632f51c5a0 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -29,6 +29,7 @@ #include #include #include +#include #include #include "../time/tick-internal.h" diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 5033b66d2753..79abeb0ca329 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -51,6 +51,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 78f54932ea1d..871d43d73375 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -26,3 +26,4 @@ obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o +obj-$(CONFIG_NO_HZ_FULL) += isolation.o diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2288a145bf01..ad188acb7636 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 56f343b8e749..591481db8c6a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -32,6 +32,7 @@ #include #include #include +#include #include diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c new file mode 100644 index 000000000000..3589252ed476 --- /dev/null +++ b/kernel/sched/isolation.c @@ -0,0 +1,33 @@ +/* + * Housekeeping management. Manage the targets for routine code that can run on + * any CPU: unbound workqueues, timers, kthreads and any offloadable work. + * + * Copyright (C) 2017 Red Hat, Inc., Frederic Weisbecker + * + */ + +#include +#include +#include +#include + +cpumask_var_t housekeeping_mask; + +void __init housekeeping_init(void) +{ + if (!tick_nohz_full_enabled()) + return; + + if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) { + WARN(1, "NO_HZ: Can't allocate not-full dynticks cpumask\n"); + cpumask_clear(tick_nohz_full_mask); + tick_nohz_full_running = false; + return; + } + + cpumask_andnot(housekeeping_mask, + cpu_possible_mask, tick_nohz_full_mask); + + /* We need at least one CPU to handle housekeeping work */ + WARN_ON_ONCE(cpumask_empty(housekeeping_mask)); +} diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 7b258c59d78a..27d7d522ac4e 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -166,7 +166,6 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) #ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; -cpumask_var_t housekeeping_mask; bool tick_nohz_full_running; static atomic_t tick_dep_mask; @@ -438,13 +437,6 @@ void __init tick_nohz_init(void) return; } - if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) { - WARN(1, "NO_HZ: Can't allocate not-full dynticks cpumask\n"); - cpumask_clear(tick_nohz_full_mask); - tick_nohz_full_running = false; - return; - } - /* * Full dynticks uses irq work to drive the tick rescheduling on safe * locking contexts. But then we need irq work to raise its own @@ -453,7 +445,6 @@ void __init tick_nohz_init(void) if (!arch_irq_work_has_interrupt()) { pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support irq work self-IPIs\n"); cpumask_clear(tick_nohz_full_mask); - cpumask_copy(housekeeping_mask, cpu_possible_mask); tick_nohz_full_running = false; return; } @@ -466,9 +457,6 @@ void __init tick_nohz_init(void) cpumask_clear_cpu(cpu, tick_nohz_full_mask); } - cpumask_andnot(housekeeping_mask, - cpu_possible_mask, tick_nohz_full_mask); - for_each_cpu(cpu, tick_nohz_full_mask) context_tracking_cpu_set(cpu); @@ -478,12 +466,6 @@ void __init tick_nohz_init(void) WARN_ON(ret < 0); pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n", cpumask_pr_args(tick_nohz_full_mask)); - - /* - * We need at least one CPU to handle housekeeping work such - * as timekeeping, unbound timers, workqueues, ... - */ - WARN_ON_ONCE(cpumask_empty(housekeeping_mask)); } #endif diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 6bcb854909c0..3c44dbaa4b9f 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include -- cgit v1.2.3 From 9f0ca2d97ef0b5e966be2cfef26c7c094ec14e41 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 27 Oct 2017 04:42:30 +0200 Subject: sched/isolation: Provide a dynamic off-case to housekeeping_any_cpu() housekeeping_any_cpu() doesn't handle correctly the case where CONFIG_NO_HZ_FULL=y and no CPU is in nohz_full mode. So far no caller needs this but let's prepare to avoid any future surprise. Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1509072159-31808-4-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/isolation.h | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index b7cfbc46286c..040df04fa78a 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -7,25 +7,20 @@ #ifdef CONFIG_NO_HZ_FULL extern cpumask_var_t housekeeping_mask; - -static inline int housekeeping_any_cpu(void) -{ - return cpumask_any_and(housekeeping_mask, cpu_online_mask); -} - extern void __init housekeeping_init(void); - #else +static inline void housekeeping_init(void) { } +#endif /* CONFIG_NO_HZ_FULL */ static inline int housekeeping_any_cpu(void) { +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_enabled()) + return cpumask_any_and(housekeeping_mask, cpu_online_mask); +#endif return smp_processor_id(); } -static inline void housekeeping_init(void) { } -#endif /* CONFIG_NO_HZ_FULL */ - - static inline const struct cpumask *housekeeping_cpumask(void) { #ifdef CONFIG_NO_HZ_FULL -- cgit v1.2.3 From 7e56a1cf4b28f5739526877b8dbad623fae2e4e7 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 27 Oct 2017 04:42:31 +0200 Subject: sched/isolation: Make the housekeeping cpumask private Nobody needs to access this detail. housekeeping_cpumask() already takes care of it. Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1509072159-31808-5-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/isolation.h | 31 ++++++++++--------------------- kernel/sched/isolation.c | 36 +++++++++++++++++++++++++++++++++++- 2 files changed, 45 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 040df04fa78a..ed935ffc6ffa 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -6,46 +6,35 @@ #include #ifdef CONFIG_NO_HZ_FULL -extern cpumask_var_t housekeeping_mask; +extern int housekeeping_any_cpu(void); +extern const struct cpumask *housekeeping_cpumask(void); +extern void housekeeping_affine(struct task_struct *t); +extern bool housekeeping_test_cpu(int cpu); extern void __init housekeeping_init(void); + #else -static inline void housekeeping_init(void) { } -#endif /* CONFIG_NO_HZ_FULL */ static inline int housekeeping_any_cpu(void) { -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_enabled()) - return cpumask_any_and(housekeeping_mask, cpu_online_mask); -#endif return smp_processor_id(); } static inline const struct cpumask *housekeeping_cpumask(void) { -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_enabled()) - return housekeeping_mask; -#endif return cpu_possible_mask; } +static inline void housekeeping_affine(struct task_struct *t) { } +static inline void housekeeping_init(void) { } +#endif /* CONFIG_NO_HZ_FULL */ + static inline bool is_housekeeping_cpu(int cpu) { #ifdef CONFIG_NO_HZ_FULL if (tick_nohz_full_enabled()) - return cpumask_test_cpu(cpu, housekeeping_mask); + return housekeeping_test_cpu(cpu); #endif return true; } -static inline void housekeeping_affine(struct task_struct *t) -{ -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_enabled()) - set_cpus_allowed_ptr(t, housekeeping_mask); - -#endif -} - #endif /* _LINUX_SCHED_ISOLATION_H */ diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 3589252ed476..16445097eb25 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -11,7 +11,41 @@ #include #include -cpumask_var_t housekeeping_mask; +static cpumask_var_t housekeeping_mask; + +int housekeeping_any_cpu(void) +{ + if (tick_nohz_full_enabled()) + return cpumask_any_and(housekeeping_mask, cpu_online_mask); + + return smp_processor_id(); +} +EXPORT_SYMBOL_GPL(housekeeping_any_cpu); + +const struct cpumask *housekeeping_cpumask(void) +{ + if (tick_nohz_full_enabled()) + return housekeeping_mask; + + return cpu_possible_mask; +} +EXPORT_SYMBOL_GPL(housekeeping_cpumask); + +void housekeeping_affine(struct task_struct *t) +{ + if (tick_nohz_full_enabled()) + set_cpus_allowed_ptr(t, housekeeping_mask); +} +EXPORT_SYMBOL_GPL(housekeeping_affine); + +bool housekeeping_test_cpu(int cpu) +{ + if (tick_nohz_full_enabled()) + return cpumask_test_cpu(cpu, housekeeping_mask); + + return true; +} +EXPORT_SYMBOL_GPL(housekeeping_test_cpu); void __init housekeeping_init(void) { -- cgit v1.2.3 From e179f5a04ba46ee5c5439480c2bfd68c358168b7 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 27 Oct 2017 04:42:32 +0200 Subject: sched/isolation: Use its own static key Housekeeping code still depends on the nohz_full static key. Since we want to decouple housekeeping from NOHZ, let's create a housekeeping specific static key. It's mostly relevant for calls to is_housekeeping_cpu() from the scheduler. Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1509072159-31808-6-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/isolation.h | 3 ++- kernel/sched/isolation.c | 13 +++++++++---- 2 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index ed935ffc6ffa..194c586fbb12 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -6,6 +6,7 @@ #include #ifdef CONFIG_NO_HZ_FULL +DECLARE_STATIC_KEY_FALSE(housekeeping_overriden); extern int housekeeping_any_cpu(void); extern const struct cpumask *housekeeping_cpumask(void); extern void housekeeping_affine(struct task_struct *t); @@ -31,7 +32,7 @@ static inline void housekeeping_init(void) { } static inline bool is_housekeeping_cpu(int cpu) { #ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_enabled()) + if (static_branch_unlikely(&housekeeping_overriden)) return housekeeping_test_cpu(cpu); #endif return true; diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 16445097eb25..bb8ba19a0235 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -10,12 +10,15 @@ #include #include #include +#include +DEFINE_STATIC_KEY_FALSE(housekeeping_overriden); +EXPORT_SYMBOL_GPL(housekeeping_overriden); static cpumask_var_t housekeeping_mask; int housekeeping_any_cpu(void) { - if (tick_nohz_full_enabled()) + if (static_branch_unlikely(&housekeeping_overriden)) return cpumask_any_and(housekeeping_mask, cpu_online_mask); return smp_processor_id(); @@ -24,7 +27,7 @@ EXPORT_SYMBOL_GPL(housekeeping_any_cpu); const struct cpumask *housekeeping_cpumask(void) { - if (tick_nohz_full_enabled()) + if (static_branch_unlikely(&housekeeping_overriden)) return housekeeping_mask; return cpu_possible_mask; @@ -33,14 +36,14 @@ EXPORT_SYMBOL_GPL(housekeeping_cpumask); void housekeeping_affine(struct task_struct *t) { - if (tick_nohz_full_enabled()) + if (static_branch_unlikely(&housekeeping_overriden)) set_cpus_allowed_ptr(t, housekeeping_mask); } EXPORT_SYMBOL_GPL(housekeeping_affine); bool housekeeping_test_cpu(int cpu) { - if (tick_nohz_full_enabled()) + if (static_branch_unlikely(&housekeeping_overriden)) return cpumask_test_cpu(cpu, housekeeping_mask); return true; @@ -62,6 +65,8 @@ void __init housekeeping_init(void) cpumask_andnot(housekeeping_mask, cpu_possible_mask, tick_nohz_full_mask); + static_branch_enable(&housekeeping_overriden); + /* We need at least one CPU to handle housekeeping work */ WARN_ON_ONCE(cpumask_empty(housekeeping_mask)); } -- cgit v1.2.3 From 204c083a009378dfa751175b5fcddc75988bab6c Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 27 Oct 2017 04:42:33 +0200 Subject: sched/isolation: Rename is_housekeeping_cpu() to housekeeping_cpu() Fit it into the housekeeping_*() namespace. Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1509072159-31808-7-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/isolation.h | 2 +- kernel/sched/core.c | 6 +++--- kernel/sched/fair.c | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 194c586fbb12..ad0f5d986a2e 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -29,7 +29,7 @@ static inline void housekeeping_affine(struct task_struct *t) { } static inline void housekeeping_init(void) { } #endif /* CONFIG_NO_HZ_FULL */ -static inline bool is_housekeeping_cpu(int cpu) +static inline bool housekeeping_cpu(int cpu) { #ifdef CONFIG_NO_HZ_FULL if (static_branch_unlikely(&housekeeping_overriden)) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ad188acb7636..d0fb448dd43a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -527,7 +527,7 @@ int get_nohz_timer_target(void) int i, cpu = smp_processor_id(); struct sched_domain *sd; - if (!idle_cpu(cpu) && is_housekeeping_cpu(cpu)) + if (!idle_cpu(cpu) && housekeeping_cpu(cpu)) return cpu; rcu_read_lock(); @@ -536,14 +536,14 @@ int get_nohz_timer_target(void) if (cpu == i) continue; - if (!idle_cpu(i) && is_housekeeping_cpu(i)) { + if (!idle_cpu(i) && housekeeping_cpu(i)) { cpu = i; goto unlock; } } } - if (!is_housekeeping_cpu(cpu)) + if (!housekeeping_cpu(cpu)) cpu = housekeeping_any_cpu(); unlock: rcu_read_unlock(); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 591481db8c6a..cdece8f967f0 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -9027,7 +9027,7 @@ void nohz_balance_enter_idle(int cpu) return; /* Spare idle load balancing on CPUs that don't want to be disturbed: */ - if (!is_housekeeping_cpu(cpu)) + if (!housekeeping_cpu(cpu)) return; if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu))) -- cgit v1.2.3 From 5c4991e24c69737bd41fc2737b1e3980abbf73f9 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 27 Oct 2017 04:42:34 +0200 Subject: sched/isolation: Split out new CONFIG_CPU_ISOLATION=y config from CONFIG_NO_HZ_FULL Split the housekeeping config from CONFIG_NO_HZ_FULL. This way we finally separate the isolation code from NOHZ. Although a dependency to CONFIG_NO_HZ_FULL remains for now, while the housekeeping code still deals with NOHZ internals. Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1509072159-31808-8-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/isolation.h | 6 +++--- init/Kconfig | 8 ++++++++ kernel/sched/Makefile | 2 +- 3 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index ad0f5d986a2e..93ac2367a520 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -5,7 +5,7 @@ #include #include -#ifdef CONFIG_NO_HZ_FULL +#ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE(housekeeping_overriden); extern int housekeeping_any_cpu(void); extern const struct cpumask *housekeeping_cpumask(void); @@ -27,11 +27,11 @@ static inline const struct cpumask *housekeeping_cpumask(void) static inline void housekeeping_affine(struct task_struct *t) { } static inline void housekeeping_init(void) { } -#endif /* CONFIG_NO_HZ_FULL */ +#endif /* CONFIG_CPU_ISOLATION */ static inline bool housekeeping_cpu(int cpu) { -#ifdef CONFIG_NO_HZ_FULL +#ifdef CONFIG_CPU_ISOLATION if (static_branch_unlikely(&housekeeping_overriden)) return housekeeping_test_cpu(cpu); #endif diff --git a/init/Kconfig b/init/Kconfig index 78cb2461012e..6f52e6f4bd9d 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -472,6 +472,14 @@ config TASK_IO_ACCOUNTING endmenu # "CPU/Task time and stats accounting" +config CPU_ISOLATION + bool "CPU isolation" + depends on NO_HZ_FULL + help + Make sure that CPUs running critical tasks are not disturbed by + any source of "noise" such as unbound workqueues, timers, kthreads... + Unbound jobs get offloaded to housekeeping CPUs. + source "kernel/rcu/Kconfig" config BUILD_BIN2C diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 871d43d73375..dbe61302c352 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -26,4 +26,4 @@ obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o -obj-$(CONFIG_NO_HZ_FULL) += isolation.o +obj-$(CONFIG_CPU_ISOLATION) += isolation.o -- cgit v1.2.3 From de201559df872f83d0c08fb4effe3efd28e6cbc8 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 27 Oct 2017 04:42:35 +0200 Subject: sched/isolation: Introduce housekeeping flags Before we implement isolcpus under housekeeping, we need the isolation features to be more finegrained. For example some people want NOHZ_FULL without the full scheduler isolation, others want full scheduler isolation without NOHZ_FULL. So let's cut all these isolation features piecewise, at the risk of overcutting it right now. We can still merge some flags later if they always make sense together. Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1509072159-31808-9-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- drivers/net/ethernet/tile/tilegx.c | 4 ++-- include/linux/sched/isolation.h | 26 +++++++++++++++++--------- kernel/rcu/tree_plugin.h | 2 +- kernel/rcu/update.c | 2 +- kernel/sched/core.c | 8 ++++---- kernel/sched/fair.c | 2 +- kernel/sched/isolation.c | 26 +++++++++++++++----------- kernel/watchdog.c | 3 ++- 8 files changed, 43 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c index 27a3272dcd48..b3e5816a4678 100644 --- a/drivers/net/ethernet/tile/tilegx.c +++ b/drivers/net/ethernet/tile/tilegx.c @@ -2270,8 +2270,8 @@ static int __init tile_net_init_module(void) tile_net_dev_init(name, mac); if (!network_cpus_init()) - cpumask_and(&network_cpus_map, housekeeping_cpumask(), - cpu_online_mask); + cpumask_and(&network_cpus_map, + housekeeping_cpumask(HK_FLAG_MISC), cpu_online_mask); return 0; } diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 93ac2367a520..9bb753eece3b 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -5,35 +5,43 @@ #include #include +enum hk_flags { + HK_FLAG_TIMER = 1, + HK_FLAG_RCU = (1 << 1), + HK_FLAG_MISC = (1 << 2), + HK_FLAG_SCHED = (1 << 3), +}; + #ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE(housekeeping_overriden); -extern int housekeeping_any_cpu(void); -extern const struct cpumask *housekeeping_cpumask(void); -extern void housekeeping_affine(struct task_struct *t); -extern bool housekeeping_test_cpu(int cpu); +extern int housekeeping_any_cpu(enum hk_flags flags); +extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags); +extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags); +extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags); extern void __init housekeeping_init(void); #else -static inline int housekeeping_any_cpu(void) +static inline int housekeeping_any_cpu(enum hk_flags flags) { return smp_processor_id(); } -static inline const struct cpumask *housekeeping_cpumask(void) +static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags) { return cpu_possible_mask; } -static inline void housekeeping_affine(struct task_struct *t) { } +static inline void housekeeping_affine(struct task_struct *t, + enum hk_flags flags) { } static inline void housekeeping_init(void) { } #endif /* CONFIG_CPU_ISOLATION */ -static inline bool housekeeping_cpu(int cpu) +static inline bool housekeeping_cpu(int cpu, enum hk_flags flags) { #ifdef CONFIG_CPU_ISOLATION if (static_branch_unlikely(&housekeeping_overriden)) - return housekeeping_test_cpu(cpu); + return housekeeping_test_cpu(cpu, flags); #endif return true; } diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index c7632f51c5a0..34125d23e58a 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2584,7 +2584,7 @@ static void rcu_bind_gp_kthread(void) if (!tick_nohz_full_enabled()) return; - housekeeping_affine(current); + housekeeping_affine(current, HK_FLAG_RCU); } /* Record the current task on dyntick-idle entry. */ diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 79abeb0ca329..e3e60efaafee 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -719,7 +719,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) LIST_HEAD(rcu_tasks_holdouts); /* Run on housekeeping CPUs by default. Sysadm can move if desired. */ - housekeeping_affine(current); + housekeeping_affine(current, HK_FLAG_RCU); /* * Each pass through the following loop makes one check for diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d0fb448dd43a..2210c0203e51 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -527,7 +527,7 @@ int get_nohz_timer_target(void) int i, cpu = smp_processor_id(); struct sched_domain *sd; - if (!idle_cpu(cpu) && housekeeping_cpu(cpu)) + if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER)) return cpu; rcu_read_lock(); @@ -536,15 +536,15 @@ int get_nohz_timer_target(void) if (cpu == i) continue; - if (!idle_cpu(i) && housekeeping_cpu(i)) { + if (!idle_cpu(i) && housekeeping_cpu(i, HK_FLAG_TIMER)) { cpu = i; goto unlock; } } } - if (!housekeeping_cpu(cpu)) - cpu = housekeeping_any_cpu(); + if (!housekeeping_cpu(cpu, HK_FLAG_TIMER)) + cpu = housekeeping_any_cpu(HK_FLAG_TIMER); unlock: rcu_read_unlock(); return cpu; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index cdece8f967f0..f755de86a813 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -9027,7 +9027,7 @@ void nohz_balance_enter_idle(int cpu) return; /* Spare idle load balancing on CPUs that don't want to be disturbed: */ - if (!housekeeping_cpu(cpu)) + if (!housekeeping_cpu(cpu, HK_FLAG_SCHED)) return; if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu))) diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index bb8ba19a0235..37a138a780ff 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -15,37 +15,39 @@ DEFINE_STATIC_KEY_FALSE(housekeeping_overriden); EXPORT_SYMBOL_GPL(housekeeping_overriden); static cpumask_var_t housekeeping_mask; +static unsigned int housekeeping_flags; -int housekeeping_any_cpu(void) +int housekeeping_any_cpu(enum hk_flags flags) { if (static_branch_unlikely(&housekeeping_overriden)) - return cpumask_any_and(housekeeping_mask, cpu_online_mask); - + if (housekeeping_flags & flags) + return cpumask_any_and(housekeeping_mask, cpu_online_mask); return smp_processor_id(); } EXPORT_SYMBOL_GPL(housekeeping_any_cpu); -const struct cpumask *housekeeping_cpumask(void) +const struct cpumask *housekeeping_cpumask(enum hk_flags flags) { if (static_branch_unlikely(&housekeeping_overriden)) - return housekeeping_mask; - + if (housekeeping_flags & flags) + return housekeeping_mask; return cpu_possible_mask; } EXPORT_SYMBOL_GPL(housekeeping_cpumask); -void housekeeping_affine(struct task_struct *t) +void housekeeping_affine(struct task_struct *t, enum hk_flags flags) { if (static_branch_unlikely(&housekeeping_overriden)) - set_cpus_allowed_ptr(t, housekeeping_mask); + if (housekeeping_flags & flags) + set_cpus_allowed_ptr(t, housekeeping_mask); } EXPORT_SYMBOL_GPL(housekeeping_affine); -bool housekeeping_test_cpu(int cpu) +bool housekeeping_test_cpu(int cpu, enum hk_flags flags) { if (static_branch_unlikely(&housekeeping_overriden)) - return cpumask_test_cpu(cpu, housekeeping_mask); - + if (housekeeping_flags & flags) + return cpumask_test_cpu(cpu, housekeeping_mask); return true; } EXPORT_SYMBOL_GPL(housekeeping_test_cpu); @@ -65,6 +67,8 @@ void __init housekeeping_init(void) cpumask_andnot(housekeeping_mask, cpu_possible_mask, tick_nohz_full_mask); + housekeeping_flags = HK_FLAG_TIMER | HK_FLAG_RCU | HK_FLAG_MISC; + static_branch_enable(&housekeeping_overriden); /* We need at least one CPU to handle housekeeping work */ diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 562652c9c815..e9e2ebb3db29 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -777,7 +777,8 @@ void __init lockup_detector_init(void) if (tick_nohz_full_enabled()) pr_info("Disabling watchdog on nohz_full cores by default\n"); - cpumask_copy(&watchdog_cpumask, housekeeping_cpumask()); + cpumask_copy(&watchdog_cpumask, + housekeeping_cpumask(HK_FLAG_TIMER)); if (!watchdog_nmi_probe()) nmi_watchdog_available = true; -- cgit v1.2.3 From 6f1982fedd59856bcc42a9b521be4c3ffd2f60a7 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 27 Oct 2017 04:42:36 +0200 Subject: sched/isolation: Handle the nohz_full= parameter We want to centralize the isolation management, done by the housekeeping subsystem. Therefore we need to handle the nohz_full= parameter from there. Since nohz_full= so far has involved unbound timers, watchdog, RCU and tilegx NAPI isolation, we keep that default behaviour. nohz_full= will be deprecated in the future. We want to control the isolation features from the isolcpus= parameter. Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1509072159-31808-10-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/isolation.h | 1 + include/linux/tick.h | 2 ++ init/Kconfig | 1 - kernel/sched/isolation.c | 42 +++++++++++++++++++++++++++++------------ kernel/time/tick-sched.c | 13 +++---------- 5 files changed, 36 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 9bb753eece3b..e53cfa96e91e 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -10,6 +10,7 @@ enum hk_flags { HK_FLAG_RCU = (1 << 1), HK_FLAG_MISC = (1 << 2), HK_FLAG_SCHED = (1 << 3), + HK_FLAG_TICK = (1 << 4), }; #ifdef CONFIG_CPU_ISOLATION diff --git a/include/linux/tick.h b/include/linux/tick.h index 68afc09aa8ac..e2a163a9f96c 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -228,6 +228,7 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal, extern void tick_nohz_full_kick_cpu(int cpu); extern void __tick_nohz_task_switch(void); +extern void __init tick_nohz_full_setup(cpumask_var_t cpumask); #else static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } @@ -248,6 +249,7 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal, static inline void tick_nohz_full_kick_cpu(int cpu) { } static inline void __tick_nohz_task_switch(void) { } +static inline void tick_nohz_full_setup(cpumask_var_t cpumask) { } #endif static inline void tick_nohz_task_switch(void) diff --git a/init/Kconfig b/init/Kconfig index 6f52e6f4bd9d..f8564df58d0a 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -474,7 +474,6 @@ endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION bool "CPU isolation" - depends on NO_HZ_FULL help Make sure that CPUs running critical tasks are not disturbed by any source of "noise" such as unbound workqueues, timers, kthreads... diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 37a138a780ff..1f61e440358d 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -54,23 +54,41 @@ EXPORT_SYMBOL_GPL(housekeeping_test_cpu); void __init housekeeping_init(void) { - if (!tick_nohz_full_enabled()) + if (!housekeeping_flags) return; - if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) { - WARN(1, "NO_HZ: Can't allocate not-full dynticks cpumask\n"); - cpumask_clear(tick_nohz_full_mask); - tick_nohz_full_running = false; - return; + static_branch_enable(&housekeeping_overriden); + + /* We need at least one CPU to handle housekeeping work */ + WARN_ON_ONCE(cpumask_empty(housekeeping_mask)); +} + +#ifdef CONFIG_NO_HZ_FULL +static int __init housekeeping_nohz_full_setup(char *str) +{ + cpumask_var_t non_housekeeping_mask; + + alloc_bootmem_cpumask_var(&non_housekeeping_mask); + if (cpulist_parse(str, non_housekeeping_mask) < 0) { + pr_warn("Housekeeping: Incorrect nohz_full cpumask\n"); + free_bootmem_cpumask_var(non_housekeeping_mask); + return 0; } - cpumask_andnot(housekeeping_mask, - cpu_possible_mask, tick_nohz_full_mask); + alloc_bootmem_cpumask_var(&housekeeping_mask); + cpumask_andnot(housekeeping_mask, cpu_possible_mask, non_housekeeping_mask); - housekeeping_flags = HK_FLAG_TIMER | HK_FLAG_RCU | HK_FLAG_MISC; + if (cpumask_empty(housekeeping_mask)) + cpumask_set_cpu(smp_processor_id(), housekeeping_mask); - static_branch_enable(&housekeeping_overriden); + housekeeping_flags = HK_FLAG_TICK | HK_FLAG_TIMER | + HK_FLAG_RCU | HK_FLAG_MISC; - /* We need at least one CPU to handle housekeeping work */ - WARN_ON_ONCE(cpumask_empty(housekeeping_mask)); + tick_nohz_full_setup(non_housekeeping_mask); + + free_bootmem_cpumask_var(non_housekeeping_mask); + + return 1; } +__setup("nohz_full=", housekeeping_nohz_full_setup); +#endif diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 27d7d522ac4e..69f3dbe38984 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -385,20 +385,13 @@ out: local_irq_restore(flags); } -/* Parse the boot-time nohz CPU list from the kernel parameters. */ -static int __init tick_nohz_full_setup(char *str) +/* Get the boot-time nohz CPU list from the kernel parameters. */ +void __init tick_nohz_full_setup(cpumask_var_t cpumask) { alloc_bootmem_cpumask_var(&tick_nohz_full_mask); - if (cpulist_parse(str, tick_nohz_full_mask) < 0) { - pr_warn("NO_HZ: Incorrect nohz_full cpumask\n"); - free_bootmem_cpumask_var(tick_nohz_full_mask); - return 1; - } + cpumask_copy(tick_nohz_full_mask, cpumask); tick_nohz_full_running = true; - - return 1; } -__setup("nohz_full=", tick_nohz_full_setup); static int tick_nohz_cpu_down(unsigned int cpu) { -- cgit v1.2.3 From edb9382175c3ebdced8ffdb3e0f20052ad9fdbe9 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 27 Oct 2017 04:42:37 +0200 Subject: sched/isolation: Move isolcpus= handling to the housekeeping code We want to centralize the isolation features, to be done by the housekeeping subsystem and scheduler domain isolation is a significant part of it. No intended behaviour change, we just reuse the housekeeping cpumask and core code. Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1509072159-31808-11-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- drivers/base/cpu.c | 11 ++++++- include/linux/sched.h | 2 -- include/linux/sched/isolation.h | 1 + kernel/cgroup/cpuset.c | 15 ++++------ kernel/sched/core.c | 16 +---------- kernel/sched/isolation.c | 63 ++++++++++++++++++++++++++++++++--------- kernel/sched/topology.c | 24 ++++------------ 7 files changed, 73 insertions(+), 59 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 321cd7b4d817..a73ab95558f5 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -18,6 +18,7 @@ #include #include #include +#include #include "base.h" @@ -271,8 +272,16 @@ static ssize_t print_cpus_isolated(struct device *dev, struct device_attribute *attr, char *buf) { int n = 0, len = PAGE_SIZE-2; + cpumask_var_t isolated; - n = scnprintf(buf, len, "%*pbl\n", cpumask_pr_args(cpu_isolated_map)); + if (!alloc_cpumask_var(&isolated, GFP_KERNEL)) + return -ENOMEM; + + cpumask_andnot(isolated, cpu_possible_mask, + housekeeping_cpumask(HK_FLAG_DOMAIN)); + n = scnprintf(buf, len, "%*pbl\n", cpumask_pr_args(isolated)); + + free_cpumask_var(isolated); return n; } diff --git a/include/linux/sched.h b/include/linux/sched.h index 0f897dfc195e..1b0cc0d6df8d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -165,8 +165,6 @@ struct task_group; /* Task command name length: */ #define TASK_COMM_LEN 16 -extern cpumask_var_t cpu_isolated_map; - extern void scheduler_tick(void); #define MAX_SCHEDULE_TIMEOUT LONG_MAX diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index e53cfa96e91e..d849431c8060 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -11,6 +11,7 @@ enum hk_flags { HK_FLAG_MISC = (1 << 2), HK_FLAG_SCHED = (1 << 3), HK_FLAG_TICK = (1 << 4), + HK_FLAG_DOMAIN = (1 << 5), }; #ifdef CONFIG_CPU_ISOLATION diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 4657e2924ecb..f7efa7b4d825 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -57,7 +57,7 @@ #include #include #include - +#include #include #include #include @@ -656,7 +656,6 @@ static int generate_sched_domains(cpumask_var_t **domains, int csn; /* how many cpuset ptrs in csa so far */ int i, j, k; /* indices for partition finding loops */ cpumask_var_t *doms; /* resulting partition; i.e. sched domains */ - cpumask_var_t non_isolated_cpus; /* load balanced CPUs */ struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ int nslot; /* next empty doms[] struct cpumask slot */ @@ -666,10 +665,6 @@ static int generate_sched_domains(cpumask_var_t **domains, dattr = NULL; csa = NULL; - if (!alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL)) - goto done; - cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); - /* Special case for the 99% of systems with one, full, sched domain */ if (is_sched_load_balance(&top_cpuset)) { ndoms = 1; @@ -683,7 +678,7 @@ static int generate_sched_domains(cpumask_var_t **domains, update_domain_attr_tree(dattr, &top_cpuset); } cpumask_and(doms[0], top_cpuset.effective_cpus, - non_isolated_cpus); + housekeeping_cpumask(HK_FLAG_DOMAIN)); goto done; } @@ -707,7 +702,8 @@ static int generate_sched_domains(cpumask_var_t **domains, */ if (!cpumask_empty(cp->cpus_allowed) && !