diff options
Diffstat (limited to 'lib')
-rw-r--r-- | lib/Kconfig | 4 | ||||
-rw-r--r-- | lib/Kconfig.debug | 1 | ||||
-rw-r--r-- | lib/Kconfig.kasan | 8 | ||||
-rw-r--r-- | lib/cpumask.c | 102 | ||||
-rw-r--r-- | lib/devres.c | 28 | ||||
-rw-r--r-- | lib/find_last_bit.c | 41 | ||||
-rw-r--r-- | lib/iommu-common.c | 192 | ||||
-rw-r--r-- | lib/percpu_counter.c | 6 | ||||
-rw-r--r-- | lib/raid6/algos.c | 41 | ||||
-rw-r--r-- | lib/raid6/altivec.uc | 1 | ||||
-rw-r--r-- | lib/raid6/avx2.c | 3 | ||||
-rw-r--r-- | lib/raid6/int.uc | 41 | ||||
-rw-r--r-- | lib/raid6/mmx.c | 2 | ||||
-rw-r--r-- | lib/raid6/neon.c | 1 | ||||
-rw-r--r-- | lib/raid6/sse1.c | 2 | ||||
-rw-r--r-- | lib/raid6/sse2.c | 227 | ||||
-rw-r--r-- | lib/raid6/test/test.c | 51 | ||||
-rw-r--r-- | lib/raid6/tilegx.uc | 1 | ||||
-rw-r--r-- | lib/rhashtable.c | 31 | ||||
-rw-r--r-- | lib/string.c | 2 | ||||
-rw-r--r-- | lib/strnlen_user.c | 12 | ||||
-rw-r--r-- | lib/swiotlb.c | 5 | ||||
-rw-r--r-- | lib/test-hexdump.c | 2 | ||||
-rw-r--r-- | lib/test_bpf.c | 2664 | ||||
-rw-r--r-- | lib/test_rhashtable.c | 215 |
25 files changed, 3344 insertions, 339 deletions
diff --git a/lib/Kconfig b/lib/Kconfig index f5440221d929..601965a948e8 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -396,10 +396,6 @@ config CPUMASK_OFFSTACK them on the stack. This is a bit more expensive, but avoids stack overflow. -config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS - bool "Disable obsolete cpumask functions" if DEBUG_PER_CPU_MAPS - depends on BROKEN - config CPU_RMAP bool depends on SMP diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 17670573dda8..ba2b0c87e65b 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1281,6 +1281,7 @@ config RCU_TORTURE_TEST_SLOW_INIT_DELAY int "How much to slow down RCU grace-period initialization" range 0 5 default 3 + depends on RCU_TORTURE_TEST_SLOW_INIT help This option specifies the number of jiffies to wait between each rcu_node structure initialization. diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index 4fecaedc80a2..777eda7d1ab4 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -10,8 +10,11 @@ config KASAN help Enables kernel address sanitizer - runtime memory debugger, designed to find out-of-bounds accesses and use-after-free bugs. - This is strictly debugging feature. It consumes about 1/8 - of available memory and brings about ~x3 performance slowdown. + This is strictly a debugging feature and it requires a gcc version + of 4.9.2 or later. Detection of out of bounds accesses to stack or + global variables requires gcc 5.0 or later. + This feature consumes about 1/8 of available memory and brings about + ~x3 performance slowdown. For better error detection enable CONFIG_STACKTRACE, and add slub_debug=U to boot cmdline. @@ -40,6 +43,7 @@ config KASAN_INLINE memory accesses. This is faster than outline (in some workloads it gives about x2 boost over outline instrumentation), but make kernel's .text size much bigger. + This requires a gcc version of 5.0 or later. endchoice diff --git a/lib/cpumask.c b/lib/cpumask.c index 5ab1553fd076..5f627084f2e9 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -5,27 +5,6 @@ #include <linux/export.h> #include <linux/bootmem.h> -int __first_cpu(const cpumask_t *srcp) -{ - return min_t(int, NR_CPUS, find_first_bit(srcp->bits, NR_CPUS)); -} -EXPORT_SYMBOL(__first_cpu); - -int __next_cpu(int n, const cpumask_t *srcp) -{ - return min_t(int, NR_CPUS, find_next_bit(srcp->bits, NR_CPUS, n+1)); -} -EXPORT_SYMBOL(__next_cpu); - -#if NR_CPUS > 64 -int __next_cpu_nr(int n, const cpumask_t *srcp) -{ - return