From bc06a9e0874239cb6d4eebcb0ecd1a91ad9272db Mon Sep 17 00:00:00 2001 From: Shanker Donthineni Date: Fri, 19 May 2023 08:49:00 -0500 Subject: genirq: Use hlist for managing resend handlers The current implementation utilizes a bitmap for managing interrupt resend handlers, which is allocated based on the SPARSE_IRQ/NR_IRQS macros. However, this method may not efficiently utilize memory during runtime, particularly when IRQ_BITMAP_BITS is large. Address this issue by using an hlist to manage interrupt resend handlers instead of relying on a static bitmap memory allocation. Additionally, a new function, clear_irq_resend(), is introduced and called from irq_shutdown to ensure a graceful teardown of the interrupt. Signed-off-by: Shanker Donthineni Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230519134902.1495562-2-sdonthineni@nvidia.com --- kernel/irq/internals.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/irq/internals.h') diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 5fdc0b557579..51fc8c497c22 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -113,6 +113,8 @@ irqreturn_t handle_irq_event(struct irq_desc *desc); /* Resending of interrupts :*/ int check_irq_resend(struct irq_desc *desc, bool inject); +void clear_irq_resend(struct irq_desc *desc); +void irq_resend_init(struct irq_desc *desc); bool irq_wait_for_poll(struct irq_desc *desc); void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action); -- cgit v1.2.3 From 5e630aa8d9fcd4c0cb6d5d09422009533aba979a Mon Sep 17 00:00:00 2001 From: Shanker Donthineni Date: Fri, 19 May 2023 08:49:01 -0500 Subject: genirq: Encapsulate sparse bitmap handling Move the open coded sparse bitmap handling into helper functions as a preparatory step for converting the sparse interrupt management to a maple tree. No functional change. Signed-off-by: Shanker Donthineni Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230519134902.1495562-3-sdonthineni@nvidia.com --- kernel/irq/internals.h | 4 ++-- kernel/irq/irqdesc.c | 30 ++++++++++++++++++++---------- 2 files changed, 22 insertions(+), 12 deletions(-) (limited to 'kernel/irq/internals.h') diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 51fc8c497c22..f3f2090dd2de 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -12,9 +12,9 @@ #include #ifdef CONFIG_SPARSE_IRQ -# define IRQ_BITMAP_BITS (NR_IRQS + 8196) +# define MAX_SPARSE_IRQS (NR_IRQS + 8196) #else -# define IRQ_BITMAP_BITS NR_IRQS +# define MAX_SPARSE_IRQS NR_IRQS #endif #define istate core_internal_state__do_not_mess_with_it diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index b401b89b226a..e0d9dd9b36f9 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -131,7 +131,18 @@ int nr_irqs = NR_IRQS; EXPORT_SYMBOL_GPL(nr_irqs); static DEFINE_MUTEX(sparse_irq_lock); -static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS); +static DECLARE_BITMAP(allocated_irqs, MAX_SPARSE_IRQS); + +static int irq_find_free_area(unsigned int from, unsigned int cnt) +{ + return bitmap_find_next_zero_area(allocated_irqs, MAX_SPARSE_IRQS, + from, cnt, 0); +} + +static unsigned int irq_find_at_or_after(unsigned int offset) +{ + return find_next_bit(allocated_irqs, nr_irqs, offset); +} #ifdef CONFIG_SPARSE_IRQ @@ -517,7 +528,7 @@ err: static int irq_expand_nr_irqs(unsigned int nr) { - if (nr > IRQ_BITMAP_BITS) + if (nr > MAX_SPARSE_IRQS) return -ENOMEM; nr_irqs = nr; return 0; @@ -535,11 +546,11 @@ int __init early_irq_init(void) printk(KERN_INFO "NR_IRQS: %d, nr_irqs: %d, preallocated irqs: %d\n", NR_IRQS, nr_irqs, initcnt); - if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS)) - nr_irqs = IRQ_BITMAP_BITS; + if (WARN_ON(nr_irqs > MAX_SPARSE_IRQS)) + nr_irqs = MAX_SPARSE_IRQS; - if (WARN_ON(initcnt > IRQ_BITMAP_BITS)) - initcnt = IRQ_BITMAP_BITS; + if (WARN_ON(initcnt > MAX_SPARSE_IRQS)) + initcnt = MAX_SPARSE_IRQS; if (initcnt > nr_irqs) nr_irqs = initcnt; @@ -812,8 +823,7 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, mutex_lock(&sparse_irq_lock); - start = bitmap_find_next_zero_area(allocated_irqs, IRQ_BITMAP_BITS, - from, cnt, 0); + start = irq_find_free_area(from, cnt); ret = -EEXIST; if (irq >=0 && start != irq) goto unlock; @@ -834,11 +844,11 @@ EXPORT_SYMBOL_GPL(__irq_alloc_descs); * irq_get_next_irq - get next allocated irq number * @offset: where to start the search * - * Returns next irq number after offset or nr_irqs if none is found. + * Returns next irq number at or after offset or nr_irqs if none is found. */ unsigned int irq_get_next_irq(unsigned int offset) { - return find_next_bit(allocated_irqs, nr_irqs, offset); + return irq_find_at_or_after(offset); } struct irq_desc * -- cgit v1.2.3 From 721255b9826bd11c7a38b585905fc2dd0fb94e52 Mon Sep 17 00:00:00 2001 From: Shanker Donthineni Date: Fri, 19 May 2023 08:49:02 -0500 Subject: genirq: Use a maple tree for interrupt descriptor management The current implementation uses a static bitmap for interrupt descriptor allocation and a radix tree to pointer store the pointer for lookup. However, the size of the bitmap is constrained by the build time macro MAX_SPARSE_IRQS, which may not be sufficient to support high-end servers, particularly those with GICv4.1 hardware, which require a large interrupt space to cover LPIs and vSGIs. Replace the bitmap and the radix tree with a maple tree, which not only stores pointers for lookup, but also provides a mechanism to find free ranges. That removes the build time hardcoded upper limit. Signed-off-by: Shanker Donthineni Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230519134902.1495562-4-sdonthineni@nvidia.com --- kernel/irq/internals.h | 2 +- kernel/irq/irqdesc.c | 57 ++++++++++++++++++++++++++++---------------------- 2 files changed, 33 insertions(+), 26 deletions(-) (limited to 'kernel/irq/internals.h') diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index f3f2090dd2de..7bdb7507efb0 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -12,7 +12,7 @@ #include #ifdef CONFIG_SPARSE_IRQ -# define MAX_SPARSE_IRQS (NR_IRQS + 8196) +# define MAX_SPARSE_IRQS INT_MAX #else # define MAX_SPARSE_IRQS NR_IRQS #endif diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index e0d9dd9b36f9..27ca1c866f29 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -12,8 +12,7 @@ #include #include #include -#include -#include +#include #include #include @@ -131,17 +130,39 @@ int nr_irqs = NR_IRQS; EXPORT_SYMBOL_GPL(nr_irqs); static DEFINE_MUTEX(sparse_irq_lock); -static DECLARE_BITMAP(allocated_irqs, MAX_SPARSE_IRQS); +static struct maple_tree sparse_irqs = MTREE_INIT_EXT(sparse_irqs, + MT_FLAGS_ALLOC_RANGE | + MT_FLAGS_LOCK_EXTERN | + MT_FLAGS_USE_RCU, + sparse_irq_lock); static int irq_find_free_area(unsigned int from, unsigned int cnt) { - return bitmap_find_next_zero_area(allocated_irqs, MAX_SPARSE_IRQS, - from, cnt, 0); + MA_STATE(mas, &sparse_irqs, 0, 0); + + if (mas_empty_area(&mas, from, MAX_SPARSE_IRQS, cnt)) + return -ENOSPC; + return mas.index; } static unsigned int irq_find_at_or_after(unsigned int offset) { - return find_next_bit(allocated_irqs, nr_irqs, offset); + unsigned long index = offset; + struct irq_desc *desc = mt_find(&sparse_irqs, &index, nr_irqs); + + return desc ? irq_desc_get_irq(desc) : nr_irqs; +} + +static void irq_insert_desc(unsigned int irq, struct irq_desc *desc) +{ + MA_STATE(mas, &sparse_irqs, irq, irq); + WARN_ON(mas_store_gfp(&mas, desc, GFP_KERNEL) != 0); +} + +static void delete_irq_desc(unsigned int irq) +{ + MA_STATE(mas, &sparse_irqs, irq, irq); + mas_erase(&mas); } #ifdef CONFIG_SPARSE_IRQ @@ -355,26 +376,14 @@ static void