(is_sched_load_balance(cp) && - cpumask_intersects(cp->cpus_allowed, non_isolated_cpus))) + cpumask_intersects(cp->cpus_allowed, + housekeeping_cpumask(HK_FLAG_DOMAIN)))) continue; if (is_sched_load_balance(cp)) @@ -789,7 +785,7 @@ restart: if (apn == b->pn) { cpumask_or(dp, dp, b->effective_cpus); - cpumask_and(dp, dp, non_isolated_cpus); + cpumask_and(dp, dp, housekeeping_cpumask(HK_FLAG_DOMAIN)); if (dattr) update_domain_attr_tree(dattr + nslot, b); @@ -802,7 +798,6 @@ restart: BUG_ON(nslot != ndoms); done: - free_cpumask_var(non_isolated_cpus); kfree(csa); /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2210c0203e51..1a55c842bfbc 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -84,9 +84,6 @@ __read_mostly int scheduler_running; */ int sysctl_sched_rt_runtime = 950000; -/* CPUs with isolated domains */ -cpumask_var_t cpu_isolated_map; - /* * __task_rq_lock - lock the rq @p resides on. */ @@ -5735,10 +5732,6 @@ static inline void sched_init_smt(void) { } void __init sched_init_smp(void) { - cpumask_var_t non_isolated_cpus; - - alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); - sched_init_numa(); /* @@ -5748,16 +5741,12 @@ void __init sched_init_smp(void) */ mutex_lock(&sched_domains_mutex); sched_init_domains(cpu_active_mask); - cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); - if (cpumask_empty(non_isolated_cpus)) - cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); mutex_unlock(&sched_domains_mutex); /* Move init over to a non-isolated CPU */ - if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0) + if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0) BUG(); sched_init_granularity(); - free_cpumask_var(non_isolated_cpus); init_sched_rt_class(); init_sched_dl_class(); @@ -5961,9 +5950,6 @@ void __init sched_init(void) calc_load_update = jiffies + LOAD_FREQ; #ifdef CONFIG_SMP - /* May be allocated at isolcpus cmdline parse time */ - if (cpu_isolated_map == NULL) - zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); idle_thread_set_boot_cpu(); set_cpu_rq_start_time(smp_processor_id()); #endif diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 1f61e440358d..8f666bc5abe8 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -63,32 +63,69 @@ void __init housekeeping_init(void) WARN_ON_ONCE(cpumask_empty(housekeeping_mask)); } -#ifdef CONFIG_NO_HZ_FULL -static int __init housekeeping_nohz_full_setup(char *str) +static int __init housekeeping_setup(char *str, enum hk_flags flags) { cpumask_var_t non_housekeeping_mask; + int err; alloc_bootmem_cpumask_var(&non_housekeeping_mask); - if (cpulist_parse(str, non_housekeeping_mask) < 0) { - pr_warn("Housekeeping: Incorrect nohz_full cpumask\n"); + err = cpulist_parse(str, non_housekeeping_mask); + if (err < 0 || cpumask_last(non_housekeeping_mask) >= nr_cpu_ids) { + pr_warn("Housekeeping: nohz_full= or isolcpus= incorrect CPU range\n"); free_bootmem_cpumask_var(non_housekeeping_mask); return 0; } - alloc_bootmem_cpumask_var(&housekeeping_mask); - cpumask_andnot(housekeeping_mask, cpu_possible_mask, non_housekeeping_mask); - - if (cpumask_empty(housekeeping_mask)) - cpumask_set_cpu(smp_processor_id(), housekeeping_mask); + if (!housekeeping_flags) { + alloc_bootmem_cpumask_var(&housekeeping_mask); + cpumask_andnot(housekeeping_mask, + cpu_possible_mask, non_housekeeping_mask); + if (cpumask_empty(housekeeping_mask)) + cpumask_set_cpu(smp_processor_id(), housekeeping_mask); + } else { + cpumask_var_t tmp; + + alloc_bootmem_cpumask_var(&tmp); + cpumask_andnot(tmp, cpu_possible_mask, non_housekeeping_mask); + if (!cpumask_equal(tmp, housekeeping_mask)) { + pr_warn("Housekeeping: nohz_full= must match isolcpus=\n"); + free_bootmem_cpumask_var(tmp); + free_bootmem_cpumask_var(non_housekeeping_mask); + return 0; + } + free_bootmem_cpumask_var(tmp); + } - housekeeping_flags = HK_FLAG_TICK | HK_FLAG_TIMER | - HK_FLAG_RCU | HK_FLAG_MISC; + if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) { + if (IS_ENABLED(CONFIG_NO_HZ_FULL)) { + tick_nohz_full_setup(non_housekeeping_mask); + } else { + pr_warn("Housekeeping: nohz unsupported." + " Build with CONFIG_NO_HZ_FULL\n"); + free_bootmem_cpumask_var(non_housekeeping_mask); + return 0; + } + } - tick_nohz_full_setup(non_housekeeping_mask); + housekeeping_flags |= flags; free_bootmem_cpumask_var(non_housekeeping_mask); return 1; } + +static int __init housekeeping_nohz_full_setup(char *str) +{ + unsigned int flags; + + flags = HK_FLAG_TICK | HK_FLAG_TIMER | HK_FLAG_RCU | HK_FLAG_MISC; + + return housekeeping_setup(str, flags); +} __setup("nohz_full=", housekeeping_nohz_full_setup); -#endif + +static int __init housekeeping_isolcpus_setup(char *str) +{ + return housekeeping_setup(str, HK_FLAG_DOMAIN); +} +__setup("isolcpus=", housekeeping_isolcpus_setup); diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index e3d31b0880dc..2e6b9126ffdc 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -3,6 +3,7 @@ */ #include #include +#include #include "sched.h" @@ -469,21 +470,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) update_top_cache_domain(cpu); } -/* Setup the mask of CPUs configured for isolated domains */ -static int __init isolated_cpu_setup(char *str) -{ - int ret; - - alloc_bootmem_cpumask_var(&cpu_isolated_map); - ret = cpulist_parse(str, cpu_isolated_map); - if (ret || cpumask_last(cpu_isolated_map) >= nr_cpu_ids) { - pr_err("sched: Error, all isolcpus= values must be between 0 and %u - ignoring them.\n", nr_cpu_ids-1); - return 0; - } - return 1; -} -__setup("isolcpus=", isolated_cpu_setup); - struct s_data { struct sched_domain ** __percpu sd; struct root_domain *rd; @@ -1792,7 +1778,7 @@ int sched_init_domains(const struct cpumask *cpu_map) doms_cur = alloc_sched_domains(ndoms_cur); if (!doms_cur) doms_cur = &fallback_doms; - cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); + cpumask_and(doms_cur[0], cpu_map, housekeeping_cpumask(HK_FLAG_DOMAIN)); err = build_sched_domains(doms_cur[0], NULL); register_sched_domain_sysctl(); @@ -1875,7 +1861,8 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], doms_new = alloc_sched_domains(1); if (doms_new) { n = 1; - cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); + cpumask_and(doms_new[0], cpu_active_mask, + housekeeping_cpumask(HK_FLAG_DOMAIN)); } } else { n = ndoms_new; @@ -1898,7 +1885,8 @@ match1: if (!doms_new) { n = 0; doms_new = &fallback_doms; - cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); + cpumask_and(doms_new[0], cpu_active_mask, + housekeeping_cpumask(HK_FLAG_DOMAIN)); } /* Build new domains: */ -- cgit v1.2.3 From 7d9285e82db5defca4d9674ba089429eeca0c697 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 5 Oct 2017 09:19:19 -0700 Subject: perf/bpf: Extend the perf_event_read_local() interface, a.k.a. "bpf: perf event change needed for subsequent bpf helpers" eBPF programs would like access to the (perf) event enabled and running times along with the event value, such that they can deal with event multiplexing (among other things). This patch extends the interface; a future eBPF patch will utilize the new functionality. [ Note, there's a same-content commit with a poor changelog and a meaningless title in the networking tree as well - but we need this change for subsequent perf work, so apply it here as well, with a proper changelog. Hopefully Git will be able to sort out this somewhat messy workflow, if there are no other, conflicting changes to these files. ] Signed-off-by: Yonghong Song [ Rewrote the changelog. ] Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Cc: Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: David S. Miller Link: http://lkml.kernel.org/r/20171005161923.332790-2-yhs@fb.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 7 +++++-- kernel/bpf/arraymap.c | 2 +- kernel/events/core.c | 15 +++++++++++++-- kernel/trace/bpf_trace.c | 2 +- 4 files changed, 20 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 8e22f24ded6a..79b18a20cf5d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -806,6 +806,7 @@ struct perf_output_handle { struct bpf_perf_event_data_kern { struct pt_regs *regs; struct perf_sample_data *data; + struct perf_event *event; }; #ifdef CONFIG_CGROUP_PERF @@ -884,7 +885,8 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); -int perf_event_read_local(struct perf_event *event, u64 *value); +int perf_event_read_local(struct perf_event *event, u64 *value, + u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); @@ -1286,7 +1288,8 @@ static inline const struct perf_event_attr *perf_event_attrs(struct perf_event * { return ERR_PTR(-EINVAL); } -static inline int perf_event_read_local(struct perf_event *event, u64 *value) +static inline int perf_event_read_local(struct perf_event *event, u64 *value, + u64 *enabled, u64 *running) { return -EINVAL; } diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index e2636737b69b..c4b9ab01bba5 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -492,7 +492,7 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, ee = ERR_PTR(-EOPNOTSUPP); event = perf_file->private_data; - if (perf_event_read_local(event, &value) == -EOPNOTSUPP) + if (perf_event_read_local(event, &value, NULL, NULL) == -EOPNOTSUPP) goto err_out; ee = bpf_event_entry_gen(perf_file, map_file); diff --git a/kernel/events/core.c b/kernel/events/core.c index 04989fb769f0..74671e101b92 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3684,10 +3684,12 @@ static inline u64 perf_event_count(struct perf_event *event) * will not be local and we cannot read them atomically * - must not have a pmu::count method */ -int perf_event_read_local(struct perf_event *event, u64 *value) +int perf_event_read_local(struct perf_event *event, u64 *value, + u64 *enabled, u64 *running) { unsigned long flags; int ret = 0; + u64 now; /* * Disabling interrupts avoids all counter scheduling (context @@ -3718,13 +3720,21 @@ int perf_event_read_local(struct perf_event *event, u64 *value) goto out; } + now = event->shadow_ctx_time + perf_clock(); + if (enabled) + *enabled = now - event->tstamp_enabled; /* * If the event is currently on this CPU, its either a per-task event, * or local to this CPU. Furthermore it means its ACTIVE (otherwise * oncpu == -1). */ - if (event->oncpu == smp_processor_id()) + if (event->oncpu == smp_processor_id()) { event->pmu->read(event); + if (running) + *running = now - event->tstamp_running; + } else if (running) { + *running = event->total_time_running; + } *value = local64_read(&event->count); out: @@ -8072,6 +8082,7 @@ static void bpf_overflow_handler(struct perf_event *event, struct bpf_perf_event_data_kern ctx = { .data = data, .regs = regs, + .event = event, }; int ret = 0; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index dc498b605d5d..95888ae6c263 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -275,7 +275,7 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) if (!ee) return -ENOENT; - err = perf_event_read_local(ee->event, &value); + err = perf_event_read_local(ee->event, &value, NULL, NULL); /* * this api is ugly since we miss [-22..-2] range of valid * counter values, but that's uapi -- cgit v1.2.3 From 8ca2bd41c7d1c135e9ac6f25970c2d491865088a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Sep 2017 14:12:35 +0200 Subject: perf/core: Rename 'enum perf_event_active_state' Its a weird name, active is one of the states, it should not be part of the name, also, its too long. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 6 +++--- kernel/events/core.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 79b18a20cf5d..b7532650de47 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -485,9 +485,9 @@ struct perf_addr_filters_head { }; /** - * enum perf_event_active_state - the states of a event + * enum perf_event_state - the states of a event */ -enum perf_event_active_state { +enum perf_event_state { PERF_EVENT_STATE_DEAD = -4, PERF_EVENT_STATE_EXIT = -3, PERF_EVENT_STATE_ERROR = -2, @@ -578,7 +578,7 @@ struct perf_event { struct pmu *pmu; void *pmu_private; - enum perf_event_active_state state; + enum perf_event_state state; unsigned int attach_state; local64_t count; atomic64_t child_count; diff --git a/kernel/events/core.c b/kernel/events/core.c index b249e0f197a7..6322e245176c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10801,7 +10801,7 @@ inherit_event(struct perf_event *parent_event, struct perf_event *group_leader, struct perf_event_context *child_ctx) { - enum perf_event_active_state parent_state = parent_event->state; + enum perf_event_state parent_state = parent_event->state; struct perf_event *child_event; unsigned long flags; -- cgit v1.2.3 From 0d3d73aac2ff05c78387aa9dcc2c8aa3804405e7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Sep 2017 14:16:28 +0200 Subject: perf/core: Rewrite event timekeeping The current even timekeeping, which computes enabled and running times, uses 3 distinct timestamps to reflect the various event states: OFF (stopped), INACTIVE (enabled) and ACTIVE (running). Furthermore, the update rules are such that even INACTIVE events need their timestamps updated. This is undesirable because we'd like to not touch INACTIVE events if at all possible, this makes event scheduling (much) more expensive than needed. Rewrite the timekeeping to directly use event->state, this greatly simplifies the code and results in only having to update things when we change state, or an up-to-date value is requested (read). Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 19 +-- kernel/events/core.c | 385 +++++++++++++++------------------------------ 2 files changed, 130 insertions(+), 274 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b7532650de47..874b71a70058 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -588,26 +588,10 @@ struct perf_event { * has been enabled (i.e. eligible to run, and the task has * been scheduled in, if this is a per-task event) * and running (scheduled onto the CPU), respectively. - * - * They are computed from tstamp_enabled, tstamp_running and - * tstamp_stopped when the event is in INACTIVE or ACTIVE state. */ u64 total_time_enabled; u64 total_time_running; - - /* - * These are timestamps used for computing total_time_enabled - * and total_time_running when the event is in INACTIVE or - * ACTIVE state, measured in nanoseconds from an arbitrary point - * in time. - * tstamp_enabled: the notional time when the event was enabled - * tstamp_running: the notional time when the event was scheduled on - * tstamp_stopped: in INACTIVE state, the notional time when the - * event was scheduled off. - */ - u64 tstamp_enabled; - u64 tstamp_running; - u64 tstamp_stopped; + u64 tstamp; /* * timestamp shadows the actual context timing but it can @@ -699,7 +683,6 @@ struct perf_event { #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; /* cgroup event is attach to */ - int cgrp_defer_enabled; #endif struct list_head sb_list; diff --git a/kernel/events/core.c b/kernel/events/core.c index 6f74f9c35490..2551e8ce7224 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -582,6 +582,88 @@ static inline u64 perf_event_clock(struct perf_event *event) return event->clock(); } +/* + * State based event timekeeping... + * + * The basic idea is to use event->state to determine which (if any) time + * fields to increment with the current delta. This means we only need to + * update timestamps when we change state or when they are explicitly requested + * (read). + * + * Event groups make things a little more complicated, but not terribly so. The + * rules for a group are that if the group leader is OFF the entire group is + * OFF, irrespecive of what the group member states are. This results in + * __perf_effective_state(). + * + * A futher ramification is that when a group leader flips between OFF and + * !OFF, we need to update all group member times. + * + * + * NOTE: perf_event_time() is based on the (cgroup) context time, and thus we + * need to make sure the relevant context time is updated before we try and + * update our timestamps. + */ + +static __always_inline enum perf_event_state +__perf_effective_state(struct perf_event *event) +{ + struct perf_event *leader = event->group_leader; + + if (leader->state <= PERF_EVENT_STATE_OFF) + return leader->state; + + return event->state; +} + +static __always_inline void +__perf_update_times(struct perf_event *event, u64 now, u64 *enabled, u64 *running) +{ + enum perf_event_state state = __perf_effective_state(event); + u64 delta = now - event->tstamp; + + *enabled = event->total_time_enabled; + if (state >= PERF_EVENT_STATE_INACTIVE) + *enabled += delta; + + *running = event->total_time_running; + if (state >= PERF_EVENT_STATE_ACTIVE) + *running += delta; +} + +static void perf_event_update_time(struct perf_event *event) +{ + u64 now = perf_event_time(event); + + __perf_update_times(event, now, &event->total_time_enabled, + &event->total_time_running); + event->tstamp = now; +} + +static void perf_event_update_sibling_time(struct perf_event *leader) +{ + struct perf_event *sibling; + + list_for_each_entry(sibling, &leader->sibling_list, group_entry) + perf_event_update_time(sibling); +} + +static void +perf_event_set_state(struct perf_event *event, enum perf_event_state state) +{ + if (event->state == state) + return; + + perf_event_update_time(event); + /* + * If a group leader gets enabled/disabled all its siblings + * are affected too. + */ + if ((event->state < 0) ^ (state < 0)) + perf_event_update_sibling_time(event); + + WRITE_ONCE(event->state, state); +} + #ifdef CONFIG_CGROUP_PERF static inline bool @@ -841,40 +923,6 @@ perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) event->shadow_ctx_time = now - t->timestamp; } -static inline void -perf_cgroup_defer_enabled(struct perf_event *event) -{ - /* - * when the current task's perf cgroup does not match - * the event's, we need to remember to call the - * perf_mark_enable() function the first time a task with - * a matching perf cgroup is scheduled in. - */ - if (is_cgroup_event(event) && !perf_cgroup_match(event)) - event->cgrp_defer_enabled = 1; -} - -static inline void -perf_cgroup_mark_enabled(struct perf_event *event, - struct perf_event_context *ctx) -{ - struct perf_event *sub; - u64 tstamp = perf_event_time(event); - - if (!event->cgrp_defer_enabled) - return; - - event->cgrp_defer_enabled = 0; - - event->tstamp_enabled = tstamp - event->total_time_enabled; - list_for_each_entry(sub, &event->sibling_list, group_entry) { - if (sub->state >= PERF_EVENT_STATE_INACTIVE) { - sub->tstamp_enabled = tstamp - sub->total_time_enabled; - sub->cgrp_defer_enabled = 0; - } - } -} - /* * Update cpuctx->cgrp so that it is set when first cgroup event is added and * cleared when last cgroup event is removed. @@ -972,17 +1020,6 @@ static inline u64 perf_cgroup_event_time(struct perf_event *event) return 0; } -static inline void -perf_cgroup_defer_enabled(struct perf_event *event) -{ -} - -static inline void -perf_cgroup_mark_enabled(struct perf_event *event, - struct perf_event_context *ctx) -{ -} - static inline void list_update_cgroup_event(struct perf_event *event, struct perf_event_context *ctx, bool add) @@ -1396,60 +1433,6 @@ static u64 perf_event_time(struct perf_event *event) return ctx ? ctx->time : 0; } -/* - * Update the total_time_enabled and total_time_running fields for a event. - */ -static void update_event_times(struct perf_event *event) -{ - struct perf_event_context *ctx = event->ctx; - u64 run_end; - - lockdep_assert_held(&ctx->lock); - - if (event->state < PERF_EVENT_STATE_INACTIVE || - event->group_leader->state < PERF_EVENT_STATE_INACTIVE) - return; - - /* - * in cgroup mode, time_enabled represents - * the time the event was enabled AND active - * tasks were in the monitored cgroup. This is - * independent of the activity of the context as - * there may be a mix of cgroup and non-cgroup events. - * - * That is why we treat cgroup events differently - * here. - */ - if (is_cgroup_event(event)) - run_end = perf_cgroup_event_time(event); - else if (ctx->is_active) - run_end = ctx->time; - else - run_end = event->tstamp_stopped; - - event->total_time_enabled = run_end - event->tstamp_enabled; - - if (event->state == PERF_EVENT_STATE_INACTIVE) - run_end = event->tstamp_stopped; - else - run_end = perf_event_time(event); - - event->total_time_running = run_end - event->tstamp_running; - -} - -/* - * Update total_time_enabled and total_time_running for all events in a group. - */ -static void update_group_times(struct perf_event *leader) -{ - struct perf_event *event; - - update_event_times(leader); - list_for_each_entry(event, &leader->sibling_list, group_entry) - update_event_times(event); -} - static enum event_type_t get_event_type(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; @@ -1492,6 +1475,8 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT); event->attach_state |= PERF_ATTACH_CONTEXT; + event->tstamp = perf_event_time(event); + /* * If we're a stand alone event or group leader, we go to the context * list, group events are kept attached to the group so that @@ -1699,8 +1684,6 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) if (event->group_leader == event) list_del_init(&event->group_entry); - update_group_times(event); - /* * If event was in error state, then keep it * that way, otherwise bogus counts will be @@ -1709,7 +1692,7 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) * of the event */ if (event->state > PERF_EVENT_STATE_OFF) - event->state = PERF_EVENT_STATE_OFF; + perf_event_set_state(event, PERF_EVENT_STATE_OFF); ctx->generation++; } @@ -1808,38 +1791,24 @@ event_sched_out(struct perf_event *event, struct perf_cpu_context *cpuctx, struct perf_event_context *ctx) { - u64 tstamp = perf_event_time(event); - u64 delta; + enum perf_event_state state = PERF_EVENT_STATE_INACTIVE; WARN_ON_ONCE(event->ctx != ctx); lockdep_assert_held(&ctx->lock); - /* - * An event which could not be activated because of - * filter mismatch still needs to have its timings - * maintained, otherwise bogus information is return - * via read() for time_enabled, time_running: - */ - if (event->state == PERF_EVENT_STATE_INACTIVE && - !event_filter_match(event)) { - delta = tstamp - event->tstamp_stopped; - event->tstamp_running += delta; - event->tstamp_stopped = tstamp; - } - if (event->state != PERF_EVENT_STATE_ACTIVE) return; perf_pmu_disable(event->pmu); - event->tstamp_stopped = tstamp; event->pmu->del(event, 0); event->oncpu = -1; - event->state = PERF_EVENT_STATE_INACTIVE; + if (event->pending_disable) { event->pending_disable = 0; - event->state = PERF_EVENT_STATE_OFF; + state = PERF_EVENT_STATE_OFF; } + perf_event_set_state(event, state); if (!is_software_event(event)) cpuctx->active_oncpu--; @@ -1859,7 +1828,9 @@ group_sched_out(struct perf_event *group_event, struct perf_event_context *ctx) { struct perf_event *event; - int state = group_event->state; + + if (group_event->state != PERF_EVENT_STATE_ACTIVE) + return; perf_pmu_disable(ctx->pmu); @@ -1873,7 +1844,7 @@ group_sched_out(struct perf_event *group_event, perf_pmu_enable(ctx->pmu); - if (state == PERF_EVENT_STATE_ACTIVE && group_event->attr.exclusive) + if (group_event->attr.exclusive) cpuctx->exclusive = 0; } @@ -1965,12 +1936,12 @@ static void __perf_event_disable(struct perf_event *event, update_cgrp_time_from_event(event); } - update_group_times(event); if (event == event->group_leader) group_sched_out(event, cpuctx, ctx); else event_sched_out(event, cpuctx, ctx); - event->state = PERF_EVENT_STATE_OFF; + + perf_event_set_state(event, PERF_EVENT_STATE_OFF); } /* @@ -2027,8 +1998,7 @@ void perf_event_disable_inatomic(struct perf_event *event) } static void perf_set_shadow_time(struct perf_event *event, - struct perf_event_context *ctx, - u64 tstamp) + struct perf_event_context *ctx) { /* * use the correct time source for the time snapshot @@ -2056,9 +2026,9 @@ static void perf_set_shadow_time(struct perf_event *event, * is cleaner and simpler to understand. */ if (is_cgroup_event(event)) - perf_cgroup_set_shadow_time(event, tstamp); + perf_cgroup_set_shadow_time(event, event->tstamp); else - event->shadow_ctx_time = tstamp - ctx->timestamp; + event->shadow_ctx_time = event->tstamp - ctx->timestamp; } #define MAX_INTERRUPTS (~0ULL) @@ -2071,7 +2041,6 @@ event_sched_in(struct perf_event *event, struct perf_cpu_context *cpuctx, struct perf_event_context *ctx) { - u64 tstamp = perf_event_time(event); int ret = 0; lockdep_assert_held(&ctx->lock); @@ -2086,7 +2055,7 @@ event_sched_in(struct perf_event *event, * ->oncpu if it sees ACTIVE. */ smp_wmb(); - WRITE_ONCE(event->state, PERF_EVENT_STATE_ACTIVE); + perf_event_set_state(event, PERF_EVENT_STATE_ACTIVE); /* * Unthrottle events, since we scheduled we might have missed several @@ -2100,19 +2069,17 @@ event_sched_in(struct perf_event *event, perf_pmu_disable(event->pmu); - perf_set_shadow_time(event, ctx, tstamp); + perf_set_shadow_time(event, ctx); perf_log_itrace_start(event); if (event->pmu->add(event, PERF_EF_START)) { - event->state = PERF_EVENT_STATE_INACTIVE; + perf_event_set_state(event, PERF_EVENT_STATE_INACTIVE); event->oncpu = -1; ret = -EAGAIN; goto out; } - event->tstamp_running += tstamp - event->tstamp_stopped; - if (!is_software_event(event)) cpuctx->active_oncpu++; if (!ctx->nr_active++) @@ -2136,8 +2103,6 @@ group_sched_in(struct perf_event *group_event, { struct perf_event *event, *partial_group = NULL; struct pmu *pmu = ctx->pmu; - u64 now = ctx->time; - bool simulate = false; if (group_event->state == PERF_EVENT_STATE_OFF) return 0; @@ -2167,27 +2132,13 @@ group_error: /* * Groups can be scheduled in as one unit only, so undo any * partial group before returning: - * The events up to the failed event are scheduled out normally, - * tstamp_stopped will be updated. - * - * The failed events and the remaining siblings need to have - * their timings updated as if they had gone thru event_sched_in() - * and event_sched_out(). This is required to get consistent timings - * across the group. This also takes care of the case where the group - * could never be scheduled by ensuring tstamp_stopped is set to mark - * the time the event was actually stopped, such that time delta - * calculation in update_event_times() is correct. + * The events up to the failed event are scheduled out normally. */ list_for_each_entry(event, &group_event->sibling_list, group_entry) { if (event == partial_group) - simulate = true; + break; - if (simulate) { - event->tstamp_running += now - event->tstamp_stopped; - event->tstamp_stopped = now; - } else { - event_sched_out(event, cpuctx, ctx); - } + event_sched_out(event, cpuctx, ctx); } event_sched_out(group_event, cpuctx, ctx); @@ -2229,46 +2180,11 @@ static int group_can_go_on(struct perf_event *event, return can_add_hw; } -/* - * Complement to update_event_times(). This computes the tstamp_* values to - * continue 'enabled' state from @now, and effectively discards the time - * between the prior tstamp_stopped and now (as we were in the OFF state, or - * just switched (context) time base). - * - * This further assumes '@event->state == INACTIVE' (we just came from OFF) and - * cannot have been scheduled in yet. And going into INACTIVE state means - * '@event->tstamp_stopped = @now'. - * - * Thus given the rules of update_event_times(): - * - * total_time_enabled = tstamp_stopped - tstamp_enabled - * total_time_running = tstamp_stopped - tstamp_running - * - * We can insert 'tstamp_stopped == now' and reverse them to compute new - * tstamp_* values. - */ -static void __perf_event_enable_time(struct perf_event *event, u64 now) -{ - WARN_ON_ONCE(event->state != PERF_EVENT_STATE_INACTIVE); - - event->tstamp_stopped = now; - event->tstamp_enabled = now - event->total_time_enabled; - event->tstamp_running = now - event->total_time_running; -} - static void add_event_to_ctx(struct perf_event *event, struct perf_event_context *ctx) { - u64 tstamp = perf_event_time(event); - list_add_event(event, ctx); perf_group_attach(event); - /* - * We can be called with event->state == STATE_OFF when we create with - * .disabled = 1. In that case the IOC_ENABLE will call this function. - */ - if (event->state == PERF_EVENT_STATE_INACTIVE) - __perf_event_enable_time(event, tstamp); } static void ctx_sched_out(struct perf_event_context *ctx, @@ -2499,28 +2415,6 @@ again: raw_spin_unlock_irq(&ctx->lock); } -/* - * Put a event into inactive state and update time fields. - * Enabling the leader of a group effectively enables all - * the group members that aren't explicitly disabled, so we - * have to update their ->tstamp_enabled also. - * Note: this works for group members as well as group leaders - * since the non-leader members' sibling_lists will be empty. - */ -static void __perf_event_mark_enabled(struct perf_event *event) -{ - struct perf_event *sub; - u64 tstamp = perf_event_time(event); - - event->state = PERF_EVENT_STATE_INACTIVE; - __perf_event_enable_time(event, tstamp); - list_for_each_entry(sub, &event->sibling_list, group_entry) { - /* XXX should not be > INACTIVE if event isn't */ - if (sub->state >= PERF_EVENT_STATE_INACTIVE) - __perf_event_enable_time(sub, tstamp); - } -} - /* * Cross CPU call to enable a performance event */ @@ -2539,14 +2433,12 @@ static void __perf_event_enable(struct perf_event *event, if (ctx->is_active) ctx_sched_out(ctx, cpuctx, EVENT_TIME); - __perf_event_mark_enabled(event); + perf_event_set_state(event, PERF_EVENT_STATE_INACTIVE); if (!ctx->is_active) return; if (!event_filter_match(event)) { - if (is_cgroup_event(event)) - perf_cgroup_defer_enabled(event); ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); return; } @@ -2866,18 +2758,10 @@ static void __perf_event_sync_stat(struct perf_event *event, * we know the event must be on the current CPU, therefore we * don't need to use it. */ - switch (event->state) { - case PERF_EVENT_STATE_ACTIVE: + if (event->state == PERF_EVENT_STATE_ACTIVE) event->pmu->read(event); - /* fall-through */ - case PERF_EVENT_STATE_INACTIVE: - update_event_times(event); - break; - - default: - break; - } + perf_event_update_time(event); /* * In order to keep per-task stats reliable we need to flip the event @@ -3114,10 +2998,6 @@ ctx_pinned_sched_in(struct perf_event_context *ctx, if (!event_filter_match(event)) continue; - /* may need to reset tstamp_enabled */ - if (is_cgroup_event(event)) - perf_cgroup_mark_enabled(event, ctx); - if (group_can_go_on(event, cpuctx, 1)) group_sched_in(event, cpuctx, ctx); @@ -3125,10 +3005,8 @@ ctx_pinned_sched_in(struct perf_event_context *ctx, * If this pinned group hasn't been scheduled, * put it in error state. */ - if (event->state == PERF_EVENT_STATE_INACTIVE) { - update_group_times(event); - event->state = PERF_EVENT_STATE_ERROR; - } + if (event->state == PERF_EVENT_STATE_INACTIVE) + perf_event_set_state(event, PERF_EVENT_STATE_ERROR); } } @@ -3150,10 +3028,6 @@ ctx_flexible_sched_in(struct perf_event_context *ctx, if (!event_filter_match(event)) continue; - /* may need to reset tstamp_enabled */ - if (is_cgroup_event(event)) - perf_cgroup_mark_enabled(event, ctx); - if (group_can_go_on(event, cpuctx, can_add_hw)) { if (group_sched_in(event, cpuctx, ctx)) can_add_hw = 0; @@ -3545,7 +3419,7 @@ static int event_enable_on_exec(struct perf_event *event, if (event->state >= PERF_EVENT_STATE_INACTIVE) return 0; - __perf_event_mark_enabled(event); + perf_event_set_state(event, PERF_EVENT_STATE_INACTIVE); return 1; } @@ -3644,10 +3518,9 @@ static void __perf_event_read(void *info) update_cgrp_time_from_event(event); } - if (!data->group) - update_event_times(event); - else - update_group_times(event); + perf_event_update_time(event); + if (data->group) + perf_event_update_sibling_time(event); if (event->state != PERF_EVENT_STATE_ACTIVE) goto unlock; @@ -3696,7 +3569,6 @@ int perf_event_read_local(struct perf_event *event, u64 *value, { unsigned long flags; int ret = 0; - u64 now; /* * Disabling interrupts avoids all counter scheduling (context @@ -3727,23 +3599,26 @@ int perf_event_read_local(struct perf_event *event, u64 *value, goto out; } - now = event->shadow_ctx_time + perf_clock(); - if (enabled) - *enabled = now - event->tstamp_enabled; + /* * If the event is currently on this CPU, its either a per-task event, * or local to this CPU. Furthermore it means its ACTIVE (otherwise * oncpu == -1). */ - if (event->oncpu == smp_processor_id()) { + if (event->oncpu == smp_processor_id()) event->pmu->read(event); - if (running) - *running = now - event->tstamp_running; - } else if (running) { - *running = event->total_time_running; - } *value = local64_read(&event->count); + if (enabled || running) { + u64 now = event->shadow_ctx_time + perf_clock(); + u64 __enabled, __running; + + __perf_update_times(event, now, &__enabled, &__running); + if (enabled) + *enabled = __enabled; + if (running) + *running = __running; + } out: local_irq_restore(flags); @@ -3818,10 +3693,9 @@ again: update_cgrp_time_from_event(event); } + perf_event_update_time(event); if (group) - update_group_times(event); - else - update_event_times(event); + perf_event_update_sibling_time(event); raw_spin_unlock_irqrestore(&ctx->lock, flags); } @@ -4945,8 +4819,7 @@ static void calc_timer_values(struct perf_event *event, *now = perf_clock(); ctx_time = event->shadow_ctx_time + *now; - *enabled = ctx_time - event->tstamp_enabled; - *running = ctx_time - event->tstamp_running; + __perf_update_times(event, ctx_time, enabled, running); } static void perf_event_init_userpage(struct perf_event *event) @@ -10581,7 +10454,7 @@ perf_event_exit_event(struct perf_event *child_event, if (parent_event) perf_group_detach(child_event); list_del_event(child_event, child_ctx); - child_event->state = PERF_EVENT_STATE_EXIT; /* is_event_hup() */ + perf_event_set_state(child_event, PERF_EVENT_STATE_EXIT); /* is_event_hup() */ raw_spin_unlock_irq(&child_ctx->lock); /* -- cgit v1.2.3 From 186731145f920fb1514200043bcaf9c689693857 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 10 Sep 2017 11:44:46 +0200 Subject: hwmon: (sht15) Root out platform data After finding out there are active users of this sensor I noticed: - It has a single PXA27x board file using the platform data - The platform data is only used to carry two GPIO pins, all other fields are unused - The driver does not use GPIO descriptors but the legacy GPIO API I saw we can swiftly fix this by: - Killing off the platform data entirely - Define a GPIO descriptor lookup table in the board file - Use the standard devm_gpiod_get() to grab the GPIO descriptors from either the device tree or the board file table. This compiles, but needs testing. Cc: arm@kernel.org Cc: Marco Franchi Cc: Davide Hug Cc: Jonathan Cameron Signed-off-by: Linus Walleij Acked-by: Arnd Bergmann Tested-by: Marco Franchi Acked-by: Arnd Bergmann Signed-off-by: Guenter Roeck --- Documentation/hwmon/sht15 | 3 +- arch/arm/mach-pxa/stargate2.c | 17 ++-- drivers/hwmon/sht15.c | 167 ++++++++++++------------------------ include/linux/platform_data/sht15.h | 38 -------- 4 files changed, 65 insertions(+), 160 deletions(-) delete mode 100644 include/linux/platform_data/sht15.h (limited to 'include/linux') diff --git a/Documentation/hwmon/sht15 b/Documentation/hwmon/sht15 index 778987d1856f..5e3207c3b177 100644 --- a/Documentation/hwmon/sht15 +++ b/Documentation/hwmon/sht15 @@ -42,8 +42,7 @@ chip. These coefficients are used to internally calibrate the signals from the sensors. Disabling the reload of those coefficients allows saving 10ms for each measurement and decrease power consumption, while losing on precision. -Some options may be set directly in the sht15_platform_data structure -or via sysfs attributes. +Some options may be set via sysfs attributes. Notes: * The regulator supply name is set to "vcc". diff --git a/arch/arm/mach-pxa/stargate2.c b/arch/arm/mach-pxa/stargate2.c index 2d45d18b1a5e..6b7df6fd2448 100644 --- a/arch/arm/mach-pxa/stargate2.c +++ b/arch/arm/mach-pxa/stargate2.