min_t(int, nr_cpu_ids, - find_next_bit(srcp->bits, nr_cpu_ids, n+1)); -} -EXPORT_SYMBOL(__next_cpu_nr); -#endif - /** * cpumask_next_and - get the next cpu in *src1p & *src2p * @n: the cpu prior to the place to search (ie. return will be > @n) @@ -90,13 +69,6 @@ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) dump_stack(); } #endif - /* FIXME: Bandaid to save us from old primitives which go to NR_CPUS. */ - if (*mask) { - unsigned char *ptr = (unsigned char *)cpumask_bits(*mask); - unsigned int tail; - tail = BITS_TO_LONGS(NR_CPUS - nr_cpumask_bits) * sizeof(long); - memset(ptr + cpumask_size() - tail, 0, tail); - } return *mask != NULL; } @@ -167,64 +139,42 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask) #endif /** - * cpumask_set_cpu_local_first - set i'th cpu with local numa cpu's first - * + * cpumask_local_spread - select the i'th cpu with local numa cpu's first * @i: index number - * @numa_node: local numa_node - * @dstp: cpumask with the relevant cpu bit set according to the policy + * @node: local numa_node * - * This function sets the cpumask according to a numa aware policy. - * cpumask could be used as an affinity hint for the IRQ related to a - * queue. When the policy is to spread queues across cores - local cores - * first. + * This function selects an online CPU according to a numa aware policy; + * local cpus are returned first, followed by non-local ones, then it + * wraps around. * - * Returns 0 on success, -ENOMEM for no memory, and -EAGAIN when failed to set - * the cpu bit and need to re-call the function. + * It's not very efficient, but useful for setup. */ -int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp) +unsigned int cpumask_local_spread(unsigned int i, int node) { - cpumask_var_t mask; int cpu; - int ret = 0; - - if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) - return -ENOMEM; + /* Wrap: we always want a cpu. */ i %= num_online_cpus(); - if (numa_node == -1 || !cpumask_of_node(numa_node)) { - /* Use all online cpu's for non numa aware system */ - cpumask_copy(mask, cpu_online_mask); + if (node == -1) { + for_each_cpu(cpu, cpu_online_mask) + if (i-- == 0) + return cpu; } else { - int n; - - cpumask_and(mask, - cpumask_of_node(numa_node), cpu_online_mask); - - n = cpumask_weight(mask); - if (i >= n) { - i -= n; - - /* If index > number of local cpu's, mask out local - * cpu's - */ - cpumask_andnot(mask, cpu_online_mask, mask); + /* NUMA first. */ + for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask) + if (i-- == 0) + return cpu; + + for_each_cpu(cpu, cpu_online_mask) { + /* Skip NUMA nodes, done above. */ + if (cpumask_test_cpu(cpu, cpumask_of_node(node))) + continue; + + if (i-- == 0) + return cpu; } } - - for_each_cpu(cpu, mask) { - if (--i < 0) - goto out; - } - - ret = -EAGAIN; - -out: - free_cpumask_var(mask); - - if (!ret) - cpumask_set_cpu(cpu, dstp); - - return ret; + BUG(); } -EXPORT_SYMBOL(cpumask_set_cpu_local_first); +EXPORT_SYMBOL(cpumask_local_spread); diff --git a/lib/devres.c b/lib/devres.c index 0f1dd2e9d2c1..fbe2aac522e6 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -72,6 +72,34 @@ void __iomem *devm_ioremap_nocache(struct device *dev, resource_size_t offset, EXPORT_SYMBOL(devm_ioremap_nocache); /** + * devm_ioremap_wc - Managed ioremap_wc() + * @dev: Generic device to remap IO address for + * @offset: BUS offset to map + * @size: Size of map + * + * Managed ioremap_wc(). Map is automatically unmapped on driver detach. + */ +void __iomem *devm_ioremap_wc(struct device *dev, resource_size_t offset, + resource_size_t size) +{ + void __iomem **ptr, *addr; + + ptr = devres_alloc(devm_ioremap_release, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return NULL; + + addr = ioremap_wc(offset, size); + if (addr) { + *ptr = addr; + devres_add(dev, ptr); + } else + devres_free(ptr); + + return addr; +} +EXPORT_SYMBOL(devm_ioremap_wc); + +/** * devm_iounmap - Managed iounmap() * @dev: Generic device to unmap for * @addr: Address to unmap diff --git a/lib/find_last_bit.c b/lib/find_last_bit.c deleted file mode 100644 index 3e3be40c6a6e..000000000000 --- a/lib/find_last_bit.c +++ /dev/null @@ -1,41 +0,0 @@ -/* find_last_bit.c: fallback find next bit implementation - * - * Copyright (C) 2008 IBM Corporation - * Written by Rusty Russell <rusty@rustcorp.com.au> - * (Inspired by David Howell's find_next_bit implementation) - * - * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease - * size and improve performance, 2015. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/bitops.h> -#include <linux/bitmap.h> -#include <linux/export.h> -#include <linux/kernel.h> - -#ifndef find_last_bit - -unsigned long find_last_bit(const unsigned long *addr, unsigned long size) -{ - if (size) { - unsigned long val = BITMAP_LAST_WORD_MASK(size); - unsigned long idx = (size-1) / BITS_PER_LONG; - - do { - val &= addr[idx]; - if (val) - return idx * BITS_PER_LONG + __fls(val); - - val = ~0ul; - } while (idx--); - } - return size; -} -EXPORT_SYMBOL(find_last_bit); - -#endif diff --git a/lib/iommu-common.c b/lib/iommu-common.c index fac4f35250c9..df30632f0bef 100644 --- a/lib/iommu-common.c +++ b/lib/iommu-common.c @@ -9,37 +9,72 @@ #include <linux/iommu-helper.h> #include <linux/iommu-common.h> #include <linux/dma-mapping.h> +#include <linux/hash.h> #ifndef DMA_ERROR_CODE #define DMA_ERROR_CODE (~(dma_addr_t)0x0) #endif -#define IOMMU_LARGE_ALLOC 15 +static unsigned long iommu_large_alloc = 15; + +static DEFINE_PER_CPU(unsigned int, iommu_hash_common); + +static inline bool need_flush(struct iommu_map_table *iommu) +{ + return (iommu->lazy_flush != NULL && + (iommu->flags & IOMMU_NEED_FLUSH) != 0); +} + +static inline void set_flush(struct iommu_map_table *iommu) +{ + iommu->flags |= IOMMU_NEED_FLUSH; +} + +static inline void clear_flush(struct iommu_map_table *iommu) +{ + iommu->flags &= ~IOMMU_NEED_FLUSH; +} + +static void setup_iommu_pool_hash(void) +{ + unsigned int i; + static bool do_once; + + if (do_once) + return; + do_once = true; + for_each_possible_cpu(i) + per_cpu(iommu_hash_common, i) = hash_32(i, IOMMU_POOL_HASHBITS); +} /* - * Initialize iommu_pool entries for the iommu_table. `num_entries' + * Initialize iommu_pool entries for the iommu_map_table. `num_entries' * is the number of table entries. If `large_pool' is set to true, * the top 1/4 of the table will be set aside for pool allocations - * of more than IOMMU_LARGE_ALLOC pages. + * of more than iommu_large_alloc pages. */ -extern void iommu_tbl_pool_init(struct iommu_table *iommu, - unsigned long num_entries, - u32 page_table_shift, - const struct iommu_tbl_ops *iommu_tbl_ops, - bool large_pool, u32 npools) +void iommu_tbl_pool_init(struct iommu_map_table *iommu, + unsigned long num_entries, + u32 table_shift, + void (*lazy_flush)(struct iommu_map_table *), + bool large_pool, u32 npools, + bool skip_span_boundary_check) { unsigned int start, i; struct iommu_pool *p = &(iommu->large_pool); + setup_iommu_pool_hash(); if (npools == 0) iommu->nr_pools = IOMMU_NR_POOLS; else iommu->nr_pools = npools; BUG_ON(npools > IOMMU_NR_POOLS); - iommu->page_table_shift = page_table_shift; - iommu->iommu_tbl_ops = iommu_tbl_ops; + iommu->table_shift = table_shift; + iommu->lazy_flush = lazy_flush; start = 0; + if (skip_span_boundary_check) + iommu->flags |= IOMMU_NO_SPAN_BOUND; if (large_pool) iommu->flags |= IOMMU_HAS_LARGE_POOL; @@ -48,11 +83,11 @@ extern void iommu_tbl_pool_init(struct iommu_table *iommu, else iommu->poolsize = (num_entries * 3 / 4)/iommu->nr_pools; for (i = 0; i < iommu->nr_pools; i++) { - spin_lock_init(&(iommu->arena_pool[i].lock)); - iommu->arena_pool[i].start = start; - iommu->arena_pool[i].hint = start; + spin_lock_init(&(iommu->pools[i].lock)); + iommu->pools[i].start = start; + iommu->pools[i].hint = start; start += iommu->poolsize; /* start for next pool */ - iommu->arena_pool[i].end = start - 1; + iommu->pools[i].end = start - 1; } if (!large_pool) return; @@ -65,121 +100,136 @@ extern void iommu_tbl_pool_init(struct iommu_table *iommu, EXPORT_SYMBOL(iommu_tbl_pool_init); unsigned long iommu_tbl_range_alloc(struct device *dev, - struct iommu_table *iommu, + struct iommu_map_table *iommu, unsigned long npages, unsigned long *handle, - unsigned int pool_hash) + unsigned long mask, + unsigned int align_order) { + unsigned int pool_hash = __this_cpu_read(iommu_hash_common); unsigned long n, end, start, limit, boundary_size; - struct iommu_pool *arena; + struct iommu_pool *pool; int pass = 0; unsigned int pool_nr; unsigned int npools = iommu->nr_pools; unsigned long flags; bool large_pool = ((iommu->flags & IOMMU_HAS_LARGE_POOL) != 0); - bool largealloc = (large_pool && npages > IOMMU_LARGE_ALLOC); + bool largealloc = (large_pool && npages > iommu_large_alloc); unsigned long shift; + unsigned long align_mask = 0; + + if (align_order > 0) + align_mask = 0xffffffffffffffffl >> (64 - align_order); /* Sanity check */ if (unlikely(npages == 0)) { - printk_ratelimited("npages == 0\n"); + WARN_ON_ONCE(1); return DMA_ERROR_CODE; } if (largealloc) { - arena = &(iommu->large_pool); - spin_lock_irqsave(&arena->lock, flags); + pool = &(iommu->large_pool); pool_nr = 0; /* to keep compiler happy */ } else { /* pick out pool_nr */ pool_nr = pool_hash & (npools - 1); - arena = &(iommu->arena_pool[pool_nr]); - - /* find first available unlocked pool */ - while (!spin_trylock_irqsave(&(arena->lock), flags)) { - pool_nr = (pool_nr + 1) & (iommu->nr_pools - 1); - arena = &(iommu->arena_pool[pool_nr]); - } + pool = &(iommu->pools[pool_nr]); } + spin_lock_irqsave(&pool->lock, flags); again: if (pass == 0 && handle && *handle && - (*handle >= arena->start) && (*handle < arena->end)) + (*handle >= pool->start) && (*handle < pool->end)) start = *handle; else - start = arena->hint; + start = pool->hint; - limit = arena->end; + limit = pool->end; /* The case below can happen if we have a small segment appended * to a large, or when the previous alloc was at the very end of - * the available space. If so, go back to the beginning and flush. + * the available space. If so, go back to the beginning. If a + * flush is needed, it will get done based on the return value + * from iommu_area_alloc() below. */ - if (start >= limit) { - start = arena->start; - if (iommu->iommu_tbl_ops->reset != NULL) - iommu->iommu_tbl_ops->reset(iommu); + if (start >= limit) + start = pool->start; + shift = iommu->table_map_base >> iommu->table_shift; + if (limit + shift > mask) { + limit = mask - shift + 1; + /* If we're constrained on address range, first try + * at the masked hint to avoid O(n) search complexity, + * but on second pass, start at 0 in pool 0. + */ + if ((start & mask) >= limit || pass > 0) { + spin_unlock(&(pool->lock)); + pool = &(iommu->pools[0]); + spin_lock(&(pool->lock)); + start = pool->start; + } else { + start &= mask; + } } if (dev) boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1, - 