irq_sysfs_del(struct irq_desc *desc) {} #endif /* CONFIG_SYSFS */ -static RADIX_TREE(irq_desc_tree, GFP_KERNEL); - -static void irq_insert_desc(unsigned int irq, struct irq_desc *desc) -{ - radix_tree_insert(&irq_desc_tree, irq, desc); -} - struct irq_desc *irq_to_desc(unsigned int irq) { - return radix_tree_lookup(&irq_desc_tree, irq); + return mtree_load(&sparse_irqs, irq); } #ifdef CONFIG_KVM_BOOK3S_64_HV_MODULE EXPORT_SYMBOL_GPL(irq_to_desc); #endif -static void delete_irq_desc(unsigned int irq) -{ - radix_tree_delete(&irq_desc_tree, irq); -} - #ifdef CONFIG_SMP static void free_masks(struct irq_desc *desc) { @@ -517,7 +526,6 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node, irq_sysfs_add(start + i, desc); irq_add_debugfs_entry(start + i, desc); } - bitmap_set(allocated_irqs, start, cnt); return start; err: @@ -557,7 +565,6 @@ int __init early_irq_init(void) for (i = 0; i < initcnt; i++) { desc = alloc_desc(i, node, 0, NULL, NULL); - set_bit(i, allocated_irqs); irq_insert_desc(i, desc); } return arch_early_irq_init(); @@ -612,6 +619,7 @@ static void free_desc(unsigned int irq) raw_spin_lock_irqsave(&desc->lock, flags); desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL, NULL); raw_spin_unlock_irqrestore(&desc->lock, flags); + delete_irq_desc(irq); } static inline int alloc_descs(unsigned int start, unsigned int cnt, int node, @@ -624,8 +632,8 @@ static inline int alloc_descs(unsigned int start, unsigned int cnt, int node, struct irq_desc *desc = irq_to_desc(start + i); desc->owner = owner; + irq_insert_desc(start + i, desc); } - bitmap_set(allocated_irqs, start, cnt); return start; } @@ -637,7 +645,7 @@ static int irq_expand_nr_irqs(unsigned int nr) void irq_mark_irq(unsigned int irq) { mutex_lock(&sparse_irq_lock); - bitmap_set(allocated_irqs, irq, 1); + irq_insert_desc(irq, irq_desc + irq); mutex_unlock(&sparse_irq_lock); } @@ -781,7 +789,6 @@ void irq_free_descs(unsigned int from, unsigned int cnt) for (i = 0; i < cnt; i++) free_desc(from + i); - bitmap_clear(allocated_irqs, from, cnt); mutex_unlock(&sparse_irq_lock); } EXPORT_SYMBOL_GPL(irq_free_descs); @@ -844,7 +851,7 @@ EXPORT_SYMBOL_GPL(__irq_alloc_descs); * irq_get_next_irq - get next allocated irq number * @offset: where to start the search * - * Returns next irq number at or after offset or nr_irqs if none is found. + * Returns next irq number after offset or nr_irqs if none is found. */ unsigned int irq_get_next_irq(unsigned int offset) { -- cgit v1.2.3 From 7cc148a32f1e7496e22c0005dd113a31d4a3b3d4 Mon Sep 17 00:00:00 2001 From: James Gowans Date: Thu, 8 Jun 2023 14:00:19 +0200 Subject: genirq: Expand doc for PENDING and REPLAY flags Adding a bit more info about what the flags are used for may help future code readers. Signed-off-by: James Gowans Cc: Thomas Gleixner Cc: Marc Zyngier Cc: Liao Chang Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230608120021.3273400-2-jgowans@amazon.com --- kernel/irq/internals.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'kernel/irq/internals.h') diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 5fdc0b557579..c443a0ddc07e 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -47,9 +47,12 @@ enum { * detection * IRQS_POLL_INPROGRESS - polling in progress * IRQS_ONESHOT - irq is not unmasked in primary handler - * IRQS_REPLAY - irq is replayed + * IRQS_REPLAY - irq has been resent and will not be resent + * again until the handler has run and cleared + * this flag. * IRQS_WAITING - irq is waiting - * IRQS_PENDING - irq is pending and replayed later + * IRQS_PENDING - irq needs to be resent and should be resent + * at the next available opportunity. * IRQS_SUSPENDED - irq is suspended * IRQS_NMI - irq line is used to deliver NMIs * IRQS_SYSFS - descriptor has been added to sysfs -- cgit v1.2.3