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -52,7 +53,6 @@ #include #include #include -#include #include "devices.h" #include "generic.h" @@ -137,17 +137,18 @@ static unsigned long sg2_im2_unified_pin_config[] __initdata = { GPIO10_GPIO, /* large basic connector pin 23 */ }; -static struct sht15_platform_data platform_data_sht15 = { - .gpio_data = 100, - .gpio_sck = 98, +static struct gpiod_lookup_table sht15_gpiod_table = { + .dev_id = "sht15", + .table = { + /* FIXME: should this have |GPIO_OPEN_DRAIN set? */ + GPIO_LOOKUP("gpio-pxa", 100, "data", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("gpio-pxa", 98, "clk", GPIO_ACTIVE_HIGH), + }, }; static struct platform_device sht15 = { .name = "sht15", .id = -1, - .dev = { - .platform_data = &platform_data_sht15, - }, }; static struct regulator_consumer_supply stargate2_sensor_3_con[] = { @@ -608,6 +609,7 @@ static void __init imote2_init(void) imote2_stargate2_init(); + gpiod_add_lookup_table(&sht15_gpiod_table); platform_add_devices(imote2_devices, ARRAY_SIZE(imote2_devices)); i2c_register_board_info(0, imote2_i2c_board_info, @@ -988,6 +990,7 @@ static void __init stargate2_init(void) imote2_stargate2_init(); + gpiod_add_lookup_table(&sht15_gpiod_table); platform_add_devices(ARRAY_AND_SIZE(stargate2_devices)); i2c_register_board_info(0, ARRAY_AND_SIZE(stargate2_i2c_board_info)); diff --git a/drivers/hwmon/sht15.c b/drivers/hwmon/sht15.c index e4d642b673c6..0e3e5f83f5cf 100644 --- a/drivers/hwmon/sht15.c +++ b/drivers/hwmon/sht15.c @@ -18,13 +18,11 @@ #include #include -#include #include #include #include #include #include -#include #include #include #include @@ -34,7 +32,8 @@ #include #include #include -#include +#include +#include /* Commands */ #define SHT15_MEASURE_TEMP 0x03 @@ -122,7 +121,8 @@ static const u8 sht15_crc8_table[] = { /** * struct sht15_data - device instance specific data - * @pdata: platform data (gpio's etc). + * @sck: clock GPIO line + * @data: data GPIO line * @read_work: bh of interrupt handler. * @wait_queue: wait queue for getting values from device. * @val_temp: last temperature value read from device. @@ -150,7 +150,8 @@ static const u8 sht15_crc8_table[] = { * @interrupt_handled: flag used to indicate a handler has been scheduled. */ struct sht15_data { - struct sht15_platform_data *pdata; + struct gpio_desc *sck; + struct gpio_desc *data; struct work_struct read_work; wait_queue_head_t wait_queue; uint16_t val_temp; @@ -205,16 +206,16 @@ static int sht15_connection_reset(struct sht15_data *data) { int i, err; - err = gpio_direction_output(data->pdata->gpio_data, 1); + err = gpiod_direction_output(data->data, 1); if (err) return err; ndelay(SHT15_TSCKL); - gpio_set_value(data->pdata->gpio_sck, 0); + gpiod_set_value(data->sck, 0); ndelay(SHT15_TSCKL); for (i = 0; i < 9; ++i) { - gpio_set_value(data->pdata->gpio_sck, 1); + gpiod_set_value(data->sck, 1); ndelay(SHT15_TSCKH); - gpio_set_value(data->pdata->gpio_sck, 0); + gpiod_set_value(data->sck, 0); ndelay(SHT15_TSCKL); } return 0; @@ -227,11 +228,11 @@ static int sht15_connection_reset(struct sht15_data *data) */ static inline void sht15_send_bit(struct sht15_data *data, int val) { - gpio_set_value(data->pdata->gpio_data, val); + gpiod_set_value(data->data, val); ndelay(SHT15_TSU); - gpio_set_value(data->pdata->gpio_sck, 1); + gpiod_set_value(data->sck, 1); ndelay(SHT15_TSCKH); - gpio_set_value(data->pdata->gpio_sck, 0); + gpiod_set_value(data->sck, 0); ndelay(SHT15_TSCKL); /* clock low time */ } @@ -248,23 +249,23 @@ static int sht15_transmission_start(struct sht15_data *data) int err; /* ensure data is high and output */ - err = gpio_direction_output(data->pdata->gpio_data, 1); + err = gpiod_direction_output(data->data, 1); if (err) return err; ndelay(SHT15_TSU); - gpio_set_value(data->pdata->gpio_sck, 0); + gpiod_set_value(data->sck, 0); ndelay(SHT15_TSCKL); - gpio_set_value(data->pdata->gpio_sck, 1); + gpiod_set_value(data->sck, 1); ndelay(SHT15_TSCKH); - gpio_set_value(data->pdata->gpio_data, 0); + gpiod_set_value(data->data, 0); ndelay(SHT15_TSU); - gpio_set_value(data->pdata->gpio_sck, 0); + gpiod_set_value(data->sck, 0); ndelay(SHT15_TSCKL); - gpio_set_value(data->pdata->gpio_sck, 1); + gpiod_set_value(data->sck, 1); ndelay(SHT15_TSCKH); - gpio_set_value(data->pdata->gpio_data, 1); + gpiod_set_value(data->data, 1); ndelay(SHT15_TSU); - gpio_set_value(data->pdata->gpio_sck, 0); + gpiod_set_value(data->sck, 0); ndelay(SHT15_TSCKL); return 0; } @@ -292,20 +293,20 @@ static int sht15_wait_for_response(struct sht15_data *data) { int err; - err = gpio_direction_input(data->pdata->gpio_data); + err = gpiod_direction_input(data->data); if (err) return err; - gpio_set_value(data->pdata->gpio_sck, 1); + gpiod_set_value(data->sck, 1); ndelay(SHT15_TSCKH); - if (gpio_get_value(data->pdata->gpio_data)) { - gpio_set_value(data->pdata->gpio_sck, 0); + if (gpiod_get_value(data->data)) { + gpiod_set_value(data->sck, 0); dev_err(data->dev, "Command not acknowledged\n"); err = sht15_connection_reset(data); if (err) return err; return -EIO; } - gpio_set_value(data->pdata->gpio_sck, 0); + gpiod_set_value(data->sck, 0); ndelay(SHT15_TSCKL); return 0; } @@ -360,17 +361,17 @@ static int sht15_ack(struct sht15_data *data) { int err; - err = gpio_direction_output(data->pdata->gpio_data, 0); + err = gpiod_direction_output(data->data, 0); if (err) return err; ndelay(SHT15_TSU); - gpio_set_value(data->pdata->gpio_sck, 1); + gpiod_set_value(data->sck, 1); ndelay(SHT15_TSU); - gpio_set_value(data->pdata->gpio_sck, 0); + gpiod_set_value(data->sck, 0); ndelay(SHT15_TSU); - gpio_set_value(data->pdata->gpio_data, 1); + gpiod_set_value(data->data, 1); - return gpio_direction_input(data->pdata->gpio_data); + return gpiod_direction_input(data->data); } /** @@ -383,13 +384,13 @@ static int sht15_end_transmission(struct sht15_data *data) { int err; - err = gpio_direction_output(data->pdata->gpio_data, 1); + err = gpiod_direction_output(data->data, 1); if (err) return err; ndelay(SHT15_TSU); - gpio_set_value(data->pdata->gpio_sck, 1); + gpiod_set_value(data->sck, 1); ndelay(SHT15_TSCKH); - gpio_set_value(data->pdata->gpio_sck, 0); + gpiod_set_value(data->sck, 0); ndelay(SHT15_TSCKL); return 0; } @@ -405,10 +406,10 @@ static u8 sht15_read_byte(struct sht15_data *data) for (i = 0; i < 8; ++i) { byte <<= 1; - gpio_set_value(data->pdata->gpio_sck, 1); + gpiod_set_value(data->sck, 1); ndelay(SHT15_TSCKH); - byte |= !!gpio_get_value(data->pdata->gpio_data); - gpio_set_value(data->pdata->gpio_sck, 0); + byte |= !!gpiod_get_value(data->data); + gpiod_set_value(data->sck, 0); ndelay(SHT15_TSCKL); } return byte; @@ -428,7 +429,7 @@ static int sht15_send_status(struct sht15_data *data, u8 status) err = sht15_send_cmd(data, SHT15_WRITE_STATUS); if (err) return err; - err = gpio_direction_output(data->pdata->gpio_data, 1); + err = gpiod_direction_output(data->data, 1); if (err) return err; ndelay(SHT15_TSU); @@ -528,14 +529,14 @@ static int sht15_measurement(struct sht15_data *data, if (ret) return ret; - ret = gpio_direction_input(data->pdata->gpio_data); + ret = gpiod_direction_input(data->data); if (ret) return ret; atomic_set(&data->interrupt_handled, 0); - enable_irq(gpio_to_irq(data->pdata->gpio_data)); - if (gpio_get_value(data->pdata->gpio_data) == 0) { - disable_irq_nosync(gpio_to_irq(data->pdata->gpio_data)); + enable_irq(gpiod_to_irq(data->data)); + if (gpiod_get_value(data->data) == 0) { + disable_irq_nosync(gpiod_to_irq(data->data)); /* Only relevant if the interrupt hasn't occurred. */ if (!atomic_read(&data->interrupt_handled)) schedule_work(&data->read_work); @@ -547,7 +548,7 @@ static int sht15_measurement(struct sht15_data *data, data->state = SHT15_READING_NOTHING; return -EIO; } else if (ret == 0) { /* timeout occurred */ - disable_irq_nosync(gpio_to_irq(data->pdata->gpio_data)); + disable_irq_nosync(gpiod_to_irq(data->data)); ret = sht15_connection_reset(data); if (ret) return ret; @@ -826,15 +827,15 @@ static void sht15_bh_read_data(struct work_struct *work_s) read_work); /* Firstly, verify the line is low */ - if (gpio_get_value(data->pdata->gpio_data)) { + if (gpiod_get_value(data->data)) { /* * If not, then start the interrupt again - care here as could * have gone low in meantime so verify it hasn't! */ atomic_set(&data->interrupt_handled, 0); - enable_irq(gpio_to_irq(data->pdata->gpio_data)); + enable_irq(gpiod_to_irq(data->data)); /* If still not occurred or another handler was scheduled */ - if (gpio_get_value(data->pdata->gpio_data) + if (gpiod_get_value(data->data) || atomic_read(&data->interrupt_handled)) return; } @@ -918,46 +919,6 @@ static const struct of_device_id sht15_dt_match[] = { { }, }; MODULE_DEVICE_TABLE(of, sht15_dt_match); - -/* - * This function returns NULL if pdev isn't a device instatiated by dt, - * a pointer to pdata if it could successfully get all information - * from dt or a negative ERR_PTR() on error. - */ -static struct sht15_platform_data *sht15_probe_dt(struct device *dev) -{ - struct device_node *np = dev->of_node; - struct sht15_platform_data *pdata; - - /* no device tree device */ - if (!np) - return NULL; - - pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); - if (!pdata) - return ERR_PTR(-ENOMEM); - - pdata->gpio_data = of_get_named_gpio(np, "data-gpios", 0); - if (pdata->gpio_data < 0) { - if (pdata->gpio_data != -EPROBE_DEFER) - dev_err(dev, "data-gpios not found\n"); - return ERR_PTR(pdata->gpio_data); - } - - pdata->gpio_sck = of_get_named_gpio(np, "clk-gpios", 0); - if (pdata->gpio_sck < 0) { - if (pdata->gpio_sck != -EPROBE_DEFER) - dev_err(dev, "clk-gpios not found\n"); - return ERR_PTR(pdata->gpio_sck); - } - - return pdata; -} -#else -static inline struct sht15_platform_data *sht15_probe_dt(struct device *dev) -{ - return NULL; -} #endif static int sht15_probe(struct platform_device *pdev) @@ -977,25 +938,6 @@ static int sht15_probe(struct platform_device *pdev) data->dev = &pdev->dev; init_waitqueue_head(&data->wait_queue); - data->pdata = sht15_probe_dt(&pdev->dev); - if (IS_ERR(data->pdata)) - return PTR_ERR(data->pdata); - if (data->pdata == NULL) { - data->pdata = dev_get_platdata(&pdev->dev); - if (data->pdata == NULL) { - dev_err(&pdev->dev, "no platform data supplied\n"); - return -EINVAL; - } - } - - data->supply_uv = data->pdata->supply_mv * 1000; - if (data->pdata->checksum) - data->checksumming = true; - if (data->pdata->no_otp_reload) - status |= SHT15_STATUS_NO_OTP_RELOAD; - if (data->pdata->low_resolution) - status |= SHT15_STATUS_LOW_RESOLUTION; - /* * If a regulator is available, * query what the supply voltage actually is! @@ -1030,21 +972,20 @@ static int sht15_probe(struct platform_device *pdev) } /* Try requesting the GPIOs */ - ret = devm_gpio_request_one(&pdev->dev, data->pdata->gpio_sck, - GPIOF_OUT_INIT_LOW, "SHT15 sck"); - if (ret) { + data->sck = devm_gpiod_get(&pdev->dev, "clk", GPIOD_OUT_LOW); + if (IS_ERR(data->sck)) { + ret = PTR_ERR(data->sck); dev_err(&pdev->dev, "clock line GPIO request failed\n"); goto err_release_reg; } - - ret = devm_gpio_request(&pdev->dev, data->pdata->gpio_data, - "SHT15 data"); - if (ret) { + data->data = devm_gpiod_get(&pdev->dev, "data", GPIOD_IN); + if (IS_ERR(data->data)) { + ret = PTR_ERR(data->data); dev_err(&pdev->dev, "data line GPIO request failed\n"); goto err_release_reg; } - ret = devm_request_irq(&pdev->dev, gpio_to_irq(data->pdata->gpio_data), + ret = devm_request_irq(&pdev->dev, gpiod_to_irq(data->data), sht15_interrupt_fired, IRQF_TRIGGER_FALLING, "sht15 data", @@ -1053,7 +994,7 @@ static int sht15_probe(struct platform_device *pdev) dev_err(&pdev->dev, "failed to get irq for data line\n"); goto err_release_reg; } - disable_irq_nosync(gpio_to_irq(data->pdata->gpio_data)); + disable_irq_nosync(gpiod_to_irq(data->data)); ret = sht15_connection_reset(data); if (ret) goto err_release_reg; diff --git a/include/linux/platform_data/sht15.h b/include/linux/platform_data/sht15.h deleted file mode 100644 index 12289c1e9413..000000000000 --- a/include/linux/platform_data/sht15.h +++ /dev/null @@ -1,38 +0,0 @@ -/* - * sht15.h - support for the SHT15 Temperature and Humidity Sensor - * - * Copyright (c) 2009 Jonathan Cameron - * - * Copyright (c) 2007 Wouter Horre - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * For further information, see the Documentation/hwmon/sht15 file. - */ - -#ifndef _PDATA_SHT15_H -#define _PDATA_SHT15_H - -/** - * struct sht15_platform_data - sht15 connectivity info - * @gpio_data: no. of gpio to which bidirectional data line is - * connected. - * @gpio_sck: no. of gpio to which the data clock is connected. - * @supply_mv: supply voltage in mv. Overridden by regulator if - * available. - * @checksum: flag to indicate the checksum should be validated. - * @no_otp_reload: flag to indicate no reload from OTP. - * @low_resolution: flag to indicate the temp/humidity resolution to use. - */ -struct sht15_platform_data { - int gpio_data; - int gpio_sck; - int supply_mv; - bool checksum; - bool no_otp_reload; - bool low_resolution; -}; - -#endif /* _PDATA_SHT15_H */ -- cgit v1.2.3 From ef7a612415958de1f9afd86235d38b14975d0b7c Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 26 Sep 2017 01:09:05 +0200 Subject: hwmon: (gpio-fan) Localize platform data There is not a single user of the platform data header in . We can conclude that all current users are probing from the device tree, so start simplifying the code by pulling the header into the driver. Convert "unsigned" to "unsigned int" in the process to make checkpatch happy. Signed-off-by: Linus Walleij Signed-off-by: Guenter Roeck --- drivers/hwmon/gpio-fan.c | 23 ++++++++++++++++++++++- include/linux/gpio-fan.h | 36 ------------------------------------ 2 files changed, 22 insertions(+), 37 deletions(-) delete mode 100644 include/linux/gpio-fan.h (limited to 'include/linux') diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c index f29cee9398ef..cfa8d9b578dd 100644 --- a/drivers/hwmon/gpio-fan.c +++ b/drivers/hwmon/gpio-fan.c @@ -30,12 +30,33 @@ #include #include #include -#include #include #include #include #include +struct gpio_fan_alarm { + unsigned int gpio; + unsigned int active_low; +}; + +struct gpio_fan_speed { + int rpm; + int ctrl_val; +}; + +struct gpio_fan_platform_data { + int num_ctrl; + unsigned int *ctrl; /* fan control GPIOs. */ + struct gpio_fan_alarm *alarm; /* fan alarm GPIO. */ + /* + * Speed conversion array: rpm from/to GPIO bit field. + * This array _must_ be sorted in ascending rpm order. + */ + int num_speed; + struct gpio_fan_speed *speed; +}; + struct gpio_fan_data { struct platform_device *pdev; struct device *hwmon_dev; diff --git a/include/linux/gpio-fan.h b/include/linux/gpio-fan.h deleted file mode 100644 index 096659169215..000000000000 --- a/include/linux/gpio-fan.h +++ /dev/null @@ -1,36 +0,0 @@ -/* - * include/linux/gpio-fan.h - * - * Platform data structure for GPIO fan driver - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. - */ - -#ifndef __LINUX_GPIO_FAN_H -#define __LINUX_GPIO_FAN_H - -struct gpio_fan_alarm { - unsigned gpio; - unsigned active_low; -}; - -struct gpio_fan_speed { - int rpm; - int ctrl_val; -}; - -struct gpio_fan_platform_data { - int num_ctrl; - unsigned *ctrl; /* fan control GPIOs. */ - struct gpio_fan_alarm *alarm; /* fan alarm GPIO. */ - /* - * Speed conversion array: rpm from/to GPIO bit field. - * This array _must_ be sorted in ascending rpm order. - */ - int num_speed; - struct gpio_fan_speed *speed; -}; - -#endif /* __LINUX_GPIO_FAN_H */ -- cgit v1.2.3 From 15670bfe19905b1dcbb63137f40d718b59d84479 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Sat, 28 Oct 2017 09:30:38 +0800 Subject: x86/mm/64: Rename the register_page_bootmem_memmap() 'size' parameter to 'nr_pages' register_page_bootmem_memmap()'s 3rd 'size' parameter is named in a somewhat misleading fashion - rename it to 'nr_pages' which makes the units of it much clearer. Meanwhile rename the existing local variable 'nr_pages' to 'nr_pmd_pages', a more expressive name, to avoid conflict with new function parameter 'nr_pages'. (Also clean up the unnecessary parentheses in which get_order() is called.) Signed-off-by: Baoquan He Acked-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Cc: akpm@linux-foundation.org Link: http://lkml.kernel.org/r/1509154238-23250-1-git-send-email-bhe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/mm/init_64.c | 10 +++++----- include/linux/mm.h | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 048fbe8fc274..adcea90a2046 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1426,16 +1426,16 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE) void register_page_bootmem_memmap(unsigned long section_nr, - struct page *start_page, unsigned long size) + struct page *start_page, unsigned long nr_pages) { unsigned long addr = (unsigned long)start_page; - unsigned long end = (unsigned long)(start_page + size); + unsigned long end = (unsigned long)(start_page + nr_pages); unsigned long next; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; - unsigned int nr_pages; + unsigned int nr_pmd_pages; struct page *page; for (; addr < end; addr = next) { @@ -1482,9 +1482,9 @@ void register_page_bootmem_memmap(unsigned long section_nr, if (pmd_none(*pmd)) continue; - nr_pages = 1 << (get_order(PMD_SIZE)); + nr_pmd_pages = 1 << get_order(PMD_SIZE); page = pmd_page(*pmd); - while (nr_pages--) + while (nr_pmd_pages--) get_page_bootmem(section_nr, page++, SECTION_INFO); } diff --git a/include/linux/mm.h b/include/linux/mm.h index 065d99deb847..b2c7045e9604 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2495,7 +2495,7 @@ void vmemmap_populate_print_last(void); void vmemmap_free(unsigned long start, unsigned long end); #endif void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, - unsigned long size); + unsigned long nr_pages); enum mf_flags { MF_COUNT_INCREASED = 1 << 0, -- cgit v1.2.3 From 79ea73b05aaa83b7451a3aee48a5e835fb0f3864 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 15 Sep 2017 20:13:28 +0200 Subject: mmc: sdhci-pci: remove outdated declaration The function was removed half a year ago, so this declaration can go, too. Fixes: 51ced59cc02e0d ("mmc: sdhci-pci: Use ACPI DSM to get driver strength for some Intel devices") Signed-off-by: Wolfram Sang Acked-by: Adrian Hunter Signed-off-by: Ulf Hansson --- include/linux/mmc/sdhci-pci-data.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sdhci-pci-data.h b/include/linux/mmc/sdhci-pci-data.h index fda15b6d4135..618f90d6e1ba 100644 --- a/include/linux/mmc/sdhci-pci-data.h +++ b/include/linux/mmc/sdhci-pci-data.h @@ -14,7 +14,4 @@ struct sdhci_pci_data { extern struct sdhci_pci_data *(*sdhci_pci_get_data)(struct pci_dev *pdev, int slotno); - -extern int sdhci_pci_spt_drive_strength; - #endif -- cgit v1.2.3 From 6c0cedd1ef9527ef13e66875746570e76a3188a7 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 22 Sep 2017 15:36:51 +0300 Subject: mmc: core: Introduce host claiming by context Currently the host can be claimed by a task. Change this so that the host can be claimed by a context that may or may not be a task. This provides for the host to be claimed by a block driver queue to support blk-mq, while maintaining compatibility with the existing use of mmc_claim_host(). Signed-off-by: Adrian Hunter Signed-off-by: Ulf Hansson --- drivers/mmc/core/block.c | 4 ++-- drivers/mmc/core/core.c | 48 ++++++++++++++++++++++++++++++++++++++------- drivers/mmc/core/core.h | 9 +++++---- drivers/mmc/core/mmc.c | 4 ++-- drivers/mmc/core/sd.c | 4 ++-- drivers/mmc/core/sdio_irq.c | 3 ++- include/linux/mmc/host.h | 7 ++++++- 7 files changed, 60 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index f11537a66a60..9476312f081a 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1989,7 +1989,7 @@ void mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req) if (req && !mq->qcnt) /* claim host only for the first request */ - mmc_get_card(card); + mmc_get_card(card, NULL); ret = mmc_blk_part_switch(card, md->part_type); if (ret) { @@ -2052,7 +2052,7 @@ void mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req) out: if (!mq->qcnt) - mmc_put_card(card); + mmc_put_card(card, NULL); } static inline int mmc_blk_readonly(struct mmc_card *card) diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 66c9cf49ad2f..b997cf92ce6c 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -832,9 +832,36 @@ unsigned int mmc_align_data_size(struct mmc_card *card, unsigned int sz) } EXPORT_SYMBOL(mmc_align_data_size); +/* + * Allow claiming an already claimed host if the context is the same or there is + * no context but the task is the same. + */ +static inline bool mmc_ctx_matches(struct mmc_host *host, struct mmc_ctx *ctx, + struct task_struct *task) +{ + return host->claimer == ctx || + (!ctx && task && host->claimer->task == task); +} + +static inline void mmc_ctx_set_claimer(struct mmc_host *host, + struct mmc_ctx *ctx, + struct task_struct *task) +{ + if (!host->claimer) { + if (ctx) + host->claimer = ctx; + else + host->claimer = &host->default_ctx; + } + if (task) + host->claimer->task = task; +} + /** * __mmc_claim_host - exclusively claim a host * @host: mmc host to claim + * @ctx: context that claims the host or NULL in which case the default + * context will be used * @abort: whether or not the operation should be aborted * * Claim a host for a set of operations. If @abort is non null and @@ -842,8 +869,10 @@ EXPORT_SYMBOL(mmc_align_data_size); * that non-zero value without acquiring the lock. Returns zero * with the lock held otherwise. */ -int __mmc_claim_host(struct mmc_host *host, atomic_t *abort) +int __mmc_claim_host(struct mmc_host *host, struct mmc_ctx *ctx, + atomic_t *abort) { + struct task_struct *task = ctx ? NULL : current; DECLARE_WAITQUEUE(wait, current); unsigned long flags; int stop; @@ -856,7 +885,7 @@ int __mmc_claim_host(struct mmc_host *host, atomic_t *abort) while (1) { set_current_state(TASK_UNINTERRUPTIBLE); stop = abort ? atomic_read(abort) : 0; - if (stop || !host->claimed || host->claimer == current) + if (stop || !host->claimed || mmc_ctx_matches(host, ctx, task)) break; spin_unlock_irqrestore(&host->lock, flags); schedule(); @@ -865,7 +894,7 @@ int __mmc_claim_host(struct mmc_host *host, atomic_t *abort) set_current_state(TASK_RUNNING); if (!stop) { host->claimed = 1; - host->claimer = current; + mmc_ctx_set_claimer(host, ctx, task); host->claim_cnt += 1; if (host->claim_cnt == 1) pm = true; @@ -900,6 +929,7 @@ void mmc_release_host(struct mmc_host *host) spin_unlock_irqrestore(&host->lock, flags); } else { host->claimed = 0; + host->claimer->task = NULL; host->claimer = NULL; spin_unlock_irqrestore(&host->lock, flags); wake_up(&host->wq); @@ -913,10 +943,10 @@ EXPORT_SYMBOL(mmc_release_host); * This is a helper function, which fetches a runtime pm reference for the * card device and also claims the host. */ -void mmc_get_card(struct mmc_card *card) +void mmc_get_card(struct mmc_card *card, struct mmc_ctx *ctx) { pm_runtime_get_sync(&card->dev); - mmc_claim_host(card->host); + __mmc_claim_host(card->host, ctx, NULL); } EXPORT_SYMBOL(mmc_get_card); @@ -924,9 +954,13 @@ EXPORT_SYMBOL(mmc_get_card); * This is a helper function, which releases the host and drops the runtime * pm reference for the card device. */ -void mmc_put_card(struct mmc_card *card) +void mmc_put_card(struct mmc_card *card, struct mmc_ctx *ctx) { - mmc_release_host(card->host); + struct mmc_host *host = card->host; + + WARN_ON(ctx && host->claimer != ctx); + + mmc_release_host(host); pm_runtime_mark_last_busy(&card->dev); pm_runtime_put_autosuspend(&card->dev); } diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h index ca861091a776..94675f88f704 100644 --- a/drivers/mmc/core/core.h +++ b/drivers/mmc/core/core.h @@ -128,10 +128,11 @@ int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen); int mmc_set_blockcount(struct mmc_card *card, unsigned int blockcount, bool is_rel_write); -int __mmc_claim_host(struct mmc_host *host, atomic_t *abort); +int __mmc_claim_host(struct mmc_host *host, struct mmc_ctx *ctx, + atomic_t *abort); void mmc_release_host(struct mmc_host *host); -void mmc_get_card(struct mmc_card *card); -void mmc_put_card(struct mmc_card *card); +void mmc_get_card(struct mmc_card *card, struct mmc_ctx *ctx); +void mmc_put_card(struct mmc_card *card, struct mmc_ctx *ctx); /** * mmc_claim_host - exclusively claim a host @@ -141,7 +142,7 @@ void mmc_put_card(struct mmc_card *card); */ static inline void mmc_claim_host(struct mmc_host *host) { - __mmc_claim_host(host, NULL); + __mmc_claim_host(host, NULL, NULL); } #endif diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 36217ad5e9b1..8d77ddc85af1 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1911,14 +1911,14 @@ static void mmc_detect(struct mmc_host *host) { int err; - mmc_get_card(host->card); + mmc_get_card(host->card, NULL); /* * Just check if our card has been removed. */ err = _mmc_detect_card_removed(host); - mmc_put_card(host->card); + mmc_put_card(host->card, NULL); if (err) { mmc_remove(host); diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index 4fd1620b732d..2036b2b4835c 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -1056,14 +1056,14 @@ static void mmc_sd_detect(struct mmc_host *host) { int err; - mmc_get_card(host->card); + mmc_get_card(host->card, NULL); /* * Just check if our card has been removed. */ err = _mmc_detect_card_removed(host); - mmc_put_card(host->card); + mmc_put_card(host->card, NULL); if (err) { mmc_sd_remove(host); diff --git a/drivers/mmc/core/sdio_irq.c b/drivers/mmc/core/sdio_irq.c index c771843e4c15..7a2eaf8410a3 100644 --- a/drivers/mmc/core/sdio_irq.c +++ b/drivers/mmc/core/sdio_irq.c @@ -155,7 +155,8 @@ static int sdio_irq_thread(void *_host) * holding of the host lock does not cover too much work * that doesn't require that lock to be held. */ - ret = __mmc_claim_host(host, &host->sdio_irq_thread_abort); + ret = __mmc_claim_host(host, NULL, + &host->sdio_irq_thread_abort); if (ret) break; ret = process_sdio_pending_irqs(host); diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 9a43763a68ad..443f7a8cdfe5 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -255,6 +255,10 @@ struct mmc_supply { struct regulator *vqmmc; /* Optional Vccq supply */ }; +struct mmc_ctx { + struct task_struct *task; +}; + struct mmc_host { struct device *parent; struct device class_dev; @@ -388,8 +392,9 @@ struct mmc_host { struct mmc_card *card; /* device attached to this host */ wait_queue_head_t wq; - struct task_struct *claimer; /* task that has host claimed */ + struct mmc_ctx *claimer; /* context that has host claimed */ int claim_cnt; /* "claim" nesting count */ + struct mmc_ctx default_ctx; /* default context */ struct delayed_work detect; int detect_change; /* card detect flag */ -- cgit v1.2.3 From 72a5af554df837e373efb0d6c8fc68c568f9a7ac Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 22 Sep 2017 15:36:52 +0300 Subject: mmc: core: Add support for handling CQE requests Add core support for handling CQE requests, including starting, completing and recovering. Signed-off-by: Adrian Hunter Reviewed-by: Linus Walleij Signed-off-by: Ulf Hansson --- drivers/mmc/core/core.c | 163 +++++++++++++++++++++++++++++++++++++++++++++-- drivers/mmc/core/core.h | 4 ++ include/linux/mmc/host.h | 2 + 3 files changed, 164 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index b997cf92ce6c..2ff614d4ffac 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -266,7 +266,8 @@ static void __mmc_start_request(struct mmc_host *host, struct mmc_request *mrq) host->ops->request(host, mrq); } -static void mmc_mrq_pr_debug(struct mmc_host *host, struct mmc_request *mrq) +static void mmc_mrq_pr_debug(struct mmc_host *host, struct mmc_request *mrq, + bool cqe) { if (mrq->sbc) { pr_debug("<%s: starting CMD%u arg %08x flags %08x>\n", @@ -275,9 +276,12 @@ static void mmc_mrq_pr_debug(struct mmc_host *host, struct mmc_request *mrq) } if (mrq->cmd) { - pr_debug("%s: starting CMD%u arg %08x flags %08x\n", - mmc_hostname(host), mrq->cmd->opcode, mrq->cmd->arg, - mrq->cmd->flags); + pr_debug("%s: starting %sCMD%u arg %08x flags %08x\n", + mmc_hostname(host), cqe ? "CQE direct " : "", + mrq->cmd->opcode, mrq->cmd->arg, mrq->cmd->flags); + } else if (cqe) { + pr_debug("%s: starting CQE transfer for tag %d blkaddr %u\n", + mmc_hostname(host), mrq->tag, mrq->data->blk_addr); } if (mrq->data) { @@ -342,7 +346,7 @@ static int mmc_start_request(struct mmc_host *host, struct mmc_request *mrq) if (mmc_card_removed(host->card)) return -ENOMEDIUM; - mmc_mrq_pr_debug(host, mrq); + mmc_mrq_pr_debug(host, mrq, false); WARN_ON(!host->claimed); @@ -482,6 +486,155 @@ void mmc_wait_for_req_done(struct mmc_host *host, struct mmc_request *mrq) } EXPORT_SYMBOL(mmc_wait_for_req_done); +/* + * mmc_cqe_start_req - Start a CQE request. + * @host: MMC host to start the request + * @mrq: request to start + * + * Start the request, re-tuning if needed and it is possible. Returns an error + * code if the request fails to start or -EBUSY if CQE is busy. + */ +int mmc_cqe_start_req(struct mmc_host *host, struct mmc_request *mrq) +{ + int err; + + /* + * CQE cannot process re-tuning commands. Caller must hold retuning + * while CQE is in use. Re-tuning can happen here only when CQE has no + * active requests i.e. this is the first. Note, re-tuning will call + * ->cqe_off(). + */ + err = mmc_retune(host); + if (err) + goto out_err; + + mrq->host = host; + + mmc_mrq_pr_debug(host, mrq, true); + + err = mmc_mrq_prep(host, mrq); + if (err) + goto out_err; + + err = host->cqe_ops->cqe_request(host, mrq); + if (err) + goto out_err; + + trace_mmc_request_start(host, mrq); + + return 0; + +out_err: + if (mrq->cmd) { + pr_debug("%s: failed to start CQE direct CMD%u, error %d\n", + mmc_hostname(host), mrq->cmd->opcode, err); + } else { + pr_debug("%s: failed to start CQE transfer for tag %d, error %d\n", + mmc_hostname(host), mrq->tag, err); + } + return err; +} +EXPORT_SYMBOL(mmc_cqe_start_req); + +/** + * mmc_cqe_request_done - CQE has finished processing an MMC request + * @host: MMC host which completed request + * @mrq: MMC request which completed + * + * CQE drivers should call this function when they have completed + * their processing of a request. + */ +void mmc_cqe_request_done(struct mmc_host *host, struct mmc_request *mrq) +{ + mmc_should_fail_request(host, mrq); + + /* Flag re-tuning needed on CRC errors */ + if ((mrq->cmd && mrq->cmd->error == -EILSEQ) || + (mrq->data && mrq->data->error == -EILSEQ)) + mmc_retune_needed(host); + + trace_mmc_request_done(host, mrq); + + if (mrq->cmd) { + pr_debug("%s: CQE req done (direct CMD%u): %d\n", + mmc_hostname(host), mrq->cmd->opcode, mrq->cmd->error); + } else { + pr_debug("%s: CQE transfer done tag %d\n", + mmc_hostname(host), mrq->tag); + } + + if (mrq->data) { + pr_debug("%s: %d bytes transferred: %d\n", + mmc_hostname(host), + mrq->data->bytes_xfered, mrq->data->error); + } + + mrq->done(mrq); +} +EXPORT_SYMBOL(mmc_cqe_request_done); + +/** + * mmc_cqe_post_req - CQE post process of a completed MMC request + * @host: MMC host + * @mrq: MMC request to be processed + */ +void mmc_cqe_post_req(struct mmc_host *host, struct mmc_request *mrq) +{ + if (host->cqe_ops->cqe_post_req) + host->cqe_ops->cqe_post_req(host, mrq); +} +EXPORT_SYMBOL(mmc_cqe_post_req); + +/* Arbitrary 1 second timeout */ +#define MMC_CQE_RECOVERY_TIMEOUT 1000 + +/* + * mmc_cqe_recovery - Recover from CQE errors. + * @host: MMC host to recover + * + * Recovery consists of stopping CQE, stopping eMMC, discarding the queue in + * in eMMC, and discarding the queue in CQE. CQE must call + * mmc_cqe_request_done() on all requests. An error is returned if the eMMC + * fails to discard its queue. + */ +int mmc_cqe_recovery(struct mmc_host *host) +{ + struct mmc_command cmd; + int err; + + mmc_retune_hold_now(host); + + /* + * Recovery is expected seldom, if at all, but it reduces performance, + * so make sure it is not completely silent. + */ + pr_warn("%s: running CQE recovery\n", mmc_hostname(host)); + + host->cqe_ops->cqe_recovery_start(host); + + memset(&cmd, 0, sizeof(cmd)); + cmd.opcode = MMC_STOP_TRANSMISSION, + cmd.flags = MMC_RSP_R1B | MMC_CMD_AC, + cmd.flags &= ~MMC_RSP_CRC; /* Ignore CRC */ + cmd.busy_timeout = MMC_CQE_RECOVERY_TIMEOUT, + mmc_wait_for_cmd(host, &cmd, 0); + + memset(&cmd, 0, sizeof(cmd)); + cmd.opcode = MMC_CMDQ_TASK_MGMT; + cmd.arg = 1; /* Discard entire queue */ + cmd.flags = MMC_RSP_R1B | MMC_CMD_AC; + cmd.flags &= ~MMC_RSP_CRC; /* Ignore CRC */ + cmd.busy_timeout = MMC_CQE_RECOVERY_TIMEOUT, + err = mmc_wait_for_cmd(host, &cmd, 0); + + host->cqe_ops->cqe_recovery_finish(host); + + mmc_retune_release(host); + + return err; +} +EXPORT_SYMBOL(mmc_cqe_recovery); + /** * mmc_is_req_done - Determine if a 'cap_cmd_during_tfr' request is done * @host: MMC host diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h index 94675f88f704..ba5a8fea0dc2 100644 --- a/drivers/mmc/core/core.h +++ b/drivers/mmc/core/core.h @@ -145,4 +145,8 @@ static inline void mmc_claim_host(struct mmc_host *host) __mmc_claim_host(host, NULL, NULL); } +int mmc_cqe_start_req(struct mmc_host *host, struct mmc_request *mrq); +void mmc_cqe_post_req(struct mmc_host *host, struct mmc_request *mrq); +int mmc_cqe_recovery(struct mmc_host *host); + #endif diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 443f7a8cdfe5..c296f4351c1d 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -474,6 +474,8 @@ void mmc_detect_change(struct mmc_host *, unsigned long delay); void mmc_request_done(struct mmc_host *, struct mmc_request *); void mmc_command_done(struct mmc_host *host, struct mmc_request *mrq); +void mmc_cqe_request_done(struct mmc_host *host, struct mmc_request *mrq); + static inline void mmc_signal_sdio_irq(struct mmc_host *host) { host->ops->enable_sdio_irq(host, 0); -- cgit v1.2.3 From 563be8b60324f8947e9c71ec81a8cb67ea2f2127 Mon Sep 17 00:00:00 2001 From: rui_feng Date: Fri, 22 Sep 2017 16:07:35 +0800 Subject: mmc: rtsx: fix tuning fail on gen3 PCI-Express On gen3 PCI-Express we should send command one by one. If sending many commands in one packet will lead to a failure. Signed-off-by: rui_feng Signed-off-by: Ulf Hansson --- drivers/mmc/host/rtsx_pci_sdmmc.c | 38 ++++++++++++++++++-------------------- include/linux/mfd/rtsx_pci.h | 1 + 2 files changed, 19 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c index 41b57713b620..0848dc0f882e 100644 --- a/drivers/mmc/host/rtsx_pci_sdmmc.c +++ b/drivers/mmc/host/rtsx_pci_sdmmc.c @@ -618,29 +618,22 @@ static int sd_change_phase(struct realtek_pci_sdmmc *host, u8 sample_point, bool rx) { struct rtsx_pcr *pcr = host->pcr; - int err; dev_dbg(sdmmc_dev(host), "%s(%s): sample_point = %d\n", __func__, rx ? "RX" : "TX", sample_point); - rtsx_pci_init_cmd(pcr); - - rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_CTL, CHANGE_CLK, CHANGE_CLK); + rtsx_pci_write_register(pcr, CLK_CTL, CHANGE_CLK, CHANGE_CLK); if (rx) - rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, - SD_VPRX_CTL, 0x1F, sample_point); + rtsx_pci_write_register(pcr, SD_VPRX_CTL, + PHASE_SELECT_MASK, sample_point); else - rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, - SD_VPTX_CTL, 0x1F, sample_point); - rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL, PHASE_NOT_RESET, 0); - rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL, - PHASE_NOT_RESET, PHASE_NOT_RESET); - rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_CTL, CHANGE_CLK, 0); - rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_CFG1, SD_ASYNC_FIFO_NOT_RST, 0); - - err = rtsx_pci_send_cmd(pcr, 100); - if (err < 0) - return err; + rtsx_pci_write_register(pcr, SD_VPTX_CTL, + PHASE_SELECT_MASK, sample_point); + rtsx_pci_write_register(pcr, SD_VPCLK0_CTL, PHASE_NOT_RESET, 0); + rtsx_pci_write_register(pcr, SD_VPCLK0_CTL, PHASE_NOT_RESET, + PHASE_NOT_RESET); + rtsx_pci_write_register(pcr, CLK_CTL, CHANGE_CLK, 0); + rtsx_pci_write_register(pcr, SD_CFG1, SD_ASYNC_FIFO_NOT_RST, 0); return 0; } @@ -708,10 +701,12 @@ static int sd_tuning_rx_cmd(struct realtek_pci_sdmmc *host, { int err; struct mmc_command cmd = {}; + struct rtsx_pcr *pcr = host->pcr; - err = sd_change_phase(host, sample_point, true); - if (err < 0) - return err; + sd_change_phase(host, sample_point, true); + + rtsx_pci_write_register(pcr, SD_CFG3, SD_RSP_80CLK_TIMEOUT_EN, + SD_RSP_80CLK_TIMEOUT_EN); cmd.opcode = opcode; err = sd_read_data(host, &cmd, 0x40, NULL, 0, 100); @@ -719,9 +714,12 @@ static int sd_tuning_rx_cmd(struct realtek_pci_sdmmc *host, /* Wait till SD DATA IDLE */ sd_wait_data_idle(host); sd_clear_error(host); + rtsx_pci_write_register(pcr, SD_CFG3, + SD_RSP_80CLK_TIMEOUT_EN, 0); return err; } + rtsx_pci_write_register(pcr, SD_CFG3, SD_RSP_80CLK_TIMEOUT_EN, 0); return 0; } diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index 116816fb9110..7815d8db7eca 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -334,6 +334,7 @@ #define DCM_DRP_RD_DATA_H 0xFC29 #define SD_VPCLK0_CTL 0xFC2A #define SD_VPCLK1_CTL 0xFC2B +#define PHASE_SELECT_MASK 0x1F #define SD_DCMPS0_CTL 0xFC2C #define SD_DCMPS1_CTL 0xFC2D #define SD_VPTX_CTL SD_VPCLK0_CTL -- cgit v1.2.3 From 6186d06c519e217351fac95b545f334f8582af90 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sun, 15 Oct 2017 14:46:14 +0200 Subject: mmc: parse new binding for eMMC fixed driver type Parse the new binding and store it in the host struct after doing some sanity checks. The code is designed to support fixed SD driver type if we ever need that. Signed-off-by: Wolfram Sang Reviewed-by: Simon Horman Signed-off-by: Ulf Hansson --- drivers/mmc/core/host.c | 13 ++++++++++++- drivers/mmc/core/mmc.c | 11 ++++++++--- include/linux/mmc/host.h | 2 ++ 3 files changed, 22 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index e58be39b1568..35a9e4fd1a9f 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -179,7 +179,7 @@ static void mmc_retune_timer(unsigned long data) int mmc_of_parse(struct mmc_host *host) { struct device *dev = host->parent; - u32 bus_width; + u32 bus_width, drv_type; int ret; bool cd_cap_invert, cd_gpio_invert = false; bool ro_cap_invert, ro_gpio_invert = false; @@ -321,6 +321,15 @@ int mmc_of_parse(struct mmc_host *host) if (device_property_read_bool(dev, "no-mmc")) host->caps2 |= MMC_CAP2_NO_MMC; + /* Must be after "non-removable" check */ + if (device_property_read_u32(dev, "fixed-emmc-driver-type", &drv_type) == 0) { + if (host->caps & MMC_CAP_NONREMOVABLE) + host->fixed_drv_type = drv_type; + else + dev_err(host->parent, + "can't use fixed driver type, media is removable\n"); + } + host->dsr_req = !device_property_read_u32(dev, "dsr", &host->dsr); if (host->dsr_req && (host->dsr & ~0xffff)) { dev_err(host->parent, @@ -393,6 +402,8 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) host->max_blk_size = 512; host->max_blk_count = PAGE_SIZE / 512; + host->fixed_drv_type = -EINVAL; + return host; } diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 066efbb89483..a552f61060d2 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1291,13 +1291,18 @@ out_err: static void mmc_select_driver_type(struct mmc_card *card) { int card_drv_type, drive_strength, drv_type; + int fixed_drv_type = card->host->fixed_drv_type; card_drv_type = card->ext_csd.raw_driver_strength | mmc_driver_type_mask(0); - drive_strength = mmc_select_drive_strength(card, - card->ext_csd.hs200_max_dtr, - card_drv_type, &drv_type); + if (fixed_drv_type >= 0) + drive_strength = card_drv_type & mmc_driver_type_mask(fixed_drv_type) + ? fixed_drv_type : 0; + else + drive_strength = mmc_select_drive_strength(card, + card->ext_csd.hs200_max_dtr, + card_drv_type, &drv_type); card->drive_strength = drive_strength; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index c296f4351c1d..e7743eca1021 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -354,6 +354,8 @@ struct mmc_host { #define MMC_CAP2_CQE (1 << 23) /* Has eMMC command queue engine */ #define MMC_CAP2_CQE_DCMD (1 << 24) /* CQE can issue a direct command */ + int fixed_drv_type; /* fixed driver type for non-removable media */ + mmc_pm_flag_t pm_caps; /* supported pm features */ /* host specific block data */ -- cgit v1.2.3 From 0f295b0650c90362b4111f46d7f9149a0a4191be Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 13 Oct 2017 11:54:33 -0600 Subject: rtc: Allow rtc drivers to specify the tv_nsec value for ntp ntp is currently hardwired to try and call the rtc set when wall clock tv_nsec is 0.5 seconds. This historical behaviour works well with certain PC RTCs, but is not universal to all rtc hardware. Change how this works by introducing the driver specific concept of set_offset_nsec, the delay between current wall clock time and the target time to set (with a 0 tv_nsecs). For x86-style CMOS set_offset_nsec should be -0.5 s which causes the last second to be written 0.5 s after it has started. For compat with the old rtc_set_ntp_time, the value is defaulted to + 0.5 s, which causes the next second to be written 0.5s before it starts, as things were before this patch. Testing shows many non-x86 RTCs would like set_offset_nsec ~= 0, so ultimately each RTC driver should set the set_offset_nsec according to its needs, and non x86 architectures should stop using update_persistent_clock64 in order to access this feature. Future patches will revise the drivers as needed. Since CMOS and RTC now have very different handling they are split into two dedicated code paths, sharing the support code, and ifdefs are replaced with IS_ENABLED. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Miroslav Lichvar Cc: Richard Cochran Cc: Prarit Bhargava Cc: Stephen Boyd Signed-off-by: Jason Gunthorpe Signed-off-by: John Stultz --- drivers/rtc/class.c | 3 + drivers/rtc/systohc.c | 53 +++++++++++----- include/linux/rtc.h | 43 ++++++++++++- kernel/time/ntp.c | 166 ++++++++++++++++++++++++++++++++++---------------- 4 files changed, 196 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 2ed970d61da1..722d683e0b0f 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -161,6 +161,9 @@ static struct rtc_device *rtc_allocate_device(void) device_initialize(&rtc->dev); + /* Drivers can revise this default after allocating the device. */ + rtc->set_offset_nsec = NSEC_PER_SEC / 2; + rtc->irq_freq = 1; rtc->max_user_freq = 64; rtc->dev.class = rtc_class; diff --git a/drivers/rtc/systohc.c b/drivers/rtc/systohc.c index b4a68ffcd06b..0c177647ea6c 100644 --- a/drivers/rtc/systohc.c +++ b/drivers/rtc/systohc.c @@ -10,6 +10,7 @@ /** * rtc_set_ntp_time - Save NTP synchronized time to the RTC * @now: Current time of day + * @target_nsec: pointer for desired now->tv_nsec value * * Replacement for the NTP platform function update_persistent_clock64 * that stores time for later retrieval by rtc_hctosys. @@ -18,30 +19,52 @@ * possible at all, and various other -errno for specific temporary failure * cases. * + * -EPROTO is returned if now.tv_nsec is not close enough to *target_nsec. + ( * If temporary failure is indicated the caller should try again 'soon' */ -int rtc_set_ntp_time(struct timespec64 now) +int rtc_set_ntp_time(struct timespec64 now, unsigned long *target_nsec) { struct rtc_device *rtc; struct rtc_time tm; + struct timespec64 to_set; int err = -ENODEV; - - if (now.tv_nsec < (NSEC_PER_SEC >> 1)) - rtc_time64_to_tm(now.tv_sec, &tm); - else - rtc_time64_to_tm(now.tv_sec + 1, &tm); + bool ok; rtc = rtc_class_open(CONFIG_RTC_SYSTOHC_DEVICE); - if (rtc) { - /* rtc_hctosys exclusively uses UTC, so we call set_time here, - * not set_mmss. */ - if (rtc->ops && - (rtc->ops->set_time || - rtc->ops->set_mmss64 || - rtc->ops->set_mmss)) - err = rtc_set_time(rtc, &tm); - rtc_class_close(rtc); + if (!rtc) + goto out_err; + + if (!rtc->ops || (!rtc->ops->set_time && !rtc->ops->set_mmss64 && + !rtc->ops->set_mmss)) + goto out_close; + + /* Compute the value of tv_nsec we require the caller to supply in + * now.tv_nsec. This is the value such that (now + + * set_offset_nsec).tv_nsec == 0. + */ + set_normalized_timespec64(&to_set, 0, -rtc->set_offset_nsec); + *target_nsec = to_set.tv_nsec; + + /* The ntp code must call this with the correct value in tv_nsec, if + * it does not we update target_nsec and return EPROTO to make the ntp + * code try again later. + */ + ok = rtc_tv_nsec_ok(rtc->set_offset_nsec, &to_set, &now); + if (!ok) { + err = -EPROTO; + goto out_close; } + rtc_time64_to_tm(to_set.tv_sec, &tm); + + /* rtc_hctosys exclusively uses UTC, so we call set_time here, not + * set_mmss. + */ + err = rtc_set_time(rtc, &tm); + +out_close: + rtc_class_close(rtc); +out_err: return err; } diff --git a/include/linux/rtc.h b/include/linux/rtc.h index e6d0f9c1cafd..5b13fa029fd6 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -135,6 +135,14 @@ struct rtc_device { /* Some hardware can't support UIE mode */ int uie_unsupported; + /* Number of nsec it takes to set the RTC clock. This influences when + * the set ops are called. An offset: + * - of 0.5 s will call RTC set for wall clock time 10.0 s at 9.5 s + * - of 1.5 s will call RTC set for wall clock time 10.0 s at 8.5 s + * - of -0.5 s will call RTC set for wall clock time 10.0 s at 10.5 s + */ + long set_offset_nsec; + bool registered; struct nvmem_config *nvmem_config; @@ -172,7 +180,7 @@ extern void devm_rtc_device_unregister(struct device *dev, extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm); extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm); -extern int rtc_set_ntp_time(struct timespec64 now); +extern int rtc_set_ntp_time(struct timespec64 now, unsigned long *target_nsec); int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm); extern int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); @@ -221,6 +229,39 @@ static inline bool is_leap_year(unsigned int year) return (!(year % 4) && (year % 100)) || !(year % 400); } +/* Determine if we can call to driver to set the time. Drivers can only be + * called to set a second aligned time value, and the field set_offset_nsec + * specifies how far away from the second aligned time to call the driver. + * + * This also computes 'to_set' which is the time we are trying to set, and has + * a zero in tv_nsecs, such that: + * to_set - set_delay_nsec == now +/- FUZZ + * + */ +static inline bool rtc_tv_nsec_ok(s64 set_offset_nsec, + struct timespec64 *to_set, + const struct timespec64 *now) +{ + /* Allowed error in tv_nsec, arbitarily set to 5 jiffies in ns. */ + const unsigned long TIME_SET_NSEC_FUZZ = TICK_NSEC * 5; + struct timespec64 delay = {.tv_sec = 0, + .tv_nsec = set_offset_nsec}; + + *to_set = timespec64_add(*now, delay); + + if (to_set->tv_nsec < TIME_SET_NSEC_FUZZ) { + to_set->tv_nsec = 0; + return true; + } + + if (to_set->tv_nsec > NSEC_PER_SEC - TIME_SET_NSEC_FUZZ) { + to_set->tv_sec++; + to_set->tv_nsec = 0; + return true; + } + return false; +} + #define rtc_register_device(device) \ __rtc_register_device(THIS_MODULE, device) diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index edf19cc53140..bc19de1a0683 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -492,6 +492,67 @@ out: return leap; } +static void sync_hw_clock(struct work_struct *work); +static DECLARE_DELAYED_WORK(sync_work, sync_hw_clock); + +static void sched_sync_hw_clock(struct timespec64 now, + unsigned long target_nsec, bool fail) + +{ + struct timespec64 next; + + getnstimeofday64(&next); + if (!fail) + next.tv_sec = 659; + else { + /* + * Try again as soon as possible. Delaying long periods + * decreases the accuracy of the work queue timer. Due to this + * the algorithm is very likely to require a short-sleep retry + * after the above long sleep to synchronize ts_nsec. + */ + next.tv_sec = 0; + } + + /* Compute the needed delay that will get to tv_nsec == target_nsec */ + next.tv_nsec = target_nsec - next.tv_nsec; + if (next.tv_nsec <= 0) + next.tv_nsec += NSEC_PER_SEC; + if (next.tv_nsec >= NSEC_PER_SEC) { + next.tv_sec++; + next.tv_nsec -= NSEC_PER_SEC; + } + + queue_delayed_work(system_power_efficient_wq, &sync_work, + timespec64_to_jiffies(&next)); +} + +static void sync_rtc_clock(void) +{ + unsigned long target_nsec; + struct timespec64 adjust, now; + int rc; + + if (!IS_ENABLED(CONFIG_RTC_SYSTOHC)) + return; + + getnstimeofday64(&now); + + adjust = now; + if (persistent_clock_is_local) + adjust.tv_sec -= (sys_tz.tz_minuteswest * 60); + + /* + * The current RTC in use will provide the target_nsec it wants to be + * called at, and does rtc_tv_nsec_ok internally. + */ + rc = rtc_set_ntp_time(adjust, &target_nsec); + if (rc == -ENODEV) + return; + + sched_sync_hw_clock(now, target_nsec, rc); +} + #ifdef CONFIG_GENERIC_CMOS_UPDATE int __weak update_persistent_clock(struct timespec now) { @@ -507,76 +568,75 @@ int __weak update_persistent_clock64(struct timespec64 now64) } #endif -#if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) -static void sync_cmos_clock(struct work_struct *work); - -static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock); - -static void sync_cmos_clock(struct work_struct *work) +static bool sync_cmos_clock(void) { + static bool no_cmos; struct timespec64 now; - struct timespec64 next; - int fail = 1; + struct timespec64 adjust; + int rc = -EPROTO; + long target_nsec = NSEC_PER_SEC / 2; + + if (!IS_ENABLED(CONFIG_GENERIC_CMOS_UPDATE)) + return false; + + if (no_cmos) + return false; /* - * If we have an externally synchronized Linux clock, then update - * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be - * called as close as possible to 500 ms before the new second starts. - * This code is run on a timer. If the clock is set, that timer - * may not expire at the correct time. Thus, we adjust... - * We want the clock to be within a couple of ticks from the target. + * Historically update_persistent_clock64() has followed x86 + * semantics, which match the MC146818A/etc RTC. This RTC will store + * 'adjust' and then in .5s it will advance once second. + * + * Architectures are strongly encouraged to use rtclib and not + * implement this legacy API. */ - if (!ntp_synced()) { - /* - * Not synced, exit, do not restart a timer (if one is - * running, let it run out). - */ - return; - } - getnstimeofday64(&now); - if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) { - struct timespec64 adjust = now; - - fail = -ENODEV; + if (rtc_tv_nsec_ok(-1 * target_nsec, &adjust, &now)) { if (persistent_clock_is_local) adjust.tv_sec -= (sys_tz.tz_minuteswest * 60); -#ifdef CONFIG_GENERIC_CMOS_UPDATE - fail = update_persistent_clock64(adjust); -#endif - -#ifdef CONFIG_RTC_SYSTOHC - if (fail == -ENODEV) - fail = rtc_set_ntp_time(adjust); -#endif + rc = update_persistent_clock64(adjust); + /* + * The machine does not support update_persistent_clock64 even + * though it defines CONFIG_GENERIC_CMOS_UPDATE. + */ + if (rc == -ENODEV) { + no_cmos = true; + return false; + } } - next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec - (TICK_NSEC / 2); - if (next.tv_nsec <= 0) - next.tv_nsec += NSEC_PER_SEC; + sched_sync_hw_clock(now, target_nsec, rc); + return true; +} - if (!fail || fail == -ENODEV) - next.tv_sec = 659; - else - next.tv_sec = 0; +/* + * If we have an externally synchronized Linux clock, then update RTC clock + * accordingly every ~11 minutes. Generally RTCs can only store second + * precision, but many RTCs will adjust the phase of their second tick to + * match the moment of update. This infrastructure arranges to call to the RTC + * set at the correct moment to phase synchronize the RTC second tick over + * with the kernel clock. + */ +static void sync_hw_clock(struct work_struct *work) +{ + if (!ntp_synced()) + return; - if (next.tv_nsec >= NSEC_PER_SEC) { - next.tv_sec++; - next.tv_nsec -= NSEC_PER_SEC; - } - queue_delayed_work(system_power_efficient_wq, - &sync_cmos_work, timespec64_to_jiffies(&next)); + if (sync_cmos_clock()) + return; + + sync_rtc_clock(); } void ntp_notify_cmos_timer(void) { - queue_delayed_work(system_power_efficient_wq, &sync_cmos_work, 0); -} - -#else -void ntp_notify_cmos_timer(void) { } -#endif + if (!ntp_synced()) + return; + if (IS_ENABLED(CONFIG_GENERIC_CMOS_UPDATE) || + IS_ENABLED(CONFIG_RTC_SYSTOHC)) + queue_delayed_work(system_power_efficient_wq, &sync_work, 0); +} /* * Propagate a new txc->status value into the NTP state: -- cgit v1.2.3 From e0956dcc4ba74ec4b17e32fc9a156fcba1ef6610 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 19 Oct 2017 13:14:44 +0200 Subject: timekeeping: Consolidate timekeeping_inject_offset code The code to check the adjtimex() or clock_adjtime() arguments is spread out across multiple files for presumably only historic reasons. As a preparatation for a rework to get rid of the use of 'struct timeval' and 'struct timespec' in there, this moves all the portions into kernel/time/timekeeping.c and marks them as 'static'. The warp_clock() function here is not as closely related as the others, but I feel it still makes sense to move it here in order to consolidate all callers of timekeeping_inject_offset(). Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Miroslav Lichvar Cc: Richard Cochran Cc: Prarit Bhargava Cc: Stephen Boyd Signed-off-by: Arnd Bergmann [jstultz: Whitespace fixup] Signed-off-by: John Stultz --- include/linux/time.h | 26 ---------- kernel/time/ntp.c | 61 ---------------------- kernel/time/ntp_internal.h | 1 - kernel/time/time.c | 36 +------------ kernel/time/timekeeping.c | 123 ++++++++++++++++++++++++++++++++++++++++++++- kernel/time/timekeeping.h | 2 +- 6 files changed, 123 insertions(+), 126 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 9bc1f945777c..c0fbad08448f 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -134,32 +134,6 @@ static inline bool timeval_valid(const struct timeval *tv) extern struct timespec timespec_trunc(struct timespec t, unsigned gran); -/* - * Validates if a timespec/timeval used to inject a time offset is valid. - * Offsets can be postive or negative. The value of the timeval/timespec - * is the sum of its fields, but *NOTE*: the field tv_usec/tv_nsec must - * always be non-negative. - */ -static inline bool timeval_inject_offset_valid(const struct timeval *tv) -{ - /* We don't check the tv_sec as it can be positive or negative */ - - /* Can't have more microseconds then a second */ - if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC) - return false; - return true; -} - -static inline bool timespec_inject_offset_valid(const struct timespec *ts) -{ - /* We don't check the tv_sec as it can be positive or negative */ - - /* Can't have more nanoseconds then a second */ - if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC) - return false; - return true; -} - /* Some architectures do not supply their own clocksource. * This is mainly the case in architectures that get their * inter-tick times by reading the counter on their interval diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index bc19de1a0683..90f84582a076 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -713,67 +713,6 @@ static inline void process_adjtimex_modes(struct timex *txc, } - -/** - * ntp_validate_timex - Ensures the timex is ok for use in do_adjtimex - */ -int ntp_validate_timex(struct timex *txc) -{ - if (txc->modes & ADJ_ADJTIME) { - /* singleshot must not be used with any other mode bits */ - if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) - return -EINVAL; - if (!(txc->modes & ADJ_OFFSET_READONLY) && - !capable(CAP_SYS_TIME)) - return -EPERM; - } else { - /* In order to modify anything, you gotta be super-user! */ - if (txc->modes && !capable(CAP_SYS_TIME)) - return -EPERM; - /* - * if the quartz is off by more than 10% then - * something is VERY wrong! - */ - if (txc->modes & ADJ_TICK && - (txc->tick < 900000/USER_HZ || - txc->tick > 1100000/USER_HZ)) - return -EINVAL; - } - - if (txc->modes & ADJ_SETOFFSET) { - /* In order to inject time, you gotta be super-user! */ - if (!capable(CAP_SYS_TIME)) - return -EPERM; - - if (txc->modes & ADJ_NANO) { - struct timespec ts; - - ts.tv_sec = txc->time.tv_sec; - ts.tv_nsec = txc->time.tv_usec; - if (!timespec_inject_offset_valid(&ts)) - return -EINVAL; - - } else { - if (!timeval_inject_offset_valid(&txc->time)) - return -EINVAL; - } - } - - /* - * Check for potential multiplication overflows that can - * only happen on 64-bit systems: - */ - if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { - if (LLONG_MIN / PPM_SCALE > txc->freq) - return -EINVAL; - if (LLONG_MAX / PPM_SCALE < txc->freq) - return -EINVAL; - } - - return 0; -} - - /* * adjtimex mainly allows reading (and writing, if superuser) of * kernel time-keeping variables. used by xntpd. diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index d8a7c11fa71a..74b52cd48209 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -7,7 +7,6 @@ extern void ntp_clear(void); extern u64 ntp_tick_length(void); extern ktime_t ntp_get_next_leap(void); extern int second_overflow(time64_t secs); -extern int ntp_validate_timex(struct timex *); extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *); extern void __hardpps(const struct timespec64 *, const struct timespec64 *); #endif /* _LINUX_NTP_INTERNAL_H */ diff --git a/kernel/time/time.c b/kernel/time/time.c index 44a8c1402133..04684e294f00 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -157,40 +157,6 @@ SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv, return 0; } -/* - * Indicates if there is an offset between the system clock and the hardware - * clock/persistent clock/rtc. - */ -int persistent_clock_is_local; - -/* - * Adjust the time obtained from the CMOS to be UTC time instead of - * local time. - * - * This is ugly, but preferable to the alternatives. Otherwise we - * would either need to write a program to do it in /etc/rc (and risk - * confusion if the program gets run more than once; it would also be - * hard to make the program warp the clock precisely n hours) or - * compile in the timezone information into the kernel. Bad, bad.... - * - * - TYT, 1992-01-01 - * - * The best thing to do is to keep the CMOS clock in universal time (UTC) - * as real UNIX machines always do it. This avoids all headaches about - * daylight saving times and warping kernel clocks. - */ -static inline void warp_clock(void) -{ - if (sys_tz.tz_minuteswest != 0) { - struct timespec adjust; - - persistent_clock_is_local = 1; - adjust.tv_sec = sys_tz.tz_minuteswest * 60; - adjust.tv_nsec = 0; - timekeeping_inject_offset(&adjust); - } -} - /* * In case for some reason the CMOS clock has not already been running * in UTC, but in some local time: The first time we set the timezone, @@ -224,7 +190,7 @@ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz if (firsttime) { firsttime = 0; if (!tv) - warp_clock(); + timekeeping_warp_clock(); } } if (tv) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 2cafb49aa65e..7d8e0e842484 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1258,13 +1258,39 @@ out: } EXPORT_SYMBOL(do_settimeofday64); +/* + * Validates if a timespec/timeval used to inject a time offset is valid. + * Offsets can be postive or negative. The value of the timeval/timespec + * is the sum of its fields, but *NOTE*: the field tv_usec/tv_nsec must + * always be non-negative. + */ +static inline bool timeval_inject_offset_valid(const struct timeval *tv) +{ + /* We don't check the tv_sec as it can be positive or negative */ + + /* Can't have more microseconds then a second */ + if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC) + return false; + return true; +} + +static inline bool timespec_inject_offset_valid(const struct timespec *ts) +{ + /* We don't check the tv_sec as it can be positive or negative */ + + /* Can't have more nanoseconds then a second */ + if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC) + return false; + return true; +} + /** * timekeeping_inject_offset - Adds or subtracts from the current time. * @tv: pointer to the timespec variable containing the offset * * Adds or subtracts an offset value from the current time. */ -int timekeeping_inject_offset(struct timespec *ts) +static int timekeeping_inject_offset(struct timespec *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; @@ -1303,7 +1329,40 @@ error: /* even if we error out, we forwarded the time, so call update */ return ret; } -EXPORT_SYMBOL(timekeeping_inject_offset); + +/* + * Indicates if there is an offset between the system clock and the hardware + * clock/persistent clock/rtc. + */ +int persistent_clock_is_local; + +/* + * Adjust the time obtained from the CMOS to be UTC time instead of + * local time. + * + * This is ugly, but preferable to the alternatives. Otherwise we + * would either need to write a program to do it in /etc/rc (and risk + * confusion if the program gets run more than once; it would also be + * hard to make the program warp the clock precisely n hours) or + * compile in the timezone information into the kernel. Bad, bad.... + * + * - TYT, 1992-01-01 + * + * The best thing to do is to keep the CMOS clock in universal time (UTC) + * as real UNIX machines always do it. This avoids all headaches about + * daylight saving times and warping kernel clocks. + */ +void timekeeping_warp_clock(void) +{ + if (sys_tz.tz_minuteswest != 0) { + struct timespec adjust; + + persistent_clock_is_local = 1; + adjust.tv_sec = sys_tz.tz_minuteswest * 60; + adjust.tv_nsec = 0; + timekeeping_inject_offset(&adjust); + } +} /** * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic @@ -2247,6 +2306,66 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, return base; } +/** + * ntp_validate_timex - Ensures the timex is ok for use in do_adjtimex + */ +static int ntp_validate_timex(struct timex *txc) +{ + if (txc->modes & ADJ_ADJTIME) { + /* singleshot must not be used with any other mode bits */ + if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) + return -EINVAL; + if (!