1 << iommu->page_table_shift); + 1 << iommu->table_shift); else - boundary_size = ALIGN(1ULL << 32, 1 << iommu->page_table_shift); + boundary_size = ALIGN(1ULL << 32, 1 << iommu->table_shift); - shift = iommu->page_table_map_base >> iommu->page_table_shift; - boundary_size = boundary_size >> iommu->page_table_shift; + boundary_size = boundary_size >> iommu->table_shift; /* - * if the iommu has a non-trivial cookie <-> index mapping, we set + * if the skip_span_boundary_check had been set during init, we set * things up so that iommu_is_span_boundary() merely checks if the * (index + npages) < num_tsb_entries */ - if (iommu->iommu_tbl_ops->cookie_to_index != NULL) { + if ((iommu->flags & IOMMU_NO_SPAN_BOUND) != 0) { shift = 0; boundary_size = iommu->poolsize * iommu->nr_pools; } n = iommu_area_alloc(iommu->map, limit, start, npages, shift, - boundary_size, 0); + boundary_size, align_mask); if (n == -1) { if (likely(pass == 0)) { /* First failure, rescan from the beginning. */ - arena->hint = arena->start; - if (iommu->iommu_tbl_ops->reset != NULL) - iommu->iommu_tbl_ops->reset(iommu); + pool->hint = pool->start; + set_flush(iommu); pass++; goto again; } else if (!largealloc && pass <= iommu->nr_pools) { - spin_unlock(&(arena->lock)); + spin_unlock(&(pool->lock)); pool_nr = (pool_nr + 1) & (iommu->nr_pools - 1); - arena = &(iommu->arena_pool[pool_nr]); - while (!spin_trylock(&(arena->lock))) { - pool_nr = (pool_nr + 1) & (iommu->nr_pools - 1); - arena = &(iommu->arena_pool[pool_nr]); - } - arena->hint = arena->start; + pool = &(iommu->pools[pool_nr]); + spin_lock(&(pool->lock)); + pool->hint = pool->start; + set_flush(iommu); pass++; goto again; } else { /* give up */ - spin_unlock_irqrestore(&(arena->lock), flags); - return DMA_ERROR_CODE; + n = DMA_ERROR_CODE; + goto bail; } } + if (n < pool->hint || need_flush(iommu)) { + clear_flush(iommu); + iommu->lazy_flush(iommu); + } end = n + npages; - - arena->hint = end; + pool->hint = end; /* Update handle for SG allocations */ if (handle) *handle = end; - spin_unlock_irqrestore(&(arena->lock), flags); +bail: + spin_unlock_irqrestore(&(pool->lock), flags); return n; } EXPORT_SYMBOL(iommu_tbl_range_alloc); -static struct iommu_pool *get_pool(struct iommu_table *tbl, +static struct iommu_pool *get_pool(struct iommu_map_table *tbl, unsigned long entry) { struct iommu_pool *p; @@ -193,31 +243,27 @@ static struct iommu_pool *get_pool(struct iommu_table *tbl, unsigned int pool_nr = entry / tbl->poolsize; BUG_ON(pool_nr >= tbl->nr_pools); - p = &tbl->arena_pool[pool_nr]; + p = &tbl->pools[pool_nr]; } return p; } -void iommu_tbl_range_free(struct iommu_table *iommu, u64 dma_addr, - unsigned long npages, bool do_demap, void *demap_arg) +/* Caller supplies the index of the entry into the iommu map table + * itself when the mapping from dma_addr to the entry is not the + * default addr->entry mapping below. + */ +void iommu_tbl_range_free(struct iommu_map_table *iommu, u64 dma_addr, + unsigned long npages, unsigned long entry) { - unsigned long entry; struct iommu_pool *pool; unsigned long flags; - unsigned long shift = iommu->page_table_shift; + unsigned long shift = iommu->table_shift; - if (iommu->iommu_tbl_ops->cookie_to_index != NULL) { - entry = (*iommu->iommu_tbl_ops->cookie_to_index)(dma_addr, - demap_arg); - } else { - entry = (dma_addr - iommu->page_table_map_base) >> shift; - } + if (entry == DMA_ERROR_CODE) /* use default addr->entry mapping */ + entry = (dma_addr - iommu->table_map_base) >> shift; pool = get_pool(iommu, entry); spin_lock_irqsave(&(pool->lock), flags); - if (do_demap && iommu->iommu_tbl_ops->demap != NULL) - (*iommu->iommu_tbl_ops->demap)(demap_arg, entry, npages); - bitmap_clear(iommu->map, entry, npages); spin_unlock_irqrestore(&(pool->lock), flags); } diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 48144cdae819..f051d69f0910 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -197,13 +197,13 @@ static int percpu_counter_hotcpu_callback(struct notifier_block *nb, * Compare counter against given value. * Return 1 if greater, 0 if equal and -1 if less */ -int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) +int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { s64 count; count = percpu_counter_read(fbc); /* Check to see if rough count will be sufficient for comparison */ - if (abs(count - rhs) > (percpu_counter_batch*num_online_cpus())) { + if (abs(count - rhs) > (batch * num_online_cpus())) { if (count > rhs) return 1; else @@ -218,7 +218,7 @@ int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) else return 0; } -EXPORT_SYMBOL(percpu_counter_compare); +EXPORT_SYMBOL(__percpu_counter_compare); static int __init percpu_counter_startup(void) { diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c index dbef2314901e..975c6e0434bd 100644 --- a/lib/raid6/algos.c +++ b/lib/raid6/algos.c @@ -131,11 +131,12 @@ static inline const struct raid6_recov_calls *raid6_choose_recov(void) static inline const struct raid6_calls *raid6_choose_gen( void *(*const dptrs)[(65536/PAGE_SIZE)+2], const int disks) { - unsigned long perf, bestperf, j0, j1; + unsigned long perf, bestgenperf, bestxorperf, j0, j1; + int start = (disks>>1)-1, stop = disks-3; /* work on the second half of the disks */ const struct raid6_calls *const *algo; const struct raid6_calls *best; - for (bestperf = 0, best = NULL, algo = raid6_algos; *algo; algo++) { + for (bestgenperf = 0, bestxorperf = 0, best = NULL, algo = raid6_algos; *algo; algo++) { if (!best || (*algo)->prefer >= best->prefer) { if ((*algo)->valid && !(*algo)->valid()) continue; @@ -153,19 +154,45 @@ static inline const struct raid6_calls *raid6_choose_gen( } preempt_enable(); - if (perf > bestperf) { - bestperf = perf; + if (perf > bestgenperf) { + bestgenperf = perf; best = *algo; } - pr_info("raid6: %-8s %5ld MB/s\n", (*algo)->name, + pr_info("raid6: %-8s gen() %5ld MB/s\n", (*algo)->name, (perf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2)); + + if (!(*algo)->xor_syndrome) + continue; + + perf = 0; + + preempt_disable(); + j0 = jiffies; + while ((j1 = jiffies) == j0) + cpu_relax(); + while (time_before(jiffies, + j1 + (1<<RAID6_TIME_JIFFIES_LG2))) { + (*algo)->xor_syndrome(disks, start, stop, + PAGE_SIZE, *dptrs); + perf++; + } + preempt_enable(); + + if (best == *algo) + bestxorperf = perf; + + pr_info("raid6: %-8s xor() %5ld MB/s\n", (*algo)->name, + (perf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2+1)); } } if (best) { - pr_info("raid6: using algorithm %s (%ld MB/s)\n", + pr_info("raid6: using algorithm %s gen() %ld MB/s\n", best->name, - (bestperf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2)); + (bestgenperf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2)); + if (best->xor_syndrome) + pr_info("raid6: .... xor() %ld MB/s, rmw enabled\n", + (bestxorperf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2+1)); raid6_call = *best; } else pr_err("raid6: Yikes! No algorithm found!