(txc->modes & ADJ_OFFSET_READONLY) && + !capable(CAP_SYS_TIME)) + return -EPERM; + } else { + /* In order to modify anything, you gotta be super-user! */ + if (txc->modes && !capable(CAP_SYS_TIME)) + return -EPERM; + /* + * if the quartz is off by more than 10% then + * something is VERY wrong! + */ + if (txc->modes & ADJ_TICK && + (txc->tick < 900000/USER_HZ || + txc->tick > 1100000/USER_HZ)) + return -EINVAL; + } + + if (txc->modes & ADJ_SETOFFSET) { + /* In order to inject time, you gotta be super-user! */ + if (!capable(CAP_SYS_TIME)) + return -EPERM; + + if (txc->modes & ADJ_NANO) { + struct timespec ts; + + ts.tv_sec = txc->time.tv_sec; + ts.tv_nsec = txc->time.tv_usec; + if (!timespec_inject_offset_valid(&ts)) + return -EINVAL; + + } else { + if (!timeval_inject_offset_valid(&txc->time)) + return -EINVAL; + } + } + + /* + * Check for potential multiplication overflows that can + * only happen on 64-bit systems: + */ + if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { + if (LLONG_MIN / PPM_SCALE > txc->freq) + return -EINVAL; + if (LLONG_MAX / PPM_SCALE < txc->freq) + return -EINVAL; + } + + return 0; +} + + /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function */ diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index d0914676d4c5..44aec7893cdd 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -10,7 +10,7 @@ extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, extern int timekeeping_valid_for_hres(void); extern u64 timekeeping_max_deferment(void); -extern int timekeeping_inject_offset(struct timespec *ts); +extern void timekeeping_warp_clock(void); extern int timekeeping_suspend(void); extern void timekeeping_resume(void); -- cgit v1.2.3 From 85bf19e7df2479140eff2348a4e6a9c19b5c3960 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 19 Oct 2017 13:14:46 +0200 Subject: time: Remove unused functions The (slow but) ongoing work on conversion from timespec to timespec64 has led some timespec based helper functions to become unused. No new code should use them, so we can remove the functions entirely. I'm planning to obsolete additional interfaces next and remove more of these. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Miroslav Lichvar Cc: Richard Cochran Cc: Prarit Bhargava Cc: Stephen Boyd Signed-off-by: Arnd Bergmann Signed-off-by: John Stultz --- include/linux/time.h | 18 ------------------ include/linux/time64.h | 28 ---------------------------- kernel/time/time.c | 18 ------------------ 3 files changed, 64 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index c0fbad08448f..0e8a80918484 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -39,15 +39,6 @@ static inline int timespec_compare(const struct timespec *lhs, const struct time return lhs->tv_nsec - rhs->tv_nsec; } -static inline int timeval_compare(const struct timeval *lhs, const struct timeval *rhs) -{ - if (lhs->tv_sec < rhs->tv_sec) - return -1; - if (lhs->tv_sec > rhs->tv_sec) - return 1; - return lhs->tv_usec - rhs->tv_usec; -} - extern time64_t mktime64(const unsigned int year, const unsigned int mon, const unsigned int day, const unsigned int hour, const unsigned int min, const unsigned int sec); @@ -65,15 +56,6 @@ static inline unsigned long mktime(const unsigned int year, extern void set_normalized_timespec(struct timespec *ts, time_t sec, s64 nsec); -/* - * timespec_add_safe assumes both values are positive and checks - * for overflow. It will return TIME_T_MAX if the reutrn would be - * smaller then either of the arguments. - */ -extern struct timespec timespec_add_safe(const struct timespec lhs, - const struct timespec rhs); - - static inline struct timespec timespec_add(struct timespec lhs, struct timespec rhs) { diff --git a/include/linux/time64.h b/include/linux/time64.h index 980c71b3001a..402b595c76d2 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -53,16 +53,6 @@ static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) return ts; } -static inline struct itimerspec itimerspec64_to_itimerspec(struct itimerspec64 *its64) -{ - return *its64; -} - -static inline struct itimerspec64 itimerspec_to_itimerspec64(struct itimerspec *its) -{ - return *its; -} - # define timespec64_equal timespec_equal # define timespec64_compare timespec_compare # define set_normalized_timespec64 set_normalized_timespec @@ -94,24 +84,6 @@ static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) return ret; } -static inline struct itimerspec itimerspec64_to_itimerspec(struct itimerspec64 *its64) -{ - struct itimerspec ret; - - ret.it_interval = timespec64_to_timespec(its64->it_interval); - ret.it_value = timespec64_to_timespec(its64->it_value); - return ret; -} - -static inline struct itimerspec64 itimerspec_to_itimerspec64(struct itimerspec *its) -{ - struct itimerspec64 ret; - - ret.it_interval = timespec_to_timespec64(its->it_interval); - ret.it_value = timespec_to_timespec64(its->it_value); - return ret; -} - static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { diff --git a/kernel/time/time.c b/kernel/time/time.c index 04684e294f00..947fb614c78f 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -818,24 +818,6 @@ unsigned long nsecs_to_jiffies(u64 n) } EXPORT_SYMBOL_GPL(nsecs_to_jiffies); -/* - * Add two timespec values and do a safety check for overflow. - * It's assumed that both values are valid (>= 0) - */ -struct timespec timespec_add_safe(const struct timespec lhs, - const struct timespec rhs) -{ - struct timespec res; - - set_normalized_timespec(&res, lhs.tv_sec + rhs.tv_sec, - lhs.tv_nsec + rhs.tv_nsec); - - if (res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec) - res.tv_sec = TIME_T_MAX; - - return res; -} - /* * Add two timespec64 values and do a safety check for overflow. * It's assumed that both values are valid (>= 0). -- cgit v1.2.3 From 5dbf20127f8cca8588ad0b0e3e8ded587ac7afa0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 19 Oct 2017 13:14:47 +0200 Subject: time: Move time_t based interfaces to time32.h Interfaces based on 'struct timespec' or 'struct timeval' should no longer be used for new code, which can use either ktime_t or 'struct timespec64' instead. To make this a little clearer, this moves the various helpers into a new time32.h header. For the moment, this gets included by the normal time.h, but we may be able to separate it entirely when most users of time32.h are gone. Individual helpers in the new file can get removed once they become unused in the future. Since the contents of time32.h look a lot like what's in time64.h, I'm reordering them during the move to make them more similar, and to allow a follow-up patch to redirect the 'timespec' based functions to thei 'timespec64' based counterparts on 64-bit architectures later. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Miroslav Lichvar Cc: Richard Cochran Cc: Prarit Bhargava Cc: Stephen Boyd Signed-off-by: Arnd Bergmann [jstultz: Whitespace & checkpatch fixups] Signed-off-by: John Stultz --- include/linux/time.h | 163 +-------------------------------------------- include/linux/time32.h | 176 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 177 insertions(+), 162 deletions(-) create mode 100644 include/linux/time32.h (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 0e8a80918484..c375f54a678d 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -17,105 +17,10 @@ int get_itimerspec64(struct itimerspec64 *it, int put_itimerspec64(const struct itimerspec64 *it, struct itimerspec __user *uit); -#define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1) - -static inline int timespec_equal(const struct timespec *a, - const struct timespec *b) -{ - return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); -} - -/* - * lhs < rhs: return <0 - * lhs == rhs: return 0 - * lhs > rhs: return >0 - */ -static inline int timespec_compare(const struct timespec *lhs, const struct timespec *rhs) -{ - if (lhs->tv_sec < rhs->tv_sec) - return -1; - if (lhs->tv_sec > rhs->tv_sec) - return 1; - return lhs->tv_nsec - rhs->tv_nsec; -} - extern time64_t mktime64(const unsigned int year, const unsigned int mon, const unsigned int day, const unsigned int hour, const unsigned int min, const unsigned int sec); -/** - * Deprecated. Use mktime64(). - */ -static inline unsigned long mktime(const unsigned int year, - const unsigned int mon, const unsigned int day, - const unsigned int hour, const unsigned int min, - const unsigned int sec) -{ - return mktime64(year, mon, day, hour, min, sec); -} - -extern void set_normalized_timespec(struct timespec *ts, time_t sec, s64 nsec); - -static inline struct timespec timespec_add(struct timespec lhs, - struct timespec rhs) -{ - struct timespec ts_delta; - set_normalized_timespec(&ts_delta, lhs.tv_sec + rhs.tv_sec, - lhs.tv_nsec + rhs.tv_nsec); - return ts_delta; -} - -/* - * sub = lhs - rhs, in normalized form - */ -static inline struct timespec timespec_sub(struct timespec lhs, - struct timespec rhs) -{ - struct timespec ts_delta; - set_normalized_timespec(&ts_delta, lhs.tv_sec - rhs.tv_sec, - lhs.tv_nsec - rhs.tv_nsec); - return ts_delta; -} - -/* - * Returns true if the timespec is norm, false if denorm: - */ -static inline bool timespec_valid(const struct timespec *ts) -{ - /* Dates before 1970 are bogus */ - if (ts->tv_sec < 0) - return false; - /* Can't have more nanoseconds then a second */ - if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) - return false; - return true; -} - -static inline bool timespec_valid_strict(const struct timespec *ts) -{ - if (!timespec_valid(ts)) - return false; - /* Disallow values that could overflow ktime_t */ - if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) - return false; - return true; -} - -static inline bool timeval_valid(const struct timeval *tv) -{ - /* Dates before 1970 are bogus */ - if (tv->tv_sec < 0) - return false; - - /* Can't have more microseconds then a second */ - if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC) - return false; - - return true; -} - -extern struct timespec timespec_trunc(struct timespec t, unsigned gran); - /* Some architectures do not supply their own clocksource. * This is mainly the case in architectures that get their * inter-tick times by reading the counter on their interval @@ -164,73 +69,7 @@ struct tm { void time64_to_tm(time64_t totalsecs, int offset, struct tm *result); -/** - * time_to_tm - converts the calendar time to local broken-down time - * - * @totalsecs the number of seconds elapsed since 00:00:00 on January 1, 1970, - * Coordinated Universal Time (UTC). - * @offset offset seconds adding to totalsecs. - * @result pointer to struct tm variable to receive broken-down time - */ -static inline void time_to_tm(time_t totalsecs, int offset, struct tm *result) -{ - time64_to_tm(totalsecs, offset, result); -} - -/** - * timespec_to_ns - Convert timespec to nanoseconds - * @ts: pointer to the timespec variable to be converted - * - * Returns the scalar nanosecond representation of the timespec - * parameter. - */ -static inline s64 timespec_to_ns(const struct timespec *ts) -{ - return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; -} - -/** - * timeval_to_ns - Convert timeval to nanoseconds - * @ts: pointer to the timeval variable to be converted - * - * Returns the scalar nanosecond representation of the timeval - * parameter. - */ -static inline s64 timeval_to_ns(const struct timeval *tv) -{ - return ((s64) tv->tv_sec * NSEC_PER_SEC) + - tv->tv_usec * NSEC_PER_USEC; -} - -/** - * ns_to_timespec - Convert nanoseconds to timespec - * @nsec: the nanoseconds value to be converted - * - * Returns the timespec representation of the nsec parameter. - */ -extern struct timespec ns_to_timespec(const s64 nsec); - -/** - * ns_to_timeval - Convert nanoseconds to timeval - * @nsec: the nanoseconds value to be converted - * - * Returns the timeval representation of the nsec parameter. - */ -extern struct timeval ns_to_timeval(const s64 nsec); - -/** - * timespec_add_ns - Adds nanoseconds to a timespec - * @a: pointer to timespec to be incremented - * @ns: unsigned nanoseconds value to be added - * - * This must always be inlined because its used from the x86-64 vdso, - * which cannot call other kernel functions. - */ -static __always_inline void timespec_add_ns(struct timespec *a, u64 ns) -{ - a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); - a->tv_nsec = ns; -} +# include static inline bool itimerspec64_valid(const struct itimerspec64 *its) { diff --git a/include/linux/time32.h b/include/linux/time32.h new file mode 100644 index 000000000000..9b9c43f0d39b --- /dev/null +++ b/include/linux/time32.h @@ -0,0 +1,176 @@ +#ifndef _LINUX_TIME32_H +#define _LINUX_TIME32_H +/* + * These are all interfaces based on the old time_t definition + * that overflows in 2038 on 32-bit architectures. New code + * should use the replacements based on time64_t and timespec64. + * + * Any interfaces in here that become unused as we migrate + * code to time64_t should get removed. + */ + +#include + +#define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1) + +static inline int timespec_equal(const struct timespec *a, + const struct timespec *b) +{ + return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); +} + +/* + * lhs < rhs: return <0 + * lhs == rhs: return 0 + * lhs > rhs: return >0 + */ +static inline int timespec_compare(const struct timespec *lhs, const struct timespec *rhs) +{ + if (lhs->tv_sec < rhs->tv_sec) + return -1; + if (lhs->tv_sec > rhs->tv_sec) + return 1; + return lhs->tv_nsec - rhs->tv_nsec; +} + +extern void set_normalized_timespec(struct timespec *ts, time_t sec, s64 nsec); + +static inline struct timespec timespec_add(struct timespec lhs, + struct timespec rhs) +{ + struct timespec ts_delta; + + set_normalized_timespec(&ts_delta, lhs.tv_sec + rhs.tv_sec, + lhs.tv_nsec + rhs.tv_nsec); + return ts_delta; +} + +/* + * sub = lhs - rhs, in normalized form + */ +static inline struct timespec timespec_sub(struct timespec lhs, + struct timespec rhs) +{ + struct timespec ts_delta; + + set_normalized_timespec(&ts_delta, lhs.tv_sec - rhs.tv_sec, + lhs.tv_nsec - rhs.tv_nsec); + return ts_delta; +} + +/* + * Returns true if the timespec is norm, false if denorm: + */ +static inline bool timespec_valid(const struct timespec *ts) +{ + /* Dates before 1970 are bogus */ + if (ts->tv_sec < 0) + return false; + /* Can't have more nanoseconds then a second */ + if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) + return false; + return true; +} + +static inline bool timespec_valid_strict(const struct timespec *ts) +{ + if (!timespec_valid(ts)) + return false; + /* Disallow values that could overflow ktime_t */ + if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) + return false; + return true; +} + +/** + * timespec_to_ns - Convert timespec to nanoseconds + * @ts: pointer to the timespec variable to be converted + * + * Returns the scalar nanosecond representation of the timespec + * parameter. + */ +static inline s64 timespec_to_ns(const struct timespec *ts) +{ + return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; +} + +/** + * ns_to_timespec - Convert nanoseconds to timespec + * @nsec: the nanoseconds value to be converted + * + * Returns the timespec representation of the nsec parameter. + */ +extern struct timespec ns_to_timespec(const s64 nsec); + +/** + * timespec_add_ns - Adds nanoseconds to a timespec + * @a: pointer to timespec to be incremented + * @ns: unsigned nanoseconds value to be added + * + * This must always be inlined because its used from the x86-64 vdso, + * which cannot call other kernel functions. + */ +static __always_inline void timespec_add_ns(struct timespec *a, u64 ns) +{ + a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); + a->tv_nsec = ns; +} + +/** + * time_to_tm - converts the calendar time to local broken-down time + * + * @totalsecs the number of seconds elapsed since 00:00:00 on January 1, 1970, + * Coordinated Universal Time (UTC). + * @offset offset seconds adding to totalsecs. + * @result pointer to struct tm variable to receive broken-down time + */ +static inline void time_to_tm(time_t totalsecs, int offset, struct tm *result) +{ + time64_to_tm(totalsecs, offset, result); +} + +static inline unsigned long mktime(const unsigned int year, + const unsigned int mon, const unsigned int day, + const unsigned int hour, const unsigned int min, + const unsigned int sec) +{ + return mktime64(year, mon, day, hour, min, sec); +} + +static inline bool timeval_valid(const struct timeval *tv) +{ + /* Dates before 1970 are bogus */ + if (tv->tv_sec < 0) + return false; + + /* Can't have more microseconds then a second */ + if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC) + return false; + + return true; +} + +extern struct timespec timespec_trunc(struct timespec t, unsigned int gran); + +/** + * timeval_to_ns - Convert timeval to nanoseconds + * @ts: pointer to the timeval variable to be converted + * + * Returns the scalar nanosecond representation of the timeval + * parameter. + */ +static inline s64 timeval_to_ns(const struct timeval *tv) +{ + return ((s64) tv->tv_sec * NSEC_PER_SEC) + + tv->tv_usec * NSEC_PER_USEC; +} + +/** + * ns_to_timeval - Convert nanoseconds to timeval + * @nsec: the nanoseconds value to be converted + * + * Returns the timeval representation of the nsec parameter. + */ +extern struct timeval ns_to_timeval(const s64 nsec); + +#endif -- cgit v1.2.3 From abc8f96e3eb846fcf6333395ee1f6ed4a734576c Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 19 Oct 2017 13:14:48 +0200 Subject: time: Move time_t conversion helpers to time32.h On 64-bit architectures, the timespec64 based helpers in linux/time.h are defined as macros pointing to their timespec based counterparts. This made sense when they were first introduced, but as we are migrating away from timespec in general, it's much less intuitive now. This changes the macros to work in the exact opposite way: we always provide the timespec64 based helpers and define the old interfaces as macros for them. Now we can move those macros into linux/time32.h, which already contains the respective helpers for 32-bit architectures. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Miroslav Lichvar Cc: Richard Cochran Cc: Prarit Bhargava Cc: Stephen Boyd Signed-off-by: Arnd Bergmann Signed-off-by: John Stultz --- include/linux/time32.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/time64.h | 50 +------------------------------------------------- kernel/time/time.c | 5 +++-- 3 files changed, 49 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time32.h b/include/linux/time32.h index 9b9c43f0d39b..65b1de25198d 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -13,6 +13,49 @@ #define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1) +#if __BITS_PER_LONG == 64 + +/* timespec64 is defined as timespec here */ +static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) +{ + return ts64; +} + +static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) +{ + return ts; +} + +# define timespec_equal timespec64_equal +# define timespec_compare timespec64_compare +# define set_normalized_timespec set_normalized_timespec64 +# define timespec_add timespec64_add +# define timespec_sub timespec64_sub +# define timespec_valid timespec64_valid +# define timespec_valid_strict timespec64_valid_strict +# define timespec_to_ns timespec64_to_ns +# define ns_to_timespec ns_to_timespec64 +# define timespec_add_ns timespec64_add_ns + +#else +static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) +{ + struct timespec ret; + + ret.tv_sec = (time_t)ts64.tv_sec; + ret.tv_nsec = ts64.tv_nsec; + return ret; +} + +static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) +{ + struct timespec64 ret; + + ret.tv_sec = ts.tv_sec; + ret.tv_nsec = ts.tv_nsec; + return ret; +} + static inline int timespec_equal(const struct timespec *a, const struct timespec *b) { @@ -116,6 +159,8 @@ static __always_inline void timespec_add_ns(struct timespec *a, u64 ns) a->tv_nsec = ns; } +#endif + /** * time_to_tm - converts the calendar time to local broken-down time * diff --git a/include/linux/time64.h b/include/linux/time64.h index 402b595c76d2..ec1888cf5378 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -7,11 +7,8 @@ typedef __s64 time64_t; typedef __u64 timeu64_t; -/* - * This wants to go into uapi/linux/time.h once we agreed about the - * userspace interfaces. - */ #if __BITS_PER_LONG == 64 +/* this trick allows us to optimize out timespec64_to_timespec */ # define timespec64 timespec #define itimerspec64 itimerspec #else @@ -41,49 +38,6 @@ struct itimerspec64 { #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) -#if __BITS_PER_LONG == 64 - -static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) -{ - return ts64; -} - -static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) -{ - return ts; -} - -# define timespec64_equal timespec_equal -# define timespec64_compare timespec_compare -# define set_normalized_timespec64 set_normalized_timespec -# define timespec64_add timespec_add -# define timespec64_sub timespec_sub -# define timespec64_valid timespec_valid -# define timespec64_valid_strict timespec_valid_strict -# define timespec64_to_ns timespec_to_ns -# define ns_to_timespec64 ns_to_timespec -# define timespec64_add_ns timespec_add_ns - -#else - -static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) -{ - struct timespec ret; - - ret.tv_sec = (time_t)ts64.tv_sec; - ret.tv_nsec = ts64.tv_nsec; - return ret; -} - -static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) -{ - struct timespec64 ret; - - ret.tv_sec = ts.tv_sec; - ret.tv_nsec = ts.tv_nsec; - return ret; -} - static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { @@ -185,8 +139,6 @@ static __always_inline void timespec64_add_ns(struct timespec64 *a, u64 ns) a->tv_nsec = ns; } -#endif - /* * timespec64_add_safe assumes both values are positive and checks for * overflow. It will return TIME64_MAX in case of overflow. diff --git a/kernel/time/time.c b/kernel/time/time.c index 947fb614c78f..fe60ebd301cf 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -407,6 +407,7 @@ time64_t mktime64(const unsigned int year0, const unsigned int mon0, } EXPORT_SYMBOL(mktime64); +#if __BITS_PER_LONG == 32 /** * set_normalized_timespec - set timespec sec and nsec parts and normalize * @@ -467,6 +468,7 @@ struct timespec ns_to_timespec(const s64 nsec) return ts; } EXPORT_SYMBOL(ns_to_timespec); +#endif /** * ns_to_timeval - Convert nanoseconds to timeval @@ -486,7 +488,6 @@ struct timeval ns_to_timeval(const s64 nsec) } EXPORT_SYMBOL(ns_to_timeval); -#if BITS_PER_LONG == 32 /** * set_normalized_timespec - set timespec sec and nsec parts and normalize * @@ -547,7 +548,7 @@ struct timespec64 ns_to_timespec64(const s64 nsec) return ts; } EXPORT_SYMBOL(ns_to_timespec64); -#endif + /** * msecs_to_jiffies: - convert milliseconds to jiffies * @m: time in milliseconds -- cgit v1.2.3 From 6546911ed369af8d747215ff8b6144618e91c6ab Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 19 Oct 2017 13:14:49 +0200 Subject: time: Move old timekeeping interfaces to timekeeping32.h The interfaces based on 'struct timespec' and 'unsigned long' seconds are no longer recommended for new code, and we are trying to migrate to ktime_t based interfaces and other y2038-safe variants. This moves all the legacy interfaces from linux/timekeeping.h into a new timekeeping32.h to better document this. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Miroslav Lichvar Cc: Richard Cochran Cc: Prarit Bhargava Cc: Stephen Boyd Signed-off-by: Arnd Bergmann Signed-off-by: John Stultz --- include/linux/ktime.h | 1 + include/linux/timekeeping.h | 137 +------------------------------------- include/linux/timekeeping32.h | 151 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 154 insertions(+), 135 deletions(-) create mode 100644 include/linux/timekeeping32.h (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 0c8bd45c8206..5b9fddbaac41 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -270,5 +270,6 @@ static inline ktime_t ms_to_ktime(u64 ms) } # include +# include #endif diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index ddc229ff6d1e..405beea4e71b 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -15,27 +15,16 @@ extern void xtime_update(unsigned long ticks); /* * Get and set timeofday */ -extern void do_gettimeofday(struct timeval *tv); extern int do_settimeofday64(const struct timespec64 *ts); extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* * Kernel time accessors */ -unsigned long get_seconds(void); struct timespec64 current_kernel_time64(void); -/* does not take xtime_lock */ -struct timespec __current_kernel_time(void); - -static inline struct timespec current_kernel_time(void) -{ - struct timespec64 now = current_kernel_time64(); - - return timespec64_to_timespec(now); -} /* - * timespec based interfaces + * timespec64 based interfaces */ struct timespec64 get_monotonic_coarse64(void); extern void getrawmonotonic64(struct timespec64 *ts); @@ -47,116 +36,6 @@ extern int __getnstimeofday64(struct timespec64 *tv); extern void getnstimeofday64(struct timespec64 *tv); extern void getboottime64(struct timespec64 *ts); -#if BITS_PER_LONG == 64 -/** - * Deprecated. Use do_settimeofday64(). - */ -static inline int do_settimeofday(const struct timespec *ts) -{ - return do_settimeofday64(ts); -} - -static inline int __getnstimeofday(struct timespec *ts) -{ - return __getnstimeofday64(ts); -} - -static inline void getnstimeofday(struct timespec *ts) -{ - getnstimeofday64(ts); -} - -static inline void ktime_get_ts(struct timespec *ts) -{ - ktime_get_ts64(ts); -} - -static inline void ktime_get_real_ts(struct timespec *ts) -{ - getnstimeofday64(ts); -} - -static inline void getrawmonotonic(struct timespec *ts) -{ - getrawmonotonic64(ts); -} - -static inline struct timespec get_monotonic_coarse(void) -{ - return get_monotonic_coarse64(); -} - -static inline void getboottime(struct timespec *ts) -{ - return getboottime64(ts); -} -#else -/** - * Deprecated. Use do_settimeofday64(). - */ -static inline int do_settimeofday(const struct timespec *ts) -{ - struct timespec64 ts64; - - ts64 = timespec_to_timespec64(*ts); - return do_settimeofday64(&ts64); -} - -static inline int __getnstimeofday(struct timespec *ts) -{ - struct timespec64 ts64; - int ret = __getnstimeofday64(&ts64); - - *ts = timespec64_to_timespec(ts64); - return ret; -} - -static inline void getnstimeofday(struct timespec *ts) -{ - struct timespec64 ts64; - - getnstimeofday64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - -static inline void ktime_get_ts(struct timespec *ts) -{ - struct timespec64 ts64; - - ktime_get_ts64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - -static inline void ktime_get_real_ts(struct timespec *ts) -{ - struct timespec64 ts64; - - getnstimeofday64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - -static inline void getrawmonotonic(struct timespec *ts) -{ - struct timespec64 ts64; - - getrawmonotonic64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - -static inline struct timespec get_monotonic_coarse(void) -{ - return timespec64_to_timespec(get_monotonic_coarse64()); -} - -static inline void getboottime(struct timespec *ts) -{ - struct timespec64 ts64; - - getboottime64(&ts64); - *ts = timespec64_to_timespec(ts64); -} -#endif - #define ktime_get_real_ts64(ts) getnstimeofday64(ts) /* @@ -241,23 +120,13 @@ extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); /* - * Timespec interfaces utilizing the ktime based ones + * timespec64 interfaces utilizing the ktime based ones */ -static inline void get_monotonic_boottime(struct timespec *ts) -{ - *ts = ktime_to_timespec(ktime_get_boottime()); -} - static inline void get_monotonic_boottime64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_boottime()); } -static inline void timekeeping_clocktai(struct timespec *ts) -{ - *ts = ktime_to_timespec(ktime_get_clocktai()); -} - static inline void timekeeping_clocktai64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); @@ -340,10 +209,8 @@ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); */ extern int persistent_clock_is_local; -extern void read_persistent_clock(struct timespec *ts); extern void read_persistent_clock64(struct timespec64 *ts); extern void read_boot_clock64(struct timespec64 *ts); -extern int update_persistent_clock(struct timespec now); extern int update_persistent_clock64(struct timespec64 now); diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h new file mode 100644 index 000000000000..af4114d5dc17 --- /dev/null +++ b/include/linux/timekeeping32.h @@ -0,0 +1,151 @@ +#ifndef _LINUX_TIMEKEEPING32_H +#define _LINUX_TIMEKEEPING32_H +/* + * These interfaces are all based on the old timespec type + * and should get replaced with the timespec64 based versions + * over time so we can remove the file here. + */ + +extern void do_gettimeofday(struct timeval *tv); +unsigned long get_seconds(void); + +/* does not take xtime_lock */ +struct timespec __current_kernel_time(void); + +static inline struct timespec current_kernel_time(void) +{ + struct timespec64 now = current_kernel_time64(); + + return timespec64_to_timespec(now); +} + +#if BITS_PER_LONG == 64 +/** + * Deprecated. Use do_settimeofday64(). + */ +static inline int do_settimeofday(const struct timespec *ts) +{ + return do_settimeofday64(ts); +} + +static inline int __getnstimeofday(struct timespec *ts) +{ + return __getnstimeofday64(ts); +} + +static inline void getnstimeofday(struct timespec *ts) +{ + getnstimeofday64(ts); +} + +static inline void ktime_get_ts(struct timespec *ts) +{ + ktime_get_ts64(ts); +} + +static inline void ktime_get_real_ts(struct timespec *ts) +{ + getnstimeofday64(ts); +} + +static inline void getrawmonotonic(struct timespec *ts) +{ + getrawmonotonic64(ts); +} + +static inline struct timespec get_monotonic_coarse(void) +{ + return get_monotonic_coarse64(); +} + +static inline void getboottime(struct timespec *ts) +{ + return getboottime64(ts); +} +#else +/** + * Deprecated. Use do_settimeofday64(). + */ +static inline int do_settimeofday(const struct timespec *ts) +{ + struct timespec64 ts64; + + ts64 = timespec_to_timespec64(*ts); + return do_settimeofday64(&ts64); +} + +static inline int __getnstimeofday(struct timespec *ts) +{ + struct timespec64 ts64; + int ret = __getnstimeofday64(&ts64); + + *ts = timespec64_to_timespec(ts64); + return ret; +} + +static inline void getnstimeofday(struct timespec *ts) +{ + struct timespec64 ts64; + + getnstimeofday64(&ts64); + *ts = timespec64_to_timespec(ts64); +} + +static inline void ktime_get_ts(struct timespec *ts) +{ + struct timespec64 ts64; + + ktime_get_ts64(&ts64); + *ts = timespec64_to_timespec(ts64); +} + +static inline void ktime_get_real_ts(struct timespec *ts) +{ + struct timespec64 ts64; + + getnstimeofday64(&ts64); + *ts = timespec64_to_timespec(ts64); +} + +static inline void getrawmonotonic(struct timespec *ts) +{ + struct timespec64 ts64; + + getrawmonotonic64(&ts64); + *ts = timespec64_to_timespec(ts64); +} + +static inline struct timespec get_monotonic_coarse(void) +{ + return timespec64_to_timespec(get_monotonic_coarse64()); +} + +static inline void getboottime(struct timespec *ts) +{ + struct timespec64 ts64; + + getboottime64(&ts64); + *ts = timespec64_to_timespec(ts64); +} +#endif + +/* + * Timespec interfaces utilizing the ktime based ones + */ +static inline void get_monotonic_boottime(struct timespec *ts) +{ + *ts = ktime_to_timespec(ktime_get_boottime()); +} + +static inline void timekeeping_clocktai(struct timespec *ts) +{ + *ts = ktime_to_timespec(ktime_get_clocktai()); +} + +/* + * Persistent clock related interfaces + */ +extern void read_persistent_clock(struct timespec *ts); +extern int update_persistent_clock(struct timespec now); + +#endif -- cgit v1.2.3 From 707ce9eac5fc3b68f98c887dddea3911a8fc4f9f Mon Sep 17 00:00:00 2001 From: James Ban Date: Mon, 30 Oct 2017 11:32:38 +0900 Subject: regulator: da9211: update for supporting da9223/4/5 This is update for supporting additional devices da9223/4/5. Only device strings is added because only package type is different. Signed-off-by: James Ban Signed-off-by: Mark Brown --- .../devicetree/bindings/regulator/da9211.txt | 82 ++++++++++++++++++++-- drivers/regulator/Kconfig | 2 +- drivers/regulator/da9211-regulator.c | 14 ++-- drivers/regulator/da9211-regulator.h | 2 +- include/linux/regulator/da9211.h | 5 +- 5 files changed, 91 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/regulator/da9211.txt b/Documentation/devicetree/bindings/regulator/da9211.txt index 0f2a6f8fcafd..27717e816e71 100644 --- a/Documentation/devicetree/bindings/regulator/da9211.txt +++ b/Documentation/devicetree/bindings/regulator/da9211.txt @@ -1,8 +1,9 @@ -* Dialog Semiconductor DA9211/DA9212/DA9213/DA9214/DA9215 Voltage Regulator +* Dialog Semiconductor DA9211/DA9212/DA9213/DA9223/DA9214/DA9224/DA9215/DA9225 + Voltage Regulator Required properties: -- compatible: "dlg,da9211" or "dlg,da9212" or "dlg,da9213" - or "dlg,da9214" or "dlg,da9215" +- compatible: "dlg,da9211" or "dlg,da9212" or "dlg,da9213" or "dlg,da9223" + or "dlg,da9214" or "dlg,da9224" or "dlg,da9215" or "dlg,da9225" - reg: I2C slave address, usually 0x68. - interrupts: the interrupt outputs of the controller - regulators: A node that houses a sub-node for each regulator within the @@ -16,7 +17,6 @@ Optional properties: - Any optional property defined in regulator.txt Example 1) DA9211 - pmic: da9211@68 { compatible = "dlg,da9211"; reg = <0x68>; @@ -35,7 +35,6 @@ Example 1) DA9211 }; Example 2) DA9212 - pmic: da9212@68 { compatible = "dlg,da9212"; reg = <0x68>; @@ -79,7 +78,25 @@ Example 3) DA9213 }; }; -Example 4) DA9214 +Example 4) DA9223 + pmic: da9223@68 { + compatible = "dlg,da9223"; + reg = <0x68>; + interrupts = <3 27>; + + regulators { + BUCKA { + regulator-name = "VBUCKA"; + regulator-min-microvolt = < 300000>; + regulator-max-microvolt = <1570000>; + regulator-min-microamp = <3000000>; + regulator-max-microamp = <6000000>; + enable-gpios = <&gpio 27 0>; + }; + }; + }; + +Example 5) DA9214 pmic: da9214@68 { compatible = "dlg,da9214"; reg = <0x68>; @@ -105,7 +122,33 @@ Example 4) DA9214 }; }; -Example 5) DA9215 +Example 6) DA9224 + pmic: da9224@68 { + compatible = "dlg,da9224"; + reg = <0x68>; + interrupts = <3 27>; + + regulators { + BUCKA { + regulator-name = "VBUCKA"; + regulator-min-microvolt = < 300000>; + regulator-max-microvolt = <1570000>; + regulator-min-microamp = <3000000>; + regulator-max-microamp = <6000000>; + enable-gpios = <&gpio 27 0>; + }; + BUCKB { + regulator-name = "VBUCKB"; + regulator-min-microvolt = < 300000>; + regulator-max-microvolt = <1570000>; + regulator-min-microamp = <3000000>; + regulator-max-microamp = <6000000>; + enable-gpios = <&gpio 17 0>; + }; + }; + }; + +Example 7) DA9215 pmic: da9215@68 { compatible = "dlg,da9215"; reg = <0x68>; @@ -131,3 +174,28 @@ Example 5) DA9215 }; }; +Example 8) DA9225 + pmic: da9225@68 { + compatible = "dlg,da9225"; + reg = <0x68>; + interrupts = <3 27>; + + regulators { + BUCKA { + regulator-name = "VBUCKA"; + regulator-min-microvolt = < 300000>; + regulator-max-microvolt = <1570000>; + regulator-min-microamp = <4000000>; + regulator-max-microamp = <7000000>; + enable-gpios = <&gpio 27 0>; + }; + BUCKB { + regulator-name = "VBUCKB"; + regulator-min-microvolt = < 300000>; + regulator-max-microvolt = <1570000>; + regulator-min-microamp = <4000000>; + regulator-max-microamp = <7000000>; + enable-gpios = <&gpio 17 0>; + }; + }; + }; diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index 0fd6195601ba..96cd55f9e3c5 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -244,7 +244,7 @@ config REGULATOR_DA9210 interface. config REGULATOR_DA9211 - tristate "Dialog Semiconductor DA9211/DA9212/DA9213/DA9214/DA9215 regulator" + tristate "Dialog Semiconductor DA9211/DA9212/DA9213/DA9223/DA9214/DA9224/DA9215/DA9225 regulator" depends on I2C select REGMAP_I2C help diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c index aa47280efd32..9b8f47617724 100644 --- a/drivers/regulator/da9211-regulator.c +++ b/drivers/regulator/da9211-regulator.c @@ -1,6 +1,6 @@ /* * da9211-regulator.c - Regulator device driver for DA9211/DA9212 - * /DA9213/DA9214/DA9215 + * /DA9213/DA9223/DA9214/DA9224/DA9215/DA9225 * Copyright (C) 2015 Dialog Semiconductor Ltd. * * This library is free software; you can redistribute it and/or @@ -496,8 +496,11 @@ static const struct i2c_device_id da9211_i2c_id[] = { {"da9211", DA9211}, {"da9212", DA9212}, {"da9213", DA9213}, + {"da9223", DA9223}, {"da9214", DA9214}, + {"da9224", DA9224}, {"da9215", DA9215}, + {"da9225", DA9225}, {}, }; MODULE_DEVICE_TABLE(i2c, da9211_i2c_id); @@ -507,8 +510,11 @@ static const struct of_device_id da9211_dt_ids[] = { { .compatible = "dlg,da9211", .data = &da9211_i2c_id[0] }, { .compatible = "dlg,da9212", .data = &da9211_i2c_id[1] }, { .compatible = "dlg,da9213", .data = &da9211_i2c_id[2] }, - { .compatible = "dlg,da9214", .data = &da9211_i2c_id[3] }, - { .compatible = "dlg,da9215", .data = &da9211_i2c_id[4] }, + { .compatible = "dlg,da9223", .data = &da9211_i2c_id[3] }, + { .compatible = "dlg,da9214", .data = &da9211_i2c_id[4] }, + { .compatible = "dlg,da9224", .data = &da9211_i2c_id[5] }, + { .compatible = "dlg,da9215", .data = &da9211_i2c_id[6] }, + { .compatible = "dlg,da9225", .data = &da9211_i2c_id[7] }, {}, }; MODULE_DEVICE_TABLE(of, da9211_dt_ids); @@ -526,5 +532,5 @@ static struct i2c_driver da9211_regulator_driver = { module_i2c_driver(da9211_regulator_driver); MODULE_AUTHOR("James Ban "); -MODULE_DESCRIPTION("DA9211/DA9212/DA9213/DA9214/DA9215 regulator driver"); +MODULE_DESCRIPTION("DA9211/DA9212/DA9213/DA9223/DA9214/DA9224/DA9215/DA9225 regulator driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/regulator/da9211-regulator.h b/drivers/regulator/da9211-regulator.h index b841bbf330cc..2cb32aab4f82 100644 --- a/drivers/regulator/da9211-regulator.h +++ b/drivers/regulator/da9211-regulator.h @@ -1,6 +1,6 @@ /* * da9211-regulator.h - Regulator definitions for DA9211/DA9212 - * /DA9213/DA9214/DA9215 + * /DA9213/DA9223/DA9214/DA9224/DA9215/DA9225 * Copyright (C) 2015 Dialog Semiconductor Ltd. * * This program is free software; you can redistribute it and/or diff --git a/include/linux/regulator/da9211.h b/include/linux/regulator/da9211.h index 80cb40b7c88d..f2fd2d3bf58f 100644 --- a/include/linux/regulator/da9211.h +++ b/include/linux/regulator/da9211.h @@ -1,6 +1,6 @@ /* * da9211.h - Regulator device driver for DA9211/DA9212 - * /DA9213/DA9214/DA9215 + * /DA9213/DA9223/DA9214/DA9224/DA9215/DA9225 * Copyright (C) 2015 Dialog Semiconductor Ltd. * * This program is free software; you can redistribute it and/or @@ -25,8 +25,11 @@ enum da9211_chip_id { DA9211, DA9212, DA9213, + DA9223, DA9214, + DA9224, DA9215, + DA9225, }; struct da9211_pdata { -- cgit v1.2.3 From a9903f04e0a4ea522d959c2f287cdf0ab029e324 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Mon, 30 Oct 2017 11:08:16 -0700 Subject: sched/sysctl: Fix attributes of some extern declarations The definition of sysctl_sched_migration_cost, sysctl_sched_nr_migrate and sysctl_sched_time_avg includes the attribute const_debug. This attribute is not part of the extern declaration of these variables in include/linux/sched/sysctl.h, while it is in kernel/sched/sched.h, and as a result Clang generates warnings like this: kernel/sched/sched.h:1618:33: warning: section attribute is specified on redeclared variable [-Wsection] extern const_debug unsigned int sysctl_sched_time_avg; ^ ./include/linux/sched/sysctl.h:42:21: note: previous declaration is here extern unsigned int sysctl_sched_time_avg; The header only declares the variables when CONFIG_SCHED_DEBUG is defined, therefore it is not necessary to duplicate the definition of const_debug. Instead we can use the attribute __read_mostly, which is the expansion of const_debug when CONFIG_SCHED_DEBUG=y is set. Signed-off-by: Matthias Kaehlcke Reviewed-by: Nick Desaulniers Cc: Douglas Anderson Cc: Guenter Roeck Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Shile Zhang Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20171030180816.170850-1-mka@chromium.org Signed-off-by: Ingo Molnar --- include/linux/sched/sysctl.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 0f5ecd4d298e..d34c823f3d36 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -37,9 +37,9 @@ extern unsigned int sysctl_numa_balancing_scan_period_max; extern unsigned int sysctl_numa_balancing_scan_size; #ifdef CONFIG_SCHED_DEBUG -extern unsigned int sysctl_sched_migration_cost; -extern unsigned int sysctl_sched_nr_migrate; -extern unsigned int sysctl_sched_time_avg; +extern __read_mostly unsigned int sysctl_sched_migration_cost; +extern __read_mostly unsigned int sysctl_sched_nr_migrate; +extern __read_mostly unsigned int sysctl_sched_time_avg; int sched_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, -- cgit v1.2.3 From 8698b9364710e7bac84b3af07dd410e39c8c2e08 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Wed, 1 Nov 2017 10:11:55 +0800 Subject: regmap: Add hardware spinlock support On some platforms, when reading or writing some special registers through regmap, we should acquire one hardware spinlock to synchronize between the multiple subsystems. Thus this patch adds the hardware spinlock support for regmap. Signed-off-by: Baolin Wang Signed-off-by: Mark Brown --- drivers/base/regmap/internal.h | 2 + drivers/base/regmap/regmap.c | 101 ++++++++++++++++++++++++++++++++++------- include/linux/regmap.h | 6 +++ 3 files changed, 93 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index 2a4435d76028..8641183cac2f 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -157,6 +157,8 @@ struct regmap { struct rb_root range_tree; void *selector_work_buf; /* Scratch buffer used for selector */ + + struct hwspinlock *hwlock; }; struct regcache_ops { diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index b9a779a4a739..999e981a174a 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -20,6 +20,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include "trace.h" @@ -413,6 +414,49 @@ static unsigned int regmap_parse_64_native(const void *buf) } #endif +static void regmap_lock_hwlock(void *__map) +{ + struct regmap *map = __map; + + hwspin_lock_timeout(map->hwlock, UINT_MAX); +} + +static void regmap_lock_hwlock_irq(void *__map) +{ + struct regmap *map = __map; + + hwspin_lock_timeout_irq(map->hwlock, UINT_MAX); +} + +static void regmap_lock_hwlock_irqsave(void *__map) +{ + struct regmap *map = __map; + + hwspin_lock_timeout_irqsave(map->hwlock, UINT_MAX, + &map->spinlock_flags); +} + +static void regmap_unlock_hwlock(void *__map) +{ + struct regmap *map = __map; + + hwspin_unlock(map->hwlock); +} + +static void regmap_unlock_hwlock_irq(void *__map) +{ + struct regmap *map = __map; + + hwspin_unlock_irq(map->hwlock); +} + +static void regmap_unlock_hwlock_irqrestore(void *__map) +{ + struct regmap *map = __map; + + hwspin_unlock_irqrestore(map->hwlock, &map->spinlock_flags); +} + static void regmap_lock_mutex(void *__map) { struct regmap *map = __map; @@ -627,6 +671,29 @@ struct regmap *__regmap_init(struct device *dev, map->lock = config->lock; map->unlock = config->unlock; map->lock_arg = config->lock_arg; + } else if (config->hwlock_id) { + map->hwlock = hwspin_lock_request_specific(config->hwlock_id); + if (!map->hwlock) { + ret = -ENXIO; + goto err_map; + } + + switch (config->hwlock_mode) { + case HWLOCK_IRQSTATE: + map->lock = regmap_lock_hwlock_irqsave; + map->unlock = regmap_unlock_hwlock_irqrestore; + break; + case HWLOCK_IRQ: + map->lock = regmap_lock_hwlock_irq; + map->unlock = regmap_unlock_hwlock_irq; + break; + default: + map->lock = regmap_lock_hwlock; + map->unlock = regmap_unlock_hwlock; + break; + } + + map->lock_arg = map; } else { if ((bus && bus->fast_io) || config->fast_io) { @@ -729,7 +796,7 @@ struct regmap *__regmap_init(struct device *dev, map->format.format_write = regmap_format_2_6_write; break; default: - goto err_map; + goto err_hwlock; } break; @@ -739,7 +806,7 @@ struct regmap *__regmap_init(struct device *dev, map->format.format_write = regmap_format_4_12_write; break; default: - goto err_map; + goto err_hwlock; } break; @@ -749,7 +816,7 @@ struct regmap *__regmap_init(struct device *dev, map->format.format_write = regmap_format_7_9_write; break; default: - goto err_map; + goto err_hwlock; } break; @@ -759,7 +826,7 @@ struct regmap *__regmap_init(struct device *dev, map->format.format_write = regmap_format_10_14_write; break; default: - goto err_map; + goto err_hwlock; } break; @@ -779,13 +846,13 @@ struct regmap *__regmap_init(struct device *dev, map->format.format_reg = regmap_format_16_native; break; default: - goto err_map; + goto err_hwlock; } break; case 24: if (reg_endian != REGMAP_ENDIAN_BIG) - goto err_map; + goto err_hwlock; map->format.format_reg = regmap_format_24; break; @@ -801,7 +868,7 @@ struct regmap *__regmap_init(struct device *dev, map->format.format_reg = regmap_format_32_native; break; default: - goto err_map; + goto err_hwlock; } break; @@ -818,13 +885,13 @@ struct regmap *__regmap_init(struct device *dev, map->format.format_reg = regmap_format_64_native; break; default: - goto err_map; + goto err_hwlock; } break; #endif default: - goto err_map; + goto err_hwlock; } if (val_endian == REGMAP_ENDIAN_NATIVE) @@ -853,12 +920,12 @@ struct regmap *__regmap_init(struct device *dev, map->format.parse_val = regmap_parse_16_native; break; default: - goto err_map; + goto err_hwlock; } break; case 24: if (val_endian != REGMAP_ENDIAN_BIG) - goto err_map; + goto err_hwlock; map->format.format_val = regmap_format_24; map->format.parse_val = regmap_parse_24; break; @@ -879,7 +946,7 @@ struct regmap *__regmap_init(struct device *dev, map->format.parse_val = regmap_parse_32_native; break; default: - goto err_map; + goto err_hwlock; } break; #ifdef CONFIG_64BIT @@ -900,7 +967,7 @@ struct regmap *__regmap_init(struct device *dev, map->format.parse_val = regmap_parse_64_native; break; default: - goto err_map; + goto err_hwlock; } break; #endif @@ -909,18 +976,18 @@ struct regmap *__regmap_init(struct device *dev, if (map->format.format_write) { if ((reg_endian != REGMAP_ENDIAN_BIG) || (val_endian != REGMAP_ENDIAN_BIG)) - goto err_map; + goto err_hwlock; map->use_single_write = true; } if (!map->format.format_write && !(map->format.format_reg && map->format.format_val)) - goto err_map; + goto err_hwlock; map->work_buf = kzalloc(map->format.buf_size, GFP_KERNEL); if (map->work_buf == NULL) { ret = -ENOMEM; - goto err_map; + goto err_hwlock; } if (map->format.format_write) { @@ -1041,6 +1108,8 @@ err_regcache: err_range: regmap_range_exit(map); kfree(map->work_buf); +err_hwlock: + hwspin_lock_free(map->hwlock); err_map: kfree(map); err: diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 978abfbac617..edc32aac84d7 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -273,6 +273,9 @@ typedef void (*regmap_unlock)(void *); * * @ranges: Array of configuration entries for virtual address ranges. * @num_ranges: Number of range configuration entries. + * @hwlock_id: Specify the hardware spinlock id. + * @hwlock_mode: The hardware spinlock mode, should be HWLOCK_IRQSTATE, + * HWLOCK_IRQ or 0. */ struct regmap_config { const char *name; @@ -317,6 +320,9 @@ struct regmap_config { const struct regmap_range_cfg *ranges; unsigned int num_ranges; + + unsigned int hwlock_id; + unsigned int hwlock_mode; }; /** -- cgit v1.2.3 From 00ed87da35e88a7a4d7f41673beab52ef828f12b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 1 Nov 2017 07:32:50 -0700 Subject: timer: Add parenthesis around timer_setup() macro arguments In the case where expressions are passed as macro arguments, the LOCKDEP version of the timer macros need enclosing parenthesis. Reported-by: Stephen Rothwell Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20171101143250.GA65266@beast --- include/linux/timer.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index 09950482309b..a1af92bac0d5 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -173,11 +173,12 @@ static inline void timer_setup_on_stack(struct timer_list *timer, * do want to keep the inline for argument type checking, though. */ # define timer_setup(timer, callback, flags) \ - __setup_timer(timer, (TIMER_FUNC_TYPE)callback, \ - (TIMER_DATA_TYPE)timer, flags) + __setup_timer((timer), (TIMER_FUNC_TYPE)(callback), \ + (TIMER_DATA_TYPE)(timer), (flags)) # define timer_setup_on_stack(timer, callback, flags) \ - __setup_timer_on_stack(timer, (TIMER_FUNC_TYPE)callback,\ - (TIMER_DATA_TYPE)timer, flags) + __setup_timer_on_stack((timer), \ + (TIMER_FUNC_TYPE)(callback), \ + (TIMER_DATA_TYPE)(timer), (flags)) #endif #define from_timer(var, callback_timer, timer_fieldname) \ -- cgit v1.2.3 From 1943dc07b45e347c52c1bfdd4a37e04a86e399aa Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 2 Nov 2017 13:30:03 +0100 Subject: bitops: Revert cbe96375025e ("bitops: Add clear/set_bit32() to linux/bitops.h") These ops are not endian safe and may break on architectures which have aligment requirements. Reverts: cbe96375025e ("bitops: Add clear/set_bit32() to linux/bitops.h") Reported-by: Peter Zijlstra Signed-off-by: Thomas Gleixner Cc: Andi Kleen --- include/linux/bitops.h | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 36794f058ba6..8fbe259b197c 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -227,32 +227,6 @@ static inline unsigned long __ffs64(u64 word) return __ffs((unsigned long)word); } -/* - * clear_bit32 - Clear a bit in memory for u32 array - * @nr: Bit to clear - * @addr: u32 * address of bitmap - * - * Same as clear_bit, but avoids needing casts for u32 arrays. - */ - -static __always_inline void clear_bit32(long nr, volatile u32 *addr) -{ - clear_bit(nr, (volatile unsigned long *)addr); -} - -/* - * set_bit32 - Set a bit in memory for u32 array - * @nr: Bit to clear - * @addr: u32 * address of bitmap - * - * Same as set_bit, but avoids needing casts for u32 arrays. - */ - -static __always_inline void set_bit32(long nr, volatile u32 *addr) -{ - set_bit(nr, (volatile unsigned long *)addr); -} - #ifdef __KERNEL__ #ifndef set_mask_bits -- cgit v1.2.3 From d4d7b4ad2f05c03fb25252aea66f9f3cd7cfbe06 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 26 Oct 2017 10:44:07 +0100 Subject: irqchip/gic-v3-its: Setup VLPI properties at map time So far, we require the hypervisor to update the VLPI properties once the the VLPI mapping has been established. While this makes it easy for the ITS driver, it creates a window where an incoming interrupt can be delivered with an unknown set of properties. Not very nice. Instead, let's add a "properties" field to the mapping structure, and use that to configure the VLPI before it actually gets mapped. Reviewed-by: Christoffer Dall Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 18 ++++++++++++++++-- include/linux/irqchip/arm-gic-v4.h | 2 ++ 2 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 6a74f0497f82..29b2ff5c6841 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1008,9 +1008,15 @@ static void lpi_write_config(struct irq_data *d, u8 clr, u8 set) if (irqd_is_forwarded_to_vcpu(d)) { struct its_device *its_dev = irq_data_get_irq_chip_data(d); u32 event = its_get_event_id(d); + struct its_vlpi_map *map; prop_page = its_dev->event_map.vm->vprop_page; - hwirq = its_dev->event_map.vlpi_maps[event].vintid; + map = &its_dev->event_map.vlpi_maps[event]; + hwirq = map->vintid; + + /* Remember the updated property */ + map->properties &= ~clr; + map->properties |= set | LPI_PROP_GROUP1; } else { prop_page = gic_rdists->prop_page; hwirq = d->hwirq; @@ -1249,12 +1255,20 @@ static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info) /* Ensure all the VPEs are mapped on this ITS */ its_map_vm(its_dev->its, info->map->vm); + /* + * Flag the interrupt as forwarded so that we can + * start poking the virtual property table. + */ + irqd_set_forwarded_to_vcpu(d); + + /* Write out the property to the prop table */ + lpi_write_config(d, 0xff, info->map->properties); + /* Drop the physical mapping */ its_send_discard(its_dev, event); /* and install the virtual one */ its_send_vmapti(its_dev, event); - irqd_set_forwarded_to_vcpu(d); /* Increment the number of VLPIs */ its_dev->event_map.nr_vlpis++; diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index 43cde15f221b..447da8ca2156 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -71,12 +71,14 @@ struct its_vpe { * @vm: Pointer to the GICv4 notion of a VM * @vpe: Pointer to the GICv4 notion of a virtual CPU (VPE) * @vintid: Virtual LPI number + * @properties: Priority and enable bits (as written in the prop table) * @db_enabled: Is the VPE doorbell to be generated? */ struct its_vlpi_map { struct its_vm *vm; struct its_vpe *vpe; u32 vintid; + u8 properties; bool db_enabled; }; -- cgit v1.2.3 From 4b82130077d93539c9fbb0f5eee21965cea9cfe9 Mon Sep 17 00:00:00 2001 From: Dou Liyang Date: Mon, 30 Oct 2017 10:15:00 +0800 Subject: irqdomain: Update the comments of fwnode field of irq_domain structure Commit: f110711a6053 ("irqdomain: Convert irqdomain-%3Eof_node to fwnode") converted of_node field to fwnode, but didn't update its comments. Update it. Fixes: f110711a6053 ("irqdomain: Convert irqdomain-%3Eof_node to fwnode") Signed-off-by: Dou Liyang Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index df162f7a4aad..ce48a23d621f 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -138,8 +138,8 @@ struct irq_domain_chip_generic; * @mapcount: The number of mapped interrupts * * Optional elements - * @of_node: Pointer to device tree nodes associated with the irq_domain. Used - * when decoding device tree interrupt specifiers. + * @fwnode: Pointer to firmware node associated with the irq_domain. Pretty easy + * to swap it for the of_node via the irq_domain_get_of_node accessor * @gc: Pointer to a list of generic chips. There is a helper function for * setting up one or more generic chips for interrupt controllers * drivers using the generic chip library which uses this pointer. -- cgit v1.2.3 From da61fcf9d62a05f3508f5646d353a9c2604bac76 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Tue, 31 Oct 2017 09:41:45 -0700 Subject: irqchip: mips-gic: Use irq_cpu_online to (un)mask all-VP(E) IRQs The gic_all_vpes_local_irq_controller chip currently attempts to operate on all CPUs/VPs in the system when masking or unmasking an interrupt. This has a few drawbacks: - In multi-cluster systems we may not always have access to all CPUs in the system. When all CPUs in a cluster are powered down that cluster's GIC may also power down, in which case we cannot configure its state. - Relatedly, if we power down a cluster after having configured interrupts for CPUs within it then the cluster's GIC may lose state & we need to reconfigure it. The current approach doesn't take this into account. - It's wasteful if we run Linux on fewer VPs than are present in the system. For example if we run a uniprocessor kernel on CPU0 of a system with 16 CPUs then there's no point in us configuring CPUs 1-15. - The implementation is also lacking in that it expects the range 0..gic_vpes-1 to represent valid Linux CPU numbers which may not always be the case - for example if we run on a system with more VPs than the kernel is configured to support. Fix all of these issues by only configuring the affected interrupts for CPUs which are online at the time, and recording the configuration in a new struct gic_all_vpes_chip_data for later use by CPUs being brought online. We register a CPU hotplug state (reusing CPUHP_AP_IRQ_GIC_STARTING which the ARM GIC driver uses, and which seems suitably generic for reuse with the MIPS GIC) and execute irq_cpu_online() in order to configure the interrupts on the newly onlined CPU. Signed-off-by: Paul Burton Cc: Jason Cooper Cc: Marc Zyngier Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-mips-gic.c | 72 ++++++++++++++++++++++++++++++++---------- include/linux/cpuhotplug.h | 1 + 2 files changed, 57 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 6fdcc1552fab..60f644279803 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -8,6 +8,7 @@ */ #include #include +#include #include #include #include @@ -55,6 +56,11 @@ static struct irq_chip gic_level_irq_controller, gic_edge_irq_controller; DECLARE_BITMAP(ipi_resrv, GIC_MAX_INTRS); DECLARE_BITMAP(ipi_available, GIC_MAX_INTRS); +static struct gic_all_vpes_chip_data { + u32 map; + bool mask; +} gic_all_vpes_chip_data[GIC_NUM_LOCAL_INTRS]; + static void gic_clear_pcpu_masks(unsigned int intr) { unsigned int i; @@ -338,13 +344,17 @@ static struct irq_chip gic_local_irq_controller = { static void gic_mask_local_irq_all_vpes(struct irq_data *d) { - int intr = GIC_HWIRQ_TO_LOCAL(d->hwirq); - int i; + struct gic_all_vpes_chip_data *cd; unsigned long flags; + int intr, cpu; + + intr = GIC_HWIRQ_TO_LOCAL(d->hwirq); + cd = irq_data_get_irq_chip_data(d); + cd->mask = false; spin_lock_irqsave(&gic_lock, flags); - for (i = 0; i < gic_vpes; i++) { - write_gic_vl_other(mips_cm_vp_id(i)); + for_each_online_cpu(cpu) { + write_gic_vl_other(mips_cm_vp_id(cpu)); write_gic_vo_rmask(BIT(intr)); } spin_unlock_irqrestore(&gic_lock, flags); @@ -352,22 +362,40 @@ static void gic_mask_local_irq_all_vpes(struct irq_data *d) static void gic_unmask_local_irq_all_vpes(struct irq_data *d) { - int intr = GIC_HWIRQ_TO_LOCAL(d->hwirq); - int i; + struct gic_all_vpes_chip_data *cd; unsigned long flags; + int intr, cpu; + + intr = GIC_HWIRQ_TO_LOCAL(d->hwirq); + cd = irq_data_get_irq_chip_data(d); + cd->mask = true; spin_lock_irqsave(&gic_lock, flags); - for (i = 0; i < gic_vpes; i++) { - write_gic_vl_other(mips_cm_vp_id(i)); + for_each_online_cpu(cpu) { + write_gic_vl_other(mips_cm_vp_id(cpu)); write_gic_vo_smask(BIT(intr)); } spin_unlock_irqrestore(&gic_lock, flags); } +static void gic_all_vpes_irq_cpu_online(struct irq_data *d) +{ + struct gic_all_vpes_chip_data *cd; + unsigned int intr; + + intr = GIC_HWIRQ_TO_LOCAL(d->hwirq); + cd = irq_data_get_irq_chip_data(d); + + write_gic_vl_map(intr, cd->map); + if (cd->mask) + write_gic_vl_smask(BIT(intr)); +} + static struct irq_chip gic_all_vpes_local_irq_controller = { - .name = "MIPS GIC Local", - .irq_mask = gic_mask_local_irq_all_vpes, - .irq_unmask = gic_unmask_local_irq_all_vpes, + .name = "MIPS GIC Local", + .irq_mask = gic_mask_local_irq_all_vpes, + .irq_unmask = gic_unmask_local_irq_all_vpes, + .irq_cpu_online = gic_all_vpes_irq_cpu_online, }; static void __gic_irq_dispatch(void) @@ -424,9 +452,10 @@ static int gic_irq_domain_xlate(struct irq_domain *d, struct device_node *ctrlr, static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hwirq) { + struct gic_all_vpes_chip_data *cd; unsigned long flags; unsigned int intr; - int err, i; + int err, cpu; u32 map; if (hwirq >= GIC_SHARED_HWIRQ_BASE) { @@ -459,9 +488,11 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, * the rest of the MIPS kernel code does not use the * percpu IRQ API for them. */ + cd = &gic_all_vpes_chip_data[intr]; + cd->map = map; err = irq_domain_set_hwirq_and_chip(d, virq, hwirq, &gic_all_vpes_local_irq_controller, - NULL); + cd); if (err) return err; @@ -484,8 +515,8 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, return -EPERM; spin_lock_irqsave(&gic_lock, flags); - for (i = 0; i < gic_vpes; i++) { - write_gic_vl_other(mips_cm_vp_id(i)); + for_each_online_cpu(cpu) { + write_gic_vl_other(mips_cm_vp_id(cpu)); write_gic_vo_map(intr, map); } spin_unlock_irqrestore(&gic_lock, flags); @@ -622,6 +653,13 @@ static const struct irq_domain_ops gic_ipi_domain_ops = { .match = gic_ipi_domain_match, }; +static int gic_cpu_startup(unsigned int cpu) +{ + /* Invoke irq_cpu_online callbacks to enable desired interrupts */ + irq_cpu_online(); + + return 0; +} static int __init gic_of_init(struct device_node *node, struct device_node *parent) @@ -768,6 +806,8 @@ static int __init gic_of_init(struct device_node *node, } } - return 0; + return cpuhp_setup_state(CPUHP_AP_IRQ_MIPS_GIC_STARTING, + "irqchip/mips/gic:starting", + gic_cpu_startup, NULL); } IRQCHIP_DECLARE(mips_gic, "mti,gic", gic_of_init); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 6d508767e144..1966a45bc453 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -98,6 +98,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_HIP04_STARTING, CPUHP_AP_IRQ_ARMADA_XP_STARTING, CPUHP_AP_IRQ_BCM2836_STARTING, + CPUHP_AP_IRQ_MIPS_GIC_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, CPUHP_AP_PERF_X86_STARTING, -- cgit v1.2.3 From ec7ed7708e009e046d1e16ed53ba4d6048748d07 Mon Sep 17 00:00:00 2001 From: Angelo Dureghello Date: Sat, 28 Oct 2017 00:23:01 +0200 Subject: spi: spi-fsl-dspi: enabling Coldfire mcf5441x dspi Signed-off-by: Angelo Dureghello Signed-off-by: Mark Brown --- drivers/spi/Kconfig | 2 +- drivers/spi/spi-fsl-dspi.c | 66 +++++++++++++++++++++++++++------------- include/linux/spi/spi-fsl-dspi.h | 31 +++++++++++++++++++ 3 files changed, 77 insertions(+), 22 deletions(-) create mode 100644 include/linux/spi/spi-fsl-dspi.h (limited to 'include/linux') diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index a75f2a2cf780..a8b761979673 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -379,7 +379,7 @@ config SPI_FSL_DSPI tristate "Freescale DSPI controller" select REGMAP_MMIO depends on HAS_DMA - depends on SOC_VF610 || SOC_LS1021A || ARCH_LAYERSCAPE || COMPILE_TEST + depends on SOC_VF610 || SOC_LS1021A || ARCH_LAYERSCAPE || M5441x || COMPILE_TEST help This enables support for the Freescale DSPI controller in master mode. VF610 platform uses the controller. diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index d89127f4a46d..f652f70cb8db 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include @@ -151,6 +152,11 @@ static const struct fsl_dspi_devtype_data ls2085a_data = { .max_clock_factor = 8, }; +static const struct fsl_dspi_devtype_data coldfire_data = { + .trans_mode = DSPI_EOQ_MODE, + .max_clock_factor = 8, +}; + struct fsl_dspi_dma { /* Length of transfer in words of DSPI_FIFO_SIZE */ u32 curr_xfer_len; @@ -741,6 +747,7 @@ static int dspi_setup(struct spi_device *spi) { struct chip_data *chip; struct fsl_dspi *dspi = spi_master_get_devdata(spi->master); + struct fsl_dspi_platform_data *pdata; u32 cs_sck_delay = 0, sck_cs_delay = 0; unsigned char br = 0, pbr = 0, pcssck = 0, cssck = 0; unsigned char pasc = 0, asc = 0, fmsz = 0; @@ -761,11 +768,18 @@ static int dspi_setup(struct spi_device *spi) return -ENOMEM; } - of_property_read_u32(spi->dev.of_node, "fsl,spi-cs-sck-delay", - &cs_sck_delay); + pdata = dev_get_platdata(&dspi->pdev->dev); - of_property_read_u32(spi->dev.of_node, "fsl,spi-sck-cs-delay", - &sck_cs_delay); + if (!pdata) { + of_property_read_u32(spi->dev.of_node, "fsl,spi-cs-sck-delay", + &cs_sck_delay); + + of_property_read_u32(spi->dev.of_node, "fsl,spi-sck-cs-delay", + &sck_cs_delay); + } else { + cs_sck_delay = pdata->cs_sck_delay; + sck_cs_delay = pdata->sck_cs_delay; + } chip->mcr_val = SPI_MCR_MASTER | SPI_MCR_PCSIS | SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF; @@ -949,6 +963,7 @@ static int dspi_probe(struct platform_device *pdev) struct fsl_dspi *dspi; struct resource *res; void __iomem *base; + struct fsl_dspi_platform_data *pdata; int ret = 0, cs_num, bus_num; master = spi_alloc_master(&pdev->dev, sizeof(struct fsl_dspi)); @@ -969,25 +984,34 @@ static int dspi_probe(struct platform_device *pdev) master->bits_per_word_mask = SPI_BPW_MASK(4) | SPI_BPW_MASK(8) | SPI_BPW_MASK(16); - ret = of_property_read_u32(np, "spi-num-chipselects", &cs_num); - if (ret < 0) { - dev_err(&pdev->dev, "can't get spi-num-chipselects\n"); - goto out_master_put; - } - master->num_chipselect = cs_num; + pdata = dev_get_platdata(&pdev->dev); + if (pdata) { + master->num_chipselect = pdata->cs_num; + master->bus_num = pdata->bus_num; - ret = of_property_read_u32(np, "bus-num", &bus_num); - if (ret < 0) { - dev_err(&pdev->dev, "can't get bus-num\n"); - goto out_master_put; - } - master->bus_num = bus_num; + dspi->devtype_data = &coldfire_data; + } else { - dspi->devtype_data = of_device_get_match_data(&pdev->dev); - if (!dspi->devtype_data) { - dev_err(&pdev->dev, "can't get devtype_data\n"); - ret = -EFAULT; - goto out_master_put; + ret = of_property_read_u32(np, "spi-num-chipselects", &cs_num); + if (ret < 0) { + dev_err(&pdev->dev, "can't get spi-num-chipselects\n"); + goto out_master_put; + } + master->num_chipselect = cs_num; + + ret = of_property_read_u32(np, "bus-num", &bus_num); + if (ret < 0) { + dev_err(&pdev->dev, "can't get bus-num\n"); + goto out_master_put; + } + master->bus_num = bus_num; + + dspi->devtype_data = of_device_get_match_data(&pdev->dev); + if (!dspi->devtype_data) { + dev_err(&pdev->dev, "can't get devtype_data\n"); + ret = -EFAULT; + goto out_master_put; + } } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); diff --git a/include/linux/spi/spi-fsl-dspi.h b/include/linux/spi/spi-fsl-dspi.h new file mode 100644 index 000000000000..74c9bae20bf2 --- /dev/null +++ b/include/linux/spi/spi-fsl-dspi.h @@ -0,0 +1,31 @@ +/* + * Freescale DSPI controller driver + * + * Copyright (c) 2017 Angelo Dureghello + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * 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. + */ + +#ifndef SPI_FSL_DSPI_HEADER_H +#define SPI_FSL_DSPI_HEADER_H + +/** + * struct fsl_dspi_platform_data - platform data for the Freescale DSPI driver + * @bus_num: board specific identifier for this DSPI driver. + * @cs_num: number of chip selects supported by this DSPI driver. + */ +struct fsl_dspi_platform_data { + u32 cs_num; + u32 bus_num; + u32 sck_cs_delay; + u32 cs_sck_delay; +}; + +#endif /* SPI_FSL_DSPI_HEADER_H */ -- cgit v1.2.3 From 10738ba8e02bc8cb1c4e832611621aa9666f4a24 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 17 Oct 2017 21:06:32 -0700 Subject: ide: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: "David S. Miller" Cc: linux-ide@vger.kernel.org Signed-off-by: Kees Cook --- drivers/ide/ide-io.c | 4 ++-- drivers/ide/ide-probe.c | 2 +- include/linux/ide.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 3a234701d92c..6f25da56a169 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -611,9 +611,9 @@ static int drive_is_ready(ide_drive_t *drive) * logic that wants cleaning up. */ -void ide_timer_expiry (unsigned long data) +void ide_timer_expiry (struct timer_list *t) { - ide_hwif_t *hwif = (ide_hwif_t *)data; + ide_hwif_t *hwif = from_timer(hwif, t, timer); ide_drive_t *uninitialized_var(drive); ide_handler_t *handler; unsigned long flags; diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 01b2adfd8226..27a2488c7468 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -1184,7 +1184,7 @@ static void ide_init_port_data(ide_hwif_t *hwif, unsigned int index) spin_lock_init(&hwif->lock); - setup_timer(&hwif->timer, &ide_timer_expiry, (unsigned long)hwif); + timer_setup(&hwif->timer, ide_timer_expiry, 0); init_completion(&hwif->gendev_rel_comp); diff --git a/include/linux/ide.h b/include/linux/ide.h index dc152e4b7f73..cc412175d036 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1211,7 +1211,7 @@ extern int ide_wait_not_busy(ide_hwif_t *hwif, unsigned long timeout); extern void ide_stall_queue(ide_drive_t *drive, unsigned long timeout); -extern void ide_timer_expiry(unsigned long); +extern void ide_timer_expiry(struct timer_list *t); extern irqreturn_t ide_intr(int irq, void *dev_id); extern void do_ide_request(struct request_queue *); extern void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq); -- cgit v1.2.3 From f791dd2589d7e217625d7e411621a5bac71cbf69 Mon Sep 17 00:00:00 2001 From: Cheng Jian Date: Fri, 3 Nov 2017 18:59:48 +0800 Subject: locking/rwlocks: Fix comments - fix the list of locking API headers in kernel/locking/spinlock.c - fix an #endif comment Signed-off-by: Cheng Jian Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: huawei.libin@huawei.com Cc: xiexiuqi@huawei.com Link: http://lkml.kernel.org/r/1509706788-152547-1-git-send-email-cj.chengjian@huawei.com Signed-off-by: Ingo Molnar --- include/linux/rwlock_api_smp.h | 2 +- kernel/locking/spinlock.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h index 5b9b84b20407..86ebb4bf9c6e 100644 --- a/include/linux/rwlock_api_smp.h +++ b/include/linux/rwlock_api_smp.h @@ -211,7 +211,7 @@ static inline void __raw_write_lock(rwlock_t *lock) LOCK_CONTENDED(lock, do_raw_write_trylock, do_raw_write_lock); } -#endif /* CONFIG_PREEMPT */ +#endif /* !CONFIG_GENERIC_LOCKBREAK || CONFIG_DEBUG_LOCK_ALLOC */ static inline void __raw_write_unlock(rwlock_t *lock) { diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index b96343374a87..1fd1a7543cdd 100644 --- a/kernel/locking/spinlock.c +++ b/kernel/locking/spinlock.c @@ -30,7 +30,8 @@ #if !defined(CONFIG_GENERIC_LOCKBREAK) || defined(CONFIG_DEBUG_LOCK_ALLOC) /* * The __lock_function inlines are taken from - * include/linux/spinlock_api_smp.h + * spinlock : include/linux/spinlock_api_smp.h + * rwlock : include/linux/rwlock_api_smp.h */ #else -- cgit v1.2.3 From d8aa7eea78a1401cce39b3bb61ead0150044a3df Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Fri, 20 Oct 2017 09:30:44 -0500 Subject: x86/mm: Add Secure Encrypted Virtualization (SEV) support Provide support for Secure Encrypted Virtualization (SEV). This initial support defines a flag that is used by the kernel to determine if it is running with SEV active. Signed-off-by: Tom Lendacky Signed-off-by: Brijesh Singh Signed-off-by: Thomas Gleixner Reviewed-by: Borislav Petkov Tested-by: Borislav Petkov Cc: kvm@vger.kernel.org Cc: Borislav Petkov Cc: Andy Lutomirski Link: https://lkml.kernel.org/r/20171020143059.3291-3-brijesh.singh@amd.com --- arch/x86/include/asm/mem_encrypt.h | 6 ++++++ arch/x86/mm/mem_encrypt.c | 26 ++++++++++++++++++++++++++ include/linux/mem_encrypt.h | 7 +++++-- 3 files changed, 37 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 6a77c63540f7..2b024741bce9 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -47,6 +47,9 @@ void __init mem_encrypt_init(void); void swiotlb_set_mem_attributes(void *vaddr, unsigned long size); +bool sme_active(void); +bool sev_active(void); + #else /* !CONFIG_AMD_MEM_ENCRYPT */ #define sme_me_mask 0ULL @@ -64,6 +67,9 @@ static inline void __init sme_early_init(void) { } static inline void __init sme_encrypt_kernel(void) { } static inline void __init sme_enable(struct boot_params *bp) { } +static inline bool sme_active(void) { return false; } +static inline bool sev_active(void) { return false; } + #endif /* CONFIG_AMD_MEM_ENCRYPT */ /* diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 16c5f37933a2..add836d3d174 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -42,6 +42,8 @@ static char sme_cmdline_off[] __initdata = "off"; u64 sme_me_mask __section(.data) = 0; EXPORT_SYMBOL_GPL(sme_me_mask); +static bool sev_enabled __section(.data); + /* Buffer used for early in-place encryption by BSP, no locking needed */ static char sme_early_buffer[PAGE_SIZE] __aligned(PAGE_SIZE); @@ -192,6 +194,30 @@ void __init sme_early_init(void) protection_map[i] = pgprot_encrypted(protection_map[i]); } +/* + * SME and SEV are very similar but they are not the same, so there are + * times that the kernel will need to distinguish between SME and SEV. The + * sme_active() and sev_active() functions are used for this. When a + * distinction isn't needed, the mem_encrypt_active() function can be used. + * + * The trampoline code is a good example for this requirement. Before + * paging is activated, SME will access all memory as decrypted, but SEV + * will access all memory as encrypted. So, when APs are being brought + * up under SME the trampoline area cannot be encrypted, whereas under SEV + * the trampoline area must be encrypted. + */ +bool sme_active(void) +{ + return sme_me_mask && !sev_enabled; +} +EXPORT_SYMBOL_GPL(sme_active); + +bool sev_active(void) +{ + return sme_me_mask && sev_enabled; +} +EXPORT_SYMBOL_GPL(sev_active); + /* Architecture __weak replacement functions */ void __init mem_encrypt_init(void) { diff --git a/include/linux/mem_encrypt.h b/include/linux/mem_encrypt.h index 265a9cd21cb4..b310a9c18113 100644 --- a/include/linux/mem_encrypt.h +++ b/include/linux/mem_encrypt.h @@ -23,11 +23,14 @@ #define sme_me_mask 0ULL +static inline bool sme_active(void) { return false; } +static inline bool sev_active(void) { return false; } + #endif /* CONFIG_ARCH_HAS_MEM_ENCRYPT */ -static inline bool sme_active(void) +static inline bool mem_encrypt_active(void) { - return !!sme_me_mask; + return sme_me_mask; } static inline u64 sme_get_me_mask(void) -- cgit v1.2.3 From 1d2e733b13b450e5854f4a8f8efcd77fa7362d62 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Fri, 20 Oct 2017 09:30:51 -0500 Subject: resource: Provide resource struct in resource walk callback In preperation for a new function that will need additional resource information during the resource walk, update the resource walk callback to pass the resource structure. Since the current callback start and end arguments are pulled from the resource structure, the callback functions can obtain them from the resource structure directly. Signed-off-by: Tom Lendacky Signed-off-by: Brijesh Singh Signed-off-by: Thomas Gleixner Reviewed-by: Kees Cook Reviewed-by: Borislav Petkov Tested-by: Borislav Petkov Cc: kvm@vger.kernel.org Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: linuxppc-dev@lists.ozlabs.org Link: https://lkml.kernel.org/r/20171020143059.3291-10-brijesh.singh@amd.com --- arch/powerpc/kernel/machine_kexec_file_64.c | 12 +++++++++--- arch/x86/kernel/crash.c | 18 +++++++++--------- arch/x86/kernel/pmem.c | 2 +- include/linux/ioport.h | 4 ++-- include/linux/kexec.h | 2 +- kernel/kexec_file.c | 5 +++-- kernel/resource.c | 9 +++++---- 7 files changed, 30 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kernel/machine_kexec_file_64.c b/arch/powerpc/kernel/machine_kexec_file_64.c index 992c0d258e5d..e4395f937d63 100644 --- a/arch/powerpc/kernel/machine_kexec_file_64.c +++ b/arch/powerpc/kernel/machine_kexec_file_64.c @@ -91,11 +91,13 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image) * and that value will be returned. If all free regions are visited without * func returning non-zero, then zero will be returned. */ -int arch_kexec_walk_mem(struct kexec_buf *kbuf, int (*func)(u64, u64, void *)) +int arch_kexec_walk_mem(struct kexec_buf *kbuf, + int (*func)(struct resource *, void *)) { int ret = 0; u64 i; phys_addr_t mstart, mend; + struct resource res = { }; if (kbuf->top_down) { for_each_free_mem_range_reverse(i, NUMA_NO_NODE, 0, @@ -105,7 +107,9 @@ int arch_kexec_walk_mem(struct kexec_buf *kbuf, int (*func)(u64, u64, void *)) * range while in kexec, end points to the last byte * in the range. */ - ret = func(mstart, mend - 1, kbuf); + res.start = mstart; + res.end = mend - 1; + ret = func(&res, kbuf); if (ret) break; } @@ -117,7 +121,9 @@ int arch_kexec_walk_mem(struct kexec_buf *kbuf, int (*func)(u64, u64, void *)) * range while in kexec, end points to the last byte * in the range. */ - ret = func(mstart, mend - 1, kbuf); + res.start = mstart; + res.end = mend - 1; + ret = func(&res, kbuf); if (ret) break; } diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 44404e2307bb..815008c9ca18 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -209,7 +209,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs) } #ifdef CONFIG_KEXEC_FILE -static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg) +static int get_nr_ram_ranges_callback(struct resource *res, void *arg) { unsigned int *nr_ranges = arg; @@ -342,7 +342,7 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced, return ret; } -static int prepare_elf64_ram_headers_callback(u64 start, u64 end, void *arg) +static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) { struct crash_elf_data *ced = arg; Elf64_Ehdr *ehdr; @@ -355,7 +355,7 @@ static int prepare_elf64_ram_headers_callback(u64 start, u64 end, void *arg) ehdr = ced->ehdr; /* Exclude unwanted mem ranges */ - ret = elf_header_exclude_ranges(ced, start, end); + ret = elf_header_exclude_ranges(ced, res->start, res->end); if (ret) return ret; @@ -518,14 +518,14 @@ static int add_e820_entry(struct boot_params *params, struct e820_entry *entry) return 0; } -static int memmap_entry_callback(u64 start, u64 end, void *arg) +static int memmap_entry_callback(struct resource *res, void *arg) { struct crash_memmap_data *cmd = arg; struct boot_params *params = cmd->params; struct e820_entry ei; - ei.addr = start; - ei.size = end - start + 1; + ei.addr = res->start; + ei.size = res->end - res->start + 1; ei.type = cmd->type; add_e820_entry(params, &ei); @@ -619,12 +619,12 @@ out: return ret; } -static int determine_backup_region(u64 start, u64 end, void *arg) +static int determine_backup_region(struct resource *res, void *arg) { struct kimage *image = arg; - image->arch.backup_src_start = start; - image->arch.backup_src_sz = end - start + 1; + image->arch.backup_src_start = res->start; + image->arch.backup_src_sz = res->end - res->start + 1; /* Expecting only one range for backup region */ return 1; diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c index 3fe690067802..6b07faaa1579 100644 --- a/arch/x86/kernel/pmem.c +++ b/arch/x86/kernel/pmem.c @@ -7,7 +7,7 @@ #include #include -static int found(u64 start, u64 end, void *data) +static int found(struct resource *res, void *data) { return 1; } diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 83c8d6530f0f..c0070d7c4b99 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -272,10 +272,10 @@ walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, void *arg, int (*func)(unsigned long, unsigned long, void *)); extern int walk_system_ram_res(u64 start, u64 end, void *arg, - int (*func)(u64, u64, void *)); + int (*func)(struct resource *, void *)); extern int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end, - void *arg, int (*func)(u64, u64, void *)); + void *arg, int (*func)(struct resource *, void *)); /* True if any part of r1 overlaps r2 */ static inline bool resource_overlaps(struct resource *r1, struct resource *r2) diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 1c08c925cefb..f16f6ceb3875 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -160,7 +160,7 @@ struct kexec_buf { }; int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf, - int (*func)(u64, u64, void *)); + int (*func)(struct resource *, void *)); extern int kexec_add_buffer(struct kexec_buf *kbuf); int kexec_locate_mem_hole(struct kexec_buf *kbuf); #endif /* CONFIG_KEXEC_FILE */ diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 9f48f4412297..e5bcd94c1efb 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -406,9 +406,10 @@ static int locate_mem_hole_bottom_up(unsigned long start, unsigned long end, return 1; } -static int locate_mem_hole_callback(u64 start, u64 end, void *arg) +static int locate_mem_hole_callback(struct resource *res, void *arg) { struct kexec_buf *kbuf = (struct kexec_buf *)arg; + u64 start = res->start, end = res->end; unsigned long sz = end - start + 1; /* Returning 0 will take to next memory range */ @@ -437,7 +438,7 @@ static int locate_mem_hole_callback(u64 start, u64 end, void *arg) * func returning non-zero, then zero will be returned. */ int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf, - int (*func)(u64, u64, void *)) + int (*func)(struct resource *, void *)) { if (kbuf->image->type == KEXEC_TYPE_CRASH) return walk_iomem_res_desc(crashk_res.desc, diff --git a/kernel/resource.c b/kernel/resource.c index 7323c1b636cd..8430042fa77b 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -402,14 +402,15 @@ static int find_next_iomem_res(struct resource *res, unsigned long desc, static int __walk_iomem_res_desc(struct resource *res, unsigned long desc, bool first_level_children_only, - void *arg, int (*func)(u64, u64, void *)) + void *arg, + int (*func)(struct resource *, void *)) { u64 orig_end = res->end; int ret = -1; while ((res->start < res->end) && !find_next_iomem_res(res, desc, first_level_children_only)) { - ret = (*func)(res->start, res->end, arg); + ret = (*func)(res, arg); if (ret) break; @@ -435,7 +436,7 @@ static int __walk_iomem_res_desc(struct resource *res, unsigned long desc, * and set it in 'desc' of a target resource entry. */ int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, - u64 end, void *arg, int (*func)(u64, u64, void *)) + u64 end, void *arg, int (*func)(struct resource *, void *)) { struct resource res; @@ -454,7 +455,7 @@ int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, * ranges. */ int walk_system_ram_res(u64 start, u64 end, void *arg, - int (*func)(u64, u64, void *)) + int (*func)(struct resource *, void *)) { struct resource res; -- cgit v1.2.3 From 0e4c12b45aa88e74fdda117896d2b61c4e510cb9 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Fri, 20 Oct 2017 09:30:52 -0500 Subject: x86/mm, resource: Use PAGE_KERNEL protection for ioremap of memory pages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order for memory pages to be properly mapped when SEV is active, it's necessary to use the PAGE_KERNEL protection attribute as the base protection. This ensures that memory mapping of, e.g. ACPI tables, receives the proper mapping attributes. Signed-off-by: Tom Lendacky Signed-off-by: Brijesh Singh Signed-off-by: Thomas Gleixner Reviewed-by: Borislav Petkov Tested-by: Borislav Petkov Cc: Laura Abbott Cc: Kees Cook Cc: kvm@vger.kernel.org Cc: Jérôme Glisse Cc: Borislav Petkov Cc: Andy Lutomirski Cc: Andrew Morton Cc: Dan Williams Cc: "Kirill A. Shutemov" Link: https://lkml.kernel.org/r/20171020143059.3291-11-brijesh.singh@amd.com --- arch/x86/mm/ioremap.c | 79 ++++++++++++++++++++++++++++++++++++++++++-------- include/linux/ioport.h | 3 ++ kernel/resource.c | 19 ++++++++++++ 3 files changed, 89 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 52cc0f4ed494..6e4573b1da34 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -27,6 +27,11 @@ #include "physaddr.h" +struct ioremap_mem_flags { + bool system_ram; + bool desc_other; +}; + /* * Fix up the linear direct mapping of the kernel to avoid cache attribute * conflicts. @@ -56,17 +61,59 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size, return err; } -static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages, - void *arg) +static bool __ioremap_check_ram(struct resource *res) { + unsigned long start_pfn, stop_pfn; unsigned long i; - for (i = 0; i < nr_pages; ++i) - if (pfn_valid(start_pfn + i) && - !PageReserved(pfn_to_page(start_pfn + i))) - return 1; + if ((res->flags & IORESOURCE_SYSTEM_RAM) != IORESOURCE_SYSTEM_RAM) + return false; - return 0; + start_pfn = (res->start + PAGE_SIZE - 1) >> PAGE_SHIFT; + stop_pfn = (res->end + 1) >> PAGE_SHIFT; + if (stop_pfn > start_pfn) { + for (i = 0; i < (stop_pfn - start_pfn); ++i) + if (pfn_valid(start_pfn + i) && + !PageReserved(pfn_to_page(start_pfn + i))) + return true; + } + + return false; +} + +static int __ioremap_check_desc_other(struct resource *res) +{ + return (res->desc != IORES_DESC_NONE); +} + +static int __ioremap_res_check(struct resource *res, void *arg) +{ + struct ioremap_mem_flags *flags = arg; + + if (!flags->system_ram) + flags->system_ram = __ioremap_check_ram(res); + + if (!flags->desc_other) + flags->desc_other = __ioremap_check_desc_other(res); + + return flags->system_ram && flags->desc_other; +} + +/* + * To avoid multiple resource walks, this function walks resources marked as + * IORESOURCE_MEM and IORESOURCE_BUSY and looking for system RAM and/or a + * resource described not as IORES_DESC_NONE (e.g. IORES_DESC_ACPI_TABLES). + */ +static void __ioremap_check_mem(resource_size_t addr, unsigned long size, + struct ioremap_mem_flags *flags) +{ + u64 start, end; + + start = (u64)addr; + end = start + size - 1; + memset(flags, 0, sizeof(*flags)); + + walk_mem_res(start, end, flags, __ioremap_res_check); } /* @@ -87,9 +134,10 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, unsigned long size, enum page_cache_mode pcm, void *caller) { unsigned long offset, vaddr; - resource_size_t pfn, last_pfn, last_addr; + resource_size_t last_addr; const resource_size_t unaligned_phys_addr = phys_addr; const unsigned long unaligned_size = size; + struct ioremap_mem_flags mem_flags; struct vm_struct *area; enum page_cache_mode new_pcm; pgprot_t prot; @@ -108,13 +156,12 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, return NULL; } + __ioremap_check_mem(phys_addr, size, &mem_flags); + /* * Don't allow anybody to remap normal RAM that we're using.. */ - pfn = phys_addr >> PAGE_SHIFT; - last_pfn = last_addr >> PAGE_SHIFT; - if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, - __ioremap_check_ram) == 1) { + if (mem_flags.system_ram) { WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n", &phys_addr, &last_addr); return NULL; @@ -146,7 +193,15 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, pcm = new_pcm; } + /* + * If the page being mapped is in memory and SEV is active then + * make sure the memory encryption attribute is enabled in the + * resulting mapping. + */ prot = PAGE_KERNEL_IO; + if (sev_active() && mem_flags.desc_other) + prot = pgprot_encrypted(prot); + switch (pcm) { case _PAGE_CACHE_MODE_UC: default: diff --git a/include/linux/ioport.h b/include/linux/ioport.h index c0070d7c4b99..93b4183cf53d 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -271,6 +271,9 @@ extern int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, void *arg, int (*func)(unsigned long, unsigned long, void *)); extern int +walk_mem_res(u64 start, u64 end, void *arg, + int (*func)(struct resource *, void *)); +extern int walk_system_ram_res(u64 start, u64 end, void *arg, int (*func)(struct resource *, void *)); extern int diff --git a/kernel/resource.c b/kernel/resource.c index 8430042fa77b..54ba6de3757c 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -397,6 +397,8 @@ static int find_next_iomem_res(struct resource *res, unsigned long desc, res->start = p->start; if (res->end > p->end) res->end = p->end; + res->flags = p->flags; + res->desc = p->desc; return 0; } @@ -467,6 +469,23 @@ int walk_system_ram_res(u64 start, u64 end, void *arg, arg, func); } +/* + * This function calls the @func callback against all memory ranges, which + * are ranges marked as IORESOURCE_MEM and IORESOUCE_BUSY. + */ +int walk_mem_res(u64 start, u64 end, void *arg, + int (*func)(struct resource *, void *)) +{ + struct resource res; + + res.start = start; + res.end = end; + res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; + + return __walk_iomem_res_desc(&res, IORES_DESC_NONE, true, + arg, func); +} + #if !defined(CONFIG_ARCH_HAS_WALK_MEMORY) /* -- cgit v1.2.3 From ac26963a1175c813e3ed21c0d2435b083173136e Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Fri, 20 Oct 2017 09:30:57 -0500 Subject: percpu: Introduce DEFINE_PER_CPU_DECRYPTED KVM guest defines three per-CPU variables (steal-time, apf_reason, and kvm_pic_eoi) which are shared between a guest and a hypervisor. When SEV is active, memory is encrypted with a guest-specific key, and if the guest OS wants to share the memory region with the hypervisor then it must clear the C-bit (i.e set decrypted) before sharing it. DEFINE_PER_CPU_DECRYPTED can be used to define the per-CPU variables which will be shared between a guest and a hypervisor. Signed-off-by: Brijesh Singh Signed-off-by: Thomas Gleixner Tested-by: Borislav Petkov Acked-by: Tejun Heo Reviewed-by: Borislav Petkov Cc: linux-arch@vger.kernel.org Cc: Tom Lendacky Cc: kvm@vger.kernel.org Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Lameter Link: https://lkml.kernel.org/r/20171020143059.3291-16-brijesh.singh@amd.com --- include/asm-generic/vmlinux.lds.h | 19 +++++++++++++++++++ include/linux/percpu-defs.h | 15 +++++++++++++++ 2 files changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 63e56f6c1877..c58f3805e348 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -777,6 +777,24 @@ #define INIT_RAM_FS #endif +/* + * Memory encryption operates on a page basis. Since we need to clear + * the memory encryption mask for this section, it needs to be aligned + * on a page boundary and be a page-size multiple in length. + * + * Note: We use a separate section so that only this section gets + * decrypted to avoid exposing more than we wish. + */ +#ifdef CONFIG_AMD_MEM_ENCRYPT +#define PERCPU_DECRYPTED_SECTION \ + . = ALIGN(PAGE_SIZE); \ + *(.data..percpu..decrypted) \ + . = ALIGN(PAGE_SIZE); +#else +#define PERCPU_DECRYPTED_SECTION +#endif + + /* * Default discarded sections. * @@ -815,6 +833,7 @@ . = ALIGN(cacheline); \ *(.data..percpu) \ *(.data..percpu..shared_aligned) \ + PERCPU_DECRYPTED_SECTION \ VMLINUX_SYMBOL(__per_cpu_end) = .; /** diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 8f16299ca068..2d2096ba1cfe 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -172,6 +172,21 @@ #define DEFINE_PER_CPU_READ_MOSTLY(type, name) \ DEFINE_PER_CPU_SECTION(type, name, "..read_mostly") +/* + * Declaration/definition used for per-CPU variables that should be accessed + * as decrypted when memory encryption is enabled in the guest. + */ +#if defined(CONFIG_VIRTUALIZATION) && defined(CONFIG_AMD_MEM_ENCRYPT) + +#define DECLARE_PER_CPU_DECRYPTED(type, name) \ + DECLARE_PER_CPU_SECTION(type, name, "..decrypted") + +#define DEFINE_PER_CPU_DECRYPTED(type, name) \ + DEFINE_PER_CPU_SECTION(type, name, "..decrypted") +#else +#define DEFINE_PER_CPU_DECRYPTED(type, name) DEFINE_PER_CPU(type, name) +#endif + /* * Intermodule exports for per-CPU variables. sparse forgets about * address space across EXPORT_SYMBOL(), change EXPORT_SYMBOL() to -- cgit v1.2.3 From f54bb2ec02c839f6bfe3e8d438cd93d30b4809dd Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 6 Nov 2017 16:01:17 +0100 Subject: locking/lockdep: Add IRQs disabled/enabled assertion APIs: lockdep_assert_irqs_enabled()/disabled() Checking whether IRQs are enabled or disabled is a very common sanity check, however not free of overhead especially on fastpath where such assertion is very common. Lockdep is a good host for such concurrency correctness check and it even already tracks down IRQs disablement state. Just reuse its machinery. This will allow us to get rid of the flags pop and check overhead from fast path when kernel is built for production. Suggested-by: Peter Zijlstra Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Cc: David S . Miller Cc: Lai Jiangshan Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Tejun Heo Link: http://lkml.kernel.org/r/1509980490-4285-2-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 02720769c159..a842551fe044 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -725,9 +725,24 @@ do { \ lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_); \ lock_release(&(lock)->dep_map, 0, _THIS_IP_); \ } while (0) + +#define lockdep_assert_irqs_enabled() do { \ + WARN_ONCE(debug_locks && !current->lockdep_recursion && \ + !current->hardirqs_enabled, \ + "IRQs not enabled as expected\n"); \ + } while (0) + +#define lockdep_assert_irqs_disabled() do { \ + WARN_ONCE(debug_locks && !current->lockdep_recursion && \ + current->hardirqs_enabled, \ + "IRQs not disabled as expected\n"); \ + } while (0) + #else # define might_lock(lock) do { } while (0) # define might_lock_read(lock) do { } while (0) +# define lockdep_assert_irqs_enabled() do { } while (0) +# define lockdep_assert_irqs_disabled() do { } while (0) #endif #ifdef CONFIG_LOCKDEP -- cgit v1.2.3 From a7d3d0392a325d630225b7dbccf2558f944114e5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 10 Sep 2017 09:49:45 +0200 Subject: integrity: use kernel_read_file_from_path() to read x509 certs The CONFIG_IMA_LOAD_X509 and CONFIG_EVM_LOAD_X509 options permit loading x509 signed certificates onto the trusted keyrings without verifying the x509 certificate file's signature. This patch replaces the call to the integrity_read_file() specific function with the common kernel_read_file_from_path() function. To avoid verifying the file signature, this patch defines READING_X509_CERTFICATE. Signed-off-by: Christoph Hellwig Signed-off-by: Mimi Zohar --- include/linux/fs.h | 1 + security/integrity/digsig.c | 14 +++++++---- security/integrity/iint.c | 49 --------------------------------------- security/integrity/ima/ima_main.c | 4 ++++ security/integrity/integrity.h | 2 -- 5 files changed, 14 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 339e73742e73..456325084f1d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2792,6 +2792,7 @@ extern int do_pipe_flags(int *, int); id(KEXEC_IMAGE, kexec-image) \ id(KEXEC_INITRAMFS, kexec-initramfs) \ id(POLICY, security-policy) \ + id(X509_CERTIFICATE, x509-certificate) \ id(MAX_ID, ) #define __fid_enumify(ENUM, dummy) READING_ ## ENUM, diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c index 06554c448dce..6f9e4ce568cd 100644 --- a/security/integrity/digsig.c +++ b/security/integrity/digsig.c @@ -112,21 +112,25 @@ int __init integrity_init_keyring(const unsigned int id) int __init integrity_load_x509(const unsigned int id, const char *path) { key_ref_t key; - char *data; + void *data; + loff_t size; int rc; if (!keyring[id]) return -EINVAL; - rc = integrity_read_file(path, &data); - if (rc < 0) + rc = kernel_read_file_from_path(path, &data, &size, 0, + READING_X509_CERTIFICATE); + if (rc < 0) { + pr_err("Unable to open file: %s (%d)", path, rc); return rc; + } key = key_create_or_update(make_key_ref(keyring[id], 1), "asymmetric", NULL, data, - rc, + size, ((KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ), KEY_ALLOC_NOT_IN_QUOTA); @@ -139,6 +143,6 @@ int __init integrity_load_x509(const unsigned int id, const char *path) key_ref_to_ptr(key)->description, path); key_ref_put(key); } - kfree(data); + vfree(data); return 0; } diff --git a/security/integrity/iint.c b/security/integrity/iint.c index 6fc888ca468e..c84e05866052 100644 --- a/security/integrity/iint.c +++ b/security/integrity/iint.c @@ -199,55 +199,6 @@ int integrity_kernel_read(struct file *file, loff_t offset, return ret; } -/* - * integrity_read_file - read entire file content into the buffer - * - * This is function opens a file, allocates the buffer of required - * size, read entire file content to the buffer and closes the file - * - * It is used only by init code. - * - */ -int __init integrity_read_file(const char *path, char **data) -{ - struct file *file; - loff_t size; - char *buf; - int rc = -EINVAL; - - if (!path || !*path) - return -EINVAL; - - file = filp_open(path, O_RDONLY, 0); - if (IS_ERR(file)) { - rc = PTR_ERR(file); - pr_err("Unable to open file: %s (%d)", path, rc); - return rc; - } - - size = i_size_read(file_inode(file)); - if (size <= 0) - goto out; - - buf = kmalloc(size, GFP_KERNEL); - if (!buf) { - rc = -ENOMEM; - goto out; - } - - rc = integrity_kernel_read(file, 0, buf, size); - if (rc == size) { - *data = buf; - } else { - kfree(buf); - if (rc >= 0) - rc = -EIO; - } -out: - fput(file); - return rc; -} - /* * integrity_load_keys - load integrity keys hook * diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 12738c8f39c2..d47f92e97f80 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -405,6 +405,10 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size, if (!file && read_id == READING_MODULE) /* MODULE_SIG_FORCE enabled */ return 0; + /* permit signed certs */ + if (!file && read_id == READING_X509_CERTIFICATE) + return 0; + if (!file || !buf || size == 0) { /* should never happen */ if (ima_appraise & IMA_APPRAISE_ENFORCE) return -EACCES; diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h index a53e7e4ab06c..e1bf040fb110 100644 --- a/security/integrity/integrity.h +++ b/security/integrity/integrity.h @@ -120,8 +120,6 @@ struct integrity_iint_cache *integrity_iint_find(struct inode *inode); int integrity_kernel_read(struct file *file, loff_t offset, void *addr, unsigned long count); -int __init integrity_read_file(const char *path, char **data); - #define INTEGRITY_KEYRING_EVM 0 #define INTEGRITY_KEYRING_IMA 1 #define INTEGRITY_KEYRING_MODULE 2 -- cgit v1.2.3 From fda784e50aace694ec2e4e16e2de07b91a938563 Mon Sep 17 00:00:00 2001 From: "Bruno E. O. Meneguele" Date: Tue, 24 Oct 2017 15:37:00 -0200 Subject: module: export module signature enforcement status A static variable sig_enforce is used as status var to indicate the real value of CONFIG_MODULE_SIG_FORCE, once this one is set the var will hold true, but if the CONFIG is not set the status var will hold whatever value is present in the module.sig_enforce kernel cmdline param: true when =1 and false when =0 or not present. Considering this cmdline param take place over the CONFIG value when it's not set, other places in the kernel could misbehave since they would have only the CONFIG_MODULE_SIG_FORCE value to rely on. Exporting this status var allows the kernel to rely in the effective value of module signature enforcement, being it from CONFIG value or cmdline param. Signed-off-by: Bruno E. O. Meneguele Signed-off-by: Mimi Zohar --- include/linux/module.h | 7 +++++++ kernel/module.c | 10 ++++++++++ 2 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index fe5aa3736707..c69b49abe877 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -639,6 +639,8 @@ static inline bool is_livepatch_module(struct module *mod) } #endif /* CONFIG_LIVEPATCH */ +bool is_module_sig_enforced(void); + #else /* !CONFIG_MODULES... */ static inline struct module *__module_address(unsigned long addr) @@ -753,6 +755,11 @@ static inline bool module_requested_async_probing(struct module *module) return false; } +static inline bool is_module_sig_enforced(void) +{ + return false; +} + #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS diff --git a/kernel/module.c b/kernel/module.c index de66ec825992..d1c194b057a2 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -278,6 +278,16 @@ static bool sig_enforce = IS_ENABLED(CONFIG_MODULE_SIG_FORCE); module_param(sig_enforce, bool_enable_only, 0644); #endif /* !CONFIG_MODULE_SIG_FORCE */ +/* + * Export sig_enforce kernel cmdline parameter to allow other subsystems rely + * on that instead of directly to CONFIG_MODULE_SIG_FORCE config. + */ +bool is_module_sig_enforced(void) +{ + return sig_enforce; +} +EXPORT_SYMBOL(is_module_sig_enforced); + /* Block module loading/unloading? */ int modules_disabled = 0; core_param(nomodule, modules_disabled, bint, 0); -- cgit v1.2.3 From 3653bc95bcc7daa938c0fdcd64ff199ed8f7f208 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 9 Oct 2017 21:52:09 -0700 Subject: timer: Prepare to change all DEFINE_TIMER() callbacks Before we can globally change the function prototype of all timer callbacks, we have to change those set up by DEFINE_TIMER(). Prepare for this by casting the callbacks until the prototype changes globally. Cc: Thomas Gleixner Signed-off-by: Kees Cook --- include/linux/timer.