\n"); diff --git a/lib/raid6/altivec.uc b/lib/raid6/altivec.uc index 7cc12b532e95..bec27fce7501 100644 --- a/lib/raid6/altivec.uc +++ b/lib/raid6/altivec.uc @@ -119,6 +119,7 @@ int raid6_have_altivec(void) const struct raid6_calls raid6_altivec$# = { raid6_altivec$#_gen_syndrome, + NULL, /* XOR not yet implemented */ raid6_have_altivec, "altivecx$#", 0 diff --git a/lib/raid6/avx2.c b/lib/raid6/avx2.c index bc3b1dd436eb..76734004358d 100644 --- a/lib/raid6/avx2.c +++ b/lib/raid6/avx2.c @@ -89,6 +89,7 @@ static void raid6_avx21_gen_syndrome(int disks, size_t bytes, void **ptrs) const struct raid6_calls raid6_avx2x1 = { raid6_avx21_gen_syndrome, + NULL, /* XOR not yet implemented */ raid6_have_avx2, "avx2x1", 1 /* Has cache hints */ @@ -150,6 +151,7 @@ static void raid6_avx22_gen_syndrome(int disks, size_t bytes, void **ptrs) const struct raid6_calls raid6_avx2x2 = { raid6_avx22_gen_syndrome, + NULL, /* XOR not yet implemented */ raid6_have_avx2, "avx2x2", 1 /* Has cache hints */ @@ -242,6 +244,7 @@ static void raid6_avx24_gen_syndrome(int disks, size_t bytes, void **ptrs) const struct raid6_calls raid6_avx2x4 = { raid6_avx24_gen_syndrome, + NULL, /* XOR not yet implemented */ raid6_have_avx2, "avx2x4", 1 /* Has cache hints */ diff --git a/lib/raid6/int.uc b/lib/raid6/int.uc index 5b50f8dfc5d2..558aeac9342a 100644 --- a/lib/raid6/int.uc +++ b/lib/raid6/int.uc @@ -107,9 +107,48 @@ static void raid6_int$#_gen_syndrome(int disks, size_t bytes, void **ptrs) } } +static void raid6_int$#_xor_syndrome(int disks, int start, int stop, + size_t bytes, void **ptrs) +{ + u8 **dptr = (u8 **)ptrs; + u8 *p, *q; + int d, z, z0; + + unative_t wd$$, wq$$, wp$$, w1$$, w2$$; + + z0 = stop; /* P/Q right side optimization */ + p = dptr[disks-2]; /* XOR parity */ + q = dptr[disks-1]; /* RS syndrome */ + + for ( d = 0 ; d < bytes ; d += NSIZE*$# ) { + /* P/Q data pages */ + wq$$ = wp$$ = *(unative_t *)&dptr[z0][d+$$*NSIZE]; + for ( z = z0-1 ; z >= start ; z-- ) { + wd$$ = *(unative_t *)&dptr[z][d+$$*NSIZE]; + wp$$ ^= wd$$; + w2$$ = MASK(wq$$); + w1$$ = SHLBYTE(wq$$); + w2$$ &= NBYTES(0x1d); + w1$$ ^= w2$$; + wq$$ = w1$$ ^ wd$$; + } + /* P/Q left side optimization */ + for ( z = start-1 ; z >= 0 ; z-- ) { + w2$$ = MASK(wq$$); + w1$$ = SHLBYTE(wq$$); + w2$$ &= NBYTES(0x1d); + wq$$ = w1$$ ^ w2$$; + } + *(unative_t *)&p[d+NSIZE*$$] ^= wp$$; + *(unative_t *)&q[d+NSIZE*$$] ^= wq$$; + } + +} + const struct raid6_calls raid6_intx$# = { raid6_int$#_gen_syndrome, - NULL, /* always valid */ + raid6_int$#_xor_syndrome, + NULL, /* always valid */ "int" NSTRING "x$#", 0 }; diff --git a/lib/raid6/mmx.c b/lib/raid6/mmx.c index 590c71c9e200..b3b0e1fcd3af 100644 --- a/lib/raid6/mmx.c +++ b/lib/raid6/mmx.c @@ -76,6 +76,7 @@ static void raid6_mmx1_gen_syndrome(int disks, size_t bytes, void **ptrs) const struct raid6_calls raid6_mmxx1 = { raid6_mmx1_gen_syndrome, + NULL, /* XOR not yet implemented */ raid6_have_mmx, "mmxx1", 0 @@ -134,6 +135,7 @@ static void raid6_mmx2_gen_syndrome(int disks, size_t bytes, void **ptrs) const struct raid6_calls raid6_mmxx2 = { raid6_mmx2_gen_syndrome, + NULL, /* XOR not yet implemented */ raid6_have_mmx, "mmxx2", 0 diff --git a/lib/raid6/neon.c b/lib/raid6/neon.c index 36ad4705df1a..d9ad6ee284f4 100644 --- a/lib/raid6/neon.c +++ b/lib/raid6/neon.c @@ -42,6 +42,7 @@ } \ struct raid6_calls const raid6_neonx ## _n = { \ raid6_neon ## _n ## _gen_syndrome, \ + NULL, /* XOR not yet implemented */ \ raid6_have_neon, \ "neonx" #_n, \ 0 \ diff --git a/lib/raid6/sse1.c b/lib/raid6/sse1.c index f76297139445..9025b8ca9aa3 100644 --- a/lib/raid6/sse1.c +++ b/lib/raid6/sse1.c @@ -92,6 +92,7 @@ static void raid6_sse11_gen_syndrome(int disks, size_t bytes, void **ptrs) const struct raid6_calls raid6_sse1x1 = { raid6_sse11_gen_syndrome, + NULL, /* XOR not yet implemented */ raid6_have_sse1_or_mmxext, "sse1x1", 1 /* Has cache hints */ @@ -154,6 +155,7 @@ static void