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index a1af92bac0d5..9f8895decb82 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -63,6 +63,9 @@ struct timer_list { #define TIMER_TRACE_FLAGMASK (TIMER_MIGRATING | TIMER_DEFERRABLE | TIMER_PINNED | TIMER_IRQSAFE) +#define TIMER_DATA_TYPE unsigned long +#define TIMER_FUNC_TYPE void (*)(TIMER_DATA_TYPE) + #define __TIMER_INITIALIZER(_function, _data, _flags) { \ .entry = { .next = TIMER_ENTRY_STATIC }, \ .function = (_function), \ @@ -74,7 +77,7 @@ struct timer_list { #define DEFINE_TIMER(_name, _function) \ struct timer_list _name = \ - __TIMER_INITIALIZER(_function, 0, 0) + __TIMER_INITIALIZER((TIMER_FUNC_TYPE)_function, 0, 0) void init_timer_key(struct timer_list *timer, unsigned int flags, const char *name, struct lock_class_key *key); @@ -147,9 +150,6 @@ static inline void init_timer_on_stack_key(struct timer_list *timer, #define setup_pinned_deferrable_timer_on_stack(timer, fn, data) \ __setup_timer_on_stack((timer), (fn), (data), TIMER_DEFERRABLE | TIMER_PINNED) -#define TIMER_DATA_TYPE unsigned long -#define TIMER_FUNC_TYPE void (*)(TIMER_DATA_TYPE) - #ifndef CONFIG_LOCKDEP static inline void timer_setup(struct timer_list *timer, void (*callback)(struct timer_list *), -- cgit v1.2.3 From f72e38e8ec8869ac0ba5a75d7d2f897d98a1454e Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 9 Nov 2017 14:27:35 +0100 Subject: x86/virt, x86/platform: Merge 'struct x86_hyper' into 'struct x86_platform' and 'struct x86_init' Instead of x86_hyper being either NULL on bare metal or a pointer to a struct hypervisor_x86 in case of the kernel running as a guest merge the struct into x86_platform and x86_init. This will remove the need for wrappers making it hard to find out what is being called. With dummy functions added for all callbacks testing for a NULL function pointer can be removed, too. Suggested-by: Ingo Molnar Signed-off-by: Juergen Gross Acked-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Cc: akataria@vmware.com Cc: boris.ostrovsky@oracle.com Cc: devel@linuxdriverproject.org Cc: haiyangz@microsoft.com Cc: kvm@vger.kernel.org Cc: kys@microsoft.com Cc: pbonzini@redhat.com Cc: rkrcmar@redhat.com Cc: rusty@rustcorp.com.au Cc: sthemmin@microsoft.com Cc: virtualization@lists.linux-foundation.org Cc: xen-devel@lists.xenproject.org Link: http://lkml.kernel.org/r/20171109132739.23465-2-jgross@suse.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/hypervisor.h | 25 ++++-------------- arch/x86/include/asm/x86_init.h | 24 +++++++++++++++++ arch/x86/kernel/apic/apic.c | 2 +- arch/x86/kernel/cpu/hypervisor.c | 54 +++++++++++++++++++-------------------- arch/x86/kernel/cpu/mshyperv.c | 2 +- arch/x86/kernel/cpu/vmware.c | 4 +-- arch/x86/kernel/kvm.c | 2 +- arch/x86/kernel/x86_init.c | 9 +++++++ arch/x86/mm/init.c | 2 +- arch/x86/xen/enlighten_hvm.c | 8 +++--- arch/x86/xen/enlighten_pv.c | 2 +- include/linux/hypervisor.h | 8 ++++-- 12 files changed, 81 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 0ead9dbb9130..0eca7239a7aa 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -23,6 +23,7 @@ #ifdef CONFIG_HYPERVISOR_GUEST #include +#include #include /* @@ -35,17 +36,11 @@ struct hypervisor_x86 { /* Detection routine */ uint32_t (*detect)(void); - /* Platform setup (run once per boot) */ - void (*init_platform)(void); + /* init time callbacks */ + struct x86_hyper_init init; - /* X2APIC detection (run once per boot) */ - bool (*x2apic_available)(void); - - /* pin current vcpu to specified physical cpu (run rarely) */ - void (*pin_vcpu)(int); - - /* called during init_mem_mapping() to setup early mappings. */ - void (*init_mem_mapping)(void); + /* runtime callbacks */ + struct x86_hyper_runtime runtime; }; extern const struct hypervisor_x86 *x86_hyper; @@ -58,17 +53,7 @@ extern const struct hypervisor_x86 x86_hyper_xen_hvm; extern const struct hypervisor_x86 x86_hyper_kvm; extern void init_hypervisor_platform(void); -extern bool hypervisor_x2apic_available(void); -extern void hypervisor_pin_vcpu(int cpu); - -static inline void hypervisor_init_mem_mapping(void) -{ - if (x86_hyper && x86_hyper->init_mem_mapping) - x86_hyper->init_mem_mapping(); -} #else static inline void init_hypervisor_platform(void) { } -static inline bool hypervisor_x2apic_available(void) { return false; } -static inline void hypervisor_init_mem_mapping(void) { } #endif /* CONFIG_HYPERVISOR_GUEST */ #endif /* _ASM_X86_HYPERVISOR_H */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 8a1ebf9540dd..ad15a0fda917 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -114,6 +114,18 @@ struct x86_init_pci { void (*fixup_irqs)(void); }; +/** + * struct x86_hyper_init - x86 hypervisor init functions + * @init_platform: platform setup + * @x2apic_available: X2APIC detection + * @init_mem_mapping: setup early mappings during init_mem_mapping() + */ +struct x86_hyper_init { + void (*init_platform)(void); + bool (*x2apic_available)(void); + void (*init_mem_mapping)(void); +}; + /** * struct x86_init_ops - functions for platform specific setup * @@ -127,6 +139,7 @@ struct x86_init_ops { struct x86_init_timers timers; struct x86_init_iommu iommu; struct x86_init_pci pci; + struct x86_hyper_init hyper; }; /** @@ -199,6 +212,15 @@ struct x86_legacy_features { struct x86_legacy_devices devices; }; +/** + * struct x86_hyper_runtime - x86 hypervisor specific runtime callbacks + * + * @pin_vcpu: pin current vcpu to specified physical cpu (run rarely) + */ +struct x86_hyper_runtime { + void (*pin_vcpu)(int cpu); +}; + /** * struct x86_platform_ops - platform specific runtime functions * @calibrate_cpu: calibrate CPU @@ -218,6 +240,7 @@ struct x86_legacy_features { * possible in x86_early_init_platform_quirks() by * only using the current x86_hardware_subarch * semantics. + * @hyper: x86 hypervisor specific runtime callbacks */ struct x86_platform_ops { unsigned long (*calibrate_cpu)(void); @@ -233,6 +256,7 @@ struct x86_platform_ops { void (*apic_post_init)(void); struct x86_legacy_features legacy; void (*set_legacy_features)(void); + struct x86_hyper_runtime hyper; }; struct pci_dev; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index ff891772c9f8..89c7c8569e5e 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1645,7 +1645,7 @@ static __init void try_to_enable_x2apic(int remap_mode) * under KVM */ if (max_physical_apicid > 255 || - !hypervisor_x2apic_available()) { + !x86_init.hyper.x2apic_available()) { pr_info("x2apic: IRQ remapping doesn't support X2APIC mode\n"); x2apic_disable(); return; diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index 4fa90006ac68..22226c1bf092 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -44,51 +44,49 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] = const struct hypervisor_x86 *x86_hyper; EXPORT_SYMBOL(x86_hyper); -static inline void __init +static inline const struct hypervisor_x86 * __init detect_hypervisor_vendor(void) { - const struct hypervisor_x86 *h, * const *p; + const struct hypervisor_x86 *h = NULL, * const *p; uint32_t pri, max_pri = 0; for (p = hypervisors; p < hypervisors + ARRAY_SIZE(hypervisors); p++) { - h = *p; - pri = h->detect(); - if (pri != 0 && pri > max_pri) { + pri = (*p)->detect(); + if (pri > max_pri) { max_pri = pri; - x86_hyper = h; + h = *p; } } - if (max_pri) - pr_info("Hypervisor detected: %s\n", x86_hyper->name); + if (h) + pr_info("Hypervisor detected: %s\n", h->name); + + return h; } -void __init init_hypervisor_platform(void) +static void __init copy_array(const void *src, void *target, unsigned int size) { + unsigned int i, n = size / sizeof(void *); + const void * const *from = (const void * const *)src; + const void **to = (const void **)target; - detect_hypervisor_vendor(); - - if (!x86_hyper) - return; - - if (x86_hyper->init_platform) - x86_hyper->init_platform(); + for (i = 0; i < n; i++) + if (from[i]) + to[i] = from[i]; } -bool __init hypervisor_x2apic_available(void) +void __init init_hypervisor_platform(void) { - return x86_hyper && - x86_hyper->x2apic_available && - x86_hyper->x2apic_available(); -} + const struct hypervisor_x86 *h; -void hypervisor_pin_vcpu(int cpu) -{ - if (!x86_hyper) + h = detect_hypervisor_vendor(); + + if (!h) return; - if (x86_hyper->pin_vcpu) - x86_hyper->pin_vcpu(cpu); - else - WARN_ONCE(1, "vcpu pinning requested but not supported!\n"); + copy_array(&h->init, &x86_init.hyper, sizeof(h->init)); + copy_array(&h->runtime, &x86_platform.hyper, sizeof(h->runtime)); + + x86_hyper = h; + x86_init.hyper.init_platform(); } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 236324e83a3a..6bb84d655e4b 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -257,6 +257,6 @@ static void __init ms_hyperv_init_platform(void) const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { .name = "Microsoft Hyper-V", .detect = ms_hyperv_platform, - .init_platform = ms_hyperv_init_platform, + .init.init_platform = ms_hyperv_init_platform, }; EXPORT_SYMBOL(x86_hyper_ms_hyperv); diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 40ed26852ebd..4804c1d063c8 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -208,7 +208,7 @@ static bool __init vmware_legacy_x2apic_available(void) const __refconst struct hypervisor_x86 x86_hyper_vmware = { .name = "VMware", .detect = vmware_platform, - .init_platform = vmware_platform_setup, - .x2apic_available = vmware_legacy_x2apic_available, + .init.init_platform = vmware_platform_setup, + .init.x2apic_available = vmware_legacy_x2apic_available, }; EXPORT_SYMBOL(x86_hyper_vmware); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 8bb9594d0761..9dca8437c795 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -547,7 +547,7 @@ static uint32_t __init kvm_detect(void) const struct hypervisor_x86 x86_hyper_kvm __refconst = { .name = "KVM", .detect = kvm_detect, - .x2apic_available = kvm_para_available, + .init.x2apic_available = kvm_para_available, }; EXPORT_SYMBOL_GPL(x86_hyper_kvm); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index a088b2c47f73..5b2d10c1973a 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -28,6 +28,8 @@ void x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } int __init iommu_init_noop(void) { return 0; } void iommu_shutdown_noop(void) { } +bool __init bool_x86_init_noop(void) { return false; } +void x86_op_int_noop(int cpu) { } /* * The platform setup functions are preset with the default functions @@ -81,6 +83,12 @@ struct x86_init_ops x86_init __initdata = { .init_irq = x86_default_pci_init_irq, .fixup_irqs = x86_default_pci_fixup_irqs, }, + + .hyper = { + .init_platform = x86_init_noop, + .x2apic_available = bool_x86_init_noop, + .init_mem_mapping = x86_init_noop, + }, }; struct x86_cpuinit_ops x86_cpuinit = { @@ -101,6 +109,7 @@ struct x86_platform_ops x86_platform __ro_after_init = { .get_nmi_reason = default_get_nmi_reason, .save_sched_clock_state = tsc_save_sched_clock_state, .restore_sched_clock_state = tsc_restore_sched_clock_state, + .hyper.pin_vcpu = x86_op_int_noop, }; EXPORT_SYMBOL_GPL(x86_platform); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index af5c1ed21d43..a22c2b95e513 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -671,7 +671,7 @@ void __init init_mem_mapping(void) load_cr3(swapper_pg_dir); __flush_tlb_all(); - hypervisor_init_mem_mapping(); + x86_init.hyper.init_mem_mapping(); early_memtest(0, max_pfn_mapped << PAGE_SHIFT); } diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index de503c225ae1..7b1622089f96 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -229,9 +229,9 @@ static uint32_t __init xen_platform_hvm(void) const struct hypervisor_x86 x86_hyper_xen_hvm = { .name = "Xen HVM", .detect = xen_platform_hvm, - .init_platform = xen_hvm_guest_init, - .pin_vcpu = xen_pin_vcpu, - .x2apic_available = xen_x2apic_para_available, - .init_mem_mapping = xen_hvm_init_mem_mapping, + .init.init_platform = xen_hvm_guest_init, + .init.x2apic_available = xen_x2apic_para_available, + .init.init_mem_mapping = xen_hvm_init_mem_mapping, + .runtime.pin_vcpu = xen_pin_vcpu, }; EXPORT_SYMBOL(x86_hyper_xen_hvm); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index d4396e27b1fb..69d1a7054ddb 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1463,6 +1463,6 @@ static uint32_t __init xen_platform_pv(void) const struct hypervisor_x86 x86_hyper_xen_pv = { .name = "Xen PV", .detect = xen_platform_pv, - .pin_vcpu = xen_pin_vcpu, + .runtime.pin_vcpu = xen_pin_vcpu, }; EXPORT_SYMBOL(x86_hyper_xen_pv); diff --git a/include/linux/hypervisor.h b/include/linux/hypervisor.h index b4054fd5b6f6..b19563f9a8eb 100644 --- a/include/linux/hypervisor.h +++ b/include/linux/hypervisor.h @@ -7,8 +7,12 @@ * Juergen Gross */ -#ifdef CONFIG_HYPERVISOR_GUEST -#include +#ifdef CONFIG_X86 +#include +static inline void hypervisor_pin_vcpu(int cpu) +{ + x86_platform.hyper.pin_vcpu(cpu); +} #else static inline void hypervisor_pin_vcpu(int cpu) { -- cgit v1.2.3 From 125b1192bd48544d9429e240c8f8e64d1533b2c1 Mon Sep 17 00:00:00 2001 From: Keerthy Date: Fri, 10 Nov 2017 17:22:44 +0530 Subject: regulator: tps65218: remove unused tps_info structure remove unused tps_info structure. Signed-off-by: Keerthy Signed-off-by: Mark Brown --- include/linux/mfd/tps65218.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h index bccd2d68b1e3..f069c518c0ed 100644 --- a/include/linux/mfd/tps65218.h +++ b/include/linux/mfd/tps65218.h @@ -245,24 +245,6 @@ enum tps65218_irqs { TPS65218_INVALID4_IRQ, }; -/** - * struct tps_info - packages regulator constraints - * @id: Id of the regulator - * @name: Voltage regulator name - * @min_uV: minimum micro volts - * @max_uV: minimum micro volts - * @strobe: sequencing strobe value for the regulator - * - * This data is used to check the regualtor voltage limits while setting. - */ -struct tps_info { - int id; - const char *name; - int min_uV; - int max_uV; - int strobe; -}; - /** * struct tps65218 - tps65218 sub-driver chip access routines * @@ -280,7 +262,6 @@ struct tps65218 { u32 irq_mask; struct regmap_irq_chip_data *irq_data; struct regulator_desc desc[TPS65218_NUM_REGULATOR]; - struct tps_info *info[TPS65218_NUM_REGULATOR]; struct regmap *regmap; u8 *strobes; }; -- cgit v1.2.3 From b24591e2fcf852ad7ad2ccf745c8220bf378d312 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 9 Nov 2017 12:35:07 +0000 Subject: timers: Add a function to start/reduce a timer Add a function, similar to mod_timer(), that will start a timer if it isn't running and will modify it if it is running and has an expiry time longer than the new time. If the timer is running with an expiry time that's the same or sooner, no change is made. The function looks like: int timer_reduce(struct timer_list *timer, unsigned long expires); This can be used by code such as networking code to make it easier to share a timer for multiple timeouts. For instance, in upcoming AF_RXRPC code, the rxrpc_call struct will maintain a number of timeouts: unsigned long ack_at; unsigned long resend_at; unsigned long ping_at; unsigned long expect_rx_by; unsigned long expect_req_by; unsigned long expect_term_by; each of which is set independently of the others. With timer reduction available, when the code needs to set one of the timeouts, it only needs to look at that timeout and then call timer_reduce() to modify the timer, starting it or bringing it forward if necessary. There is no need to refer to the other timeouts to see which is earliest and no need to take any lock other than, potentially, the timer lock inside timer_reduce(). Note, that this does not protect against concurrent invocations of any of the timer functions. As an example, the expect_rx_by timeout above, which terminates a call if we don't get a packet from the server within a certain time window, would be set something like this: unsigned long now = jiffies; unsigned long expect_rx_by = now + packet_receive_timeout; WRITE_ONCE(call->expect_rx_by, expect_rx_by); timer_reduce(&call->timer, expect_rx_by); The timer service code (which might, say, be in a work function) would then check all the timeouts to see which, if any, had triggered, deal with those: t = READ_ONCE(call->ack_at); if (time_after_eq(now, t)) { cmpxchg(&call->ack_at, t, now + MAX_JIFFY_OFFSET); set_bit(RXRPC_CALL_EV_ACK, &call->events); } and then restart the timer if necessary by finding the soonest timeout that hasn't yet passed and then calling timer_reduce(). The disadvantage of doing things this way rather than comparing the timers each time and calling mod_timer() is that you *will* take timer events unless you can finish what you're doing and delete the timer in time. The advantage of doing things this way is that you don't need to use a lock to work out when the next timer should be set, other than the timer's own lock - which you might not have to take. [ tglx: Fixed weird formatting and adopted it to pending changes ] Signed-off-by: David Howells Signed-off-by: Thomas Gleixner Cc: keyrings@vger.kernel.org Cc: linux-afs@lists.infradead.org Link: https://lkml.kernel.org/r/151023090769.23050.1801643667223880753.stgit@warthog.procyon.org.uk --- include/linux/timer.h | 1 + kernel/time/timer.c | 45 ++++++++++++++++++++++++++++++++++++++------- 2 files changed, 39 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index 9f8895decb82..37b5e2f74d21 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -203,6 +203,7 @@ extern void add_timer_on(struct timer_list *timer, int cpu); extern int del_timer(struct timer_list * timer); extern int mod_timer(struct timer_list *timer, unsigned long expires); extern int mod_timer_pending(struct timer_list *timer, unsigned long expires); +extern int timer_reduce(struct timer_list *timer, unsigned long expires); /* * The jiffies value which is added to now, when there is no timer diff --git a/kernel/time/timer.c b/kernel/time/timer.c index fbb1f85327bf..af0b8bae4502 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -929,8 +929,11 @@ static struct timer_base *lock_timer_base(struct timer_list *timer, } } +#define MOD_TIMER_PENDING_ONLY 0x01 +#define MOD_TIMER_REDUCE 0x02 + static inline int -__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) +__mod_timer(struct timer_list *timer, unsigned long expires, unsigned int options) { struct timer_base *base, *new_base; unsigned int idx = UINT_MAX; @@ -950,7 +953,11 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) * larger granularity than you would get from adding a new * timer with this expiry. */ - if (timer->expires == expires) + long diff = timer->expires - expires; + + if (!diff) + return 1; + if (options & MOD_TIMER_REDUCE && diff <= 0) return 1; /* @@ -962,6 +969,12 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) base = lock_timer_base(timer, &flags); forward_timer_base(base); + if (timer_pending(timer) && (options & MOD_TIMER_REDUCE) && + time_before_eq(timer->expires, expires)) { + ret = 1; + goto out_unlock; + } + clk = base->clk; idx = calc_wheel_index(expires, clk); @@ -971,7 +984,10 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) * subsequent call will exit in the expires check above. */ if (idx == timer_get_idx(timer)) { - timer->expires = expires; + if (!(options & MOD_TIMER_REDUCE)) + timer->expires = expires; + else if (time_after(timer->expires, expires)) + timer->expires = expires; ret = 1; goto out_unlock; } @@ -981,7 +997,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) } ret = detach_if_pending(timer, base, false); - if (!ret && pending_only) + if (!ret && (options & MOD_TIMER_PENDING_ONLY)) goto out_unlock; debug_activate(timer, expires); @@ -1042,7 +1058,7 @@ out_unlock: */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { - return __mod_timer(timer, expires, true); + return __mod_timer(timer, expires, MOD_TIMER_PENDING_ONLY); } EXPORT_SYMBOL(mod_timer_pending); @@ -1068,10 +1084,25 @@ EXPORT_SYMBOL(mod_timer_pending); */ int mod_timer(struct timer_list *timer, unsigned long expires) { - return __mod_timer(timer, expires, false); + return __mod_timer(timer, expires, 0); } EXPORT_SYMBOL(mod_timer); +/** + * timer_reduce - Modify a timer's timeout if it would reduce the timeout + * @timer: The timer to be modified + * @expires: New timeout in jiffies + * + * timer_reduce() is very similar to mod_timer(), except that it will only + * modify a running timer if that would reduce the expiration time (it will + * start a timer that isn't running). + */ +int timer_reduce(struct timer_list *timer, unsigned long expires) +{ + return __mod_timer(timer, expires, MOD_TIMER_REDUCE); +} +EXPORT_SYMBOL(timer_reduce); + /** * add_timer - start a timer * @timer: the timer to be added @@ -1754,7 +1785,7 @@ signed long __sched schedule_timeout(signed long timeout) timer.task = current; timer_setup_on_stack(&timer.timer, process_timeout, 0); - __mod_timer(&timer.timer, expire, false); + __mod_timer(&timer.timer, expire, 0); schedule(); del_singleshot_timer_sync(&timer.timer); -- cgit v1.2.3 From fcdfafcb73be8fa45909327bbddca46fb362a675 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 13 Nov 2017 07:59:10 +0100 Subject: kprobes: Don't spam the build log with deprecation warnings The jprobes APIs are deprecated - but are still in occasional use for code that few people seem to care about, so stop generating deprecation warnings. Cc: Masami Hiramatsu Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/kprobes.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 56b2e698dbad..9440a2fc8893 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -468,18 +468,18 @@ static inline int enable_kprobe(struct kprobe *kp) return -ENOSYS; } #endif /* CONFIG_KPROBES */ -static inline int __deprecated register_jprobe(struct jprobe *p) +static inline int register_jprobe(struct jprobe *p) { return -ENOSYS; } -static inline int __deprecated register_jprobes(struct jprobe **jps, int num) +static inline int register_jprobes(struct jprobe **jps, int num) { return -ENOSYS; } -static inline void __deprecated unregister_jprobe(struct jprobe *p) +static inline void unregister_jprobe(struct jprobe *p) { } -static inline void __deprecated unregister_jprobes(struct jprobe **jps, int num) +static inline void unregister_jprobes(struct jprobe **jps, int num) { } static inline int disable_kretprobe(struct kretprobe *rp) @@ -490,11 +490,11 @@ static inline int enable_kretprobe(struct kretprobe *rp) { return enable_kprobe(&rp->kp); } -static inline int __deprecated disable_jprobe(struct jprobe *jp) +static inline int disable_jprobe(struct jprobe *jp) { return -ENOSYS; } -static inline int __deprecated enable_jprobe(struct jprobe *jp) +static inline int enable_jprobe(struct jprobe *jp) { return -ENOSYS; } -- cgit v1.2.3 From f4c09f87adfe31587aa4b2aea2cb2dbde2150f54 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 13 Nov 2017 09:39:01 +0100 Subject: cpu/hotplug: Get rid of CPU hotplug notifier leftovers The CPU hotplug notifiers are history. Remove the last reminders. Reported-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- .../fault-injection/notifier-error-inject.txt | 30 ---------------------- Documentation/power/suspend-and-cpuhotplug.txt | 9 +++---- include/linux/cpu.h | 27 ++++++++----------- 3 files changed, 14 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/Documentation/fault-injection/notifier-error-inject.txt b/Documentation/fault-injection/notifier-error-inject.txt index 83d3f4e43e91..e861d761de24 100644 --- a/Documentation/fault-injection/notifier-error-inject.txt +++ b/Documentation/fault-injection/notifier-error-inject.txt @@ -6,41 +6,11 @@ specified notifier chain callbacks. It is useful to test the error handling of notifier call chain failures which is rarely executed. There are kernel modules that can be used to test the following notifiers. - * CPU notifier * PM notifier * Memory hotplug notifier * powerpc pSeries reconfig notifier * Netdevice notifier -CPU notifier error injection module ------------------------------------ -This feature can be used to test the error handling of the CPU notifiers by -injecting artificial errors to CPU notifier chain callbacks. - -If the notifier call chain should be failed with some events notified, write -the error code to debugfs interface -/sys/kernel/debug/notifier-error-inject/cpu/actions//error - -Possible CPU notifier events to be failed are: - - * CPU_UP_PREPARE - * CPU_UP_PREPARE_FROZEN - * CPU_DOWN_PREPARE - * CPU_DOWN_PREPARE_FROZEN - -Example1: Inject CPU offline error (-1 == -EPERM) - - # cd /sys/kernel/debug/notifier-error-inject/cpu - # echo -1 > actions/CPU_DOWN_PREPARE/error - # echo 0 > /sys/devices/system/cpu/cpu1/online - bash: echo: write error: Operation not permitted - -Example2: inject CPU online error (-2 == -ENOENT) - - # echo -2 > actions/CPU_UP_PREPARE/error - # echo 1 > /sys/devices/system/cpu/cpu1/online - bash: echo: write error: No such file or directory - PM notifier error injection module ---------------------------------- This feature is controlled through debugfs interface diff --git a/Documentation/power/suspend-and-cpuhotplug.txt b/Documentation/power/suspend-and-cpuhotplug.txt index 2fc909502db5..31abd04b9572 100644 --- a/Documentation/power/suspend-and-cpuhotplug.txt +++ b/Documentation/power/suspend-and-cpuhotplug.txt @@ -232,7 +232,7 @@ d. Handling microcode update during suspend/hibernate: hibernate/restore cycle.] In the current design of the kernel however, during a CPU offline operation - as part of the suspend/hibernate cycle (the CPU_DEAD_FROZEN notification), + as part of the suspend/hibernate cycle (cpuhp_tasks_frozen is set), the existing copy of microcode image in the kernel is not freed up. And during the CPU online operations (during resume/restore), since the kernel finds that it already has copies of the microcode images for all the @@ -252,10 +252,9 @@ Yes, they are listed below: the _cpu_down() and _cpu_up() functions is *always* 0. This might not reflect the true current state of the system, since the tasks could have been frozen by an out-of-band event such as a suspend - operation in progress. Hence, it will lead to wrong notifications being - sent during the cpu online/offline events (eg, CPU_ONLINE notification - instead of CPU_ONLINE_FROZEN) which in turn will lead to execution of - inappropriate code by the callbacks registered for such CPU hotplug events. + operation in progress. Hence, the cpuhp_tasks_frozen variable will not + reflect the frozen state and the CPU hotplug callbacks which evaluate + that variable might execute the wrong code path. 2. If a regular CPU hotplug stress test happens to race with the freezer due to a suspend operation in progress at the same time, then we could hit the diff --git a/include/linux/cpu.h b/include/linux/cpu.h index cd4771b772c0..b6e4a598b2cd 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -55,24 +55,17 @@ extern void unregister_cpu(struct cpu *cpu); extern ssize_t arch_cpu_probe(const char *, size_t); extern ssize_t arch_cpu_release(const char *, size_t); #endif -struct notifier_block; - -#define CPU_ONLINE 0x0002 /* CPU (unsigned)v is up */ -#define CPU_UP_PREPARE 0x0003 /* CPU (unsigned)v coming up */ -#define CPU_DEAD 0x0007 /* CPU (unsigned)v dead */ -#define CPU_POST_DEAD 0x0009 /* CPU (unsigned)v dead, cpu_hotplug - * lock is dropped */ -#define CPU_BROKEN 0x000B /* CPU (unsigned)v did not die properly, - * perhaps due to preemption. */ - -/* Used for CPU hotplug events occurring while tasks are frozen due to a suspend - * operation in progress - */ -#define CPU_TASKS_FROZEN 0x0010 -#define CPU_ONLINE_FROZEN (CPU_ONLINE | CPU_TASKS_FROZEN) -#define CPU_UP_PREPARE_FROZEN (CPU_UP_PREPARE | CPU_TASKS_FROZEN) -#define CPU_DEAD_FROZEN (CPU_DEAD | CPU_TASKS_FROZEN) +/* + * These states are not related to the core CPU hotplug mechanism. They are + * used by various (sub)architectures to track internal state + */ +#define CPU_ONLINE 0x0002 /* CPU is up */ +#define CPU_UP_PREPARE 0x0003 /* CPU coming up */ +#define CPU_DEAD 0x0007 /* CPU dead */ +#define CPU_DEAD_FROZEN 0x0008 /* CPU timed out on unplug */ +#define CPU_POST_DEAD 0x0009 /* CPU successfully unplugged */ +#define CPU_BROKEN 0x000B /* CPU did not die properly */ #ifdef CONFIG_SMP extern bool cpuhp_tasks_frozen; -- cgit v1.2.3 From 01c313dded34a16ef69e3972ceca687ba8a7cdf2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 13 Nov 2017 17:50:59 +0100 Subject: kallsyms: fix building without printk Building kallsyms fails without CONFIG_PRINTK due to a missing declaration: kernel/kallsyms.c: In function 'kallsyms_show_value': kernel/kallsyms.c:670:10: error: 'kptr_restrict' undeclared (first use in this function); did you mean 'keyring_restrict'? This moves the declaration outside of the #ifdef guard, the definition is already available without CONFIG_PRINTK. Fixes: c0f3ea158939 ("stop using '%pK' for /proc/kallsyms pointer values") Signed-off-by: Arnd Bergmann [ I clearly need to start doing "allnoconfig" builds too, or just have a test branch for the 0day robot - Linus ] Signed-off-by: Linus Torvalds --- include/linux/printk.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 335926039adc..905bba92f015 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -189,7 +189,6 @@ extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, extern int printk_delay_msec; extern int dmesg_restrict; -extern int kptr_restrict; extern int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void __user *buf, @@ -280,6 +279,8 @@ static inline void printk_safe_flush_on_panic(void) } #endif +extern int kptr_restrict; + extern asmlinkage void dump_stack(void) __cold; #ifndef pr_fmt -- cgit v1.2.3 From e4a8ca3baa5557fa54557d42b5910ed0d3316922 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 13 Nov 2017 17:51:00 +0100 Subject: /proc/module: fix building without kallsyms As reported by kernelci and other build bots, we now get a link failure without CONFIG_KALLSYMS: module.c:(.text+0xf2c): undefined reference to `kallsyms_show_value' This adds a dummy helper with the same name that can be used for compilation. It's not entirely clear to me what this should return for !CONFIG_KALLSYMS, I picked an unconditional 'false', which leads to the module address being unavailable to user space. Link: https://kernelci.org/build/mainline/branch/master/kernel/v4.14-5-g516fb7f2e73d/ Fixes: 516fb7f2e73d ("/proc/module: use the same logic as /proc/kallsyms for address exposure") Signed-off-by: Arnd Bergmann Signed-off-by: Linus Torvalds --- include/linux/kallsyms.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 0a777c5216b1..708f337d780b 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -14,8 +14,6 @@ #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \ 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1) -/* How and when do we show kallsyms values? */ -extern int kallsyms_show_value(void); #ifndef CONFIG_64BIT # define KALLSYM_FMT "%08lx" #else @@ -54,6 +52,9 @@ extern void __print_symbol(const char *fmt, unsigned long address); int lookup_symbol_name(unsigned long addr, char *symname); int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); +/* How and when do we show kallsyms values? */ +extern int kallsyms_show_value(void); + #else /* !CONFIG_KALLSYMS */ static inline unsigned long kallsyms_lookup_name(const char *name) @@ -112,6 +113,11 @@ static inline int lookup_symbol_attrs(unsigned long addr, unsigned long *size, u return -ERANGE; } +static inline int kallsyms_show_value(void) +{ + return false; +} + /* Stupid that this does nothing, but I didn't create this mess. */ #define __print_symbol(fmt, addr) #endif /*CONFIG_KALLSYMS*/ -- cgit v1.2.3