raid6_sse12_gen_syndrome(int disks, size_t bytes, void **ptrs) const struct raid6_calls raid6_sse1x2 = { raid6_sse12_gen_syndrome, + NULL, /* XOR not yet implemented */ raid6_have_sse1_or_mmxext, "sse1x2", 1 /* Has cache hints */ diff --git a/lib/raid6/sse2.c b/lib/raid6/sse2.c index 85b82c85f28e..1d2276b007ee 100644 --- a/lib/raid6/sse2.c +++ b/lib/raid6/sse2.c @@ -88,8 +88,58 @@ static void raid6_sse21_gen_syndrome(int disks, size_t bytes, void **ptrs) kernel_fpu_end(); } + +static void raid6_sse21_xor_syndrome(int disks, int start, int stop, + size_t bytes, void **ptrs) + { + u8 **dptr = (u8 **)ptrs; + u8 *p, *q; + int d, z, z0; + + z0 = stop; /* P/Q right side optimization */ + p = dptr[disks-2]; /* XOR parity */ + q = dptr[disks-1]; /* RS syndrome */ + + kernel_fpu_begin(); + + asm volatile("movdqa %0,%%xmm0" : : "m" (raid6_sse_constants.x1d[0])); + + for ( d = 0 ; d < bytes ; d += 16 ) { + asm volatile("movdqa %0,%%xmm4" :: "m" (dptr[z0][d])); + asm volatile("movdqa %0,%%xmm2" : : "m" (p[d])); + asm volatile("pxor %xmm4,%xmm2"); + /* P/Q data pages */ + for ( z = z0-1 ; z >= start ; z-- ) { + asm volatile("pxor %xmm5,%xmm5"); + asm volatile("pcmpgtb %xmm4,%xmm5"); + asm volatile("paddb %xmm4,%xmm4"); + asm volatile("pand %xmm0,%xmm5"); + asm volatile("pxor %xmm5,%xmm4"); + asm volatile("movdqa %0,%%xmm5" :: "m" (dptr[z][d])); + asm volatile("pxor %xmm5,%xmm2"); + asm volatile("pxor %xmm5,%xmm4"); + } + /* P/Q left side optimization */ + for ( z = start-1 ; z >= 0 ; z-- ) { + asm volatile("pxor %xmm5,%xmm5"); + asm volatile("pcmpgtb %xmm4,%xmm5"); + asm volatile("paddb %xmm4,%xmm4"); + asm volatile("pand %xmm0,%xmm5"); + asm volatile("pxor %xmm5,%xmm4"); + } + asm volatile("pxor %0,%%xmm4" : : "m" (q[d])); + /* Don't use movntdq for r/w memory area < cache line */ + asm volatile("movdqa %%xmm4,%0" : "=m" (q[d])); + asm volatile("movdqa %%xmm2,%0" : "=m" (p[d])); + } + + asm volatile("sfence" : : : "memory"); + kernel_fpu_end(); +} + const struct raid6_calls raid6_sse2x1 = { raid6_sse21_gen_syndrome, + raid6_sse21_xor_syndrome, raid6_have_sse2, "sse2x1", 1 /* Has cache hints */ @@ -150,8 +200,76 @@ static void raid6_sse22_gen_syndrome(int disks, size_t bytes, void **ptrs) kernel_fpu_end(); } + static void raid6_sse22_xor_syndrome(int disks, int start, int stop, + size_t bytes, void **ptrs) + { + u8 **dptr = (u8 **)ptrs; + u8 *p, *q; + int d, z, z0; + + z0 = stop; /* P/Q right side optimization */ + p = dptr[disks-2]; /* XOR parity */ + q = dptr[disks-1]; /* RS syndrome */ + + kernel_fpu_begin(); + + asm volatile("movdqa %0,%%xmm0" : : "m" (raid6_sse_constants.x1d[0])); + + for ( d = 0 ; d < bytes ; d += 32 ) { + asm volatile("movdqa %0,%%xmm4" :: "m" (dptr[z0][d])); + asm volatile("movdqa %0,%%xmm6" :: "m" (dptr[z0][d+16])); + asm volatile("movdqa %0,%%xmm2" : : "m" (p[d])); + asm volatile("movdqa %0,%%xmm3" : : "m" (p[d+16])); + asm volatile("pxor %xmm4,%xmm2"); + asm volatile("pxor %xmm6,%xmm3"); + /* P/Q data pages */ + for ( z = z0-1 ; z >= start ; z-- ) { + asm volatile("pxor %xmm5,%xmm5"); + asm volatile("pxor %xmm7,%xmm7"); + asm volatile("pcmpgtb %xmm4,%xmm5"); + asm volatile("pcmpgtb %xmm6,%xmm7"); + asm volatile("paddb %xmm4,%xmm4"); + asm volatile("paddb %xmm6,%xmm6"); + asm volatile("pand %xmm0,%xmm5"); + asm volatile("pand %xmm0,%xmm7"); + asm volatile("pxor %xmm5,%xmm4"); + asm volatile("pxor %xmm7,%xmm6"); + asm volatile("movdqa %0,%%xmm5" :: "m" (dptr[z][d])); + asm volatile("movdqa %0,%%xmm7" :: "m" (dptr[z][d+16])); + asm volatile("pxor %xmm5,%xmm2"); + asm volatile("pxor %xmm7,%xmm3"); + asm volatile("pxor %xmm5,%xmm4"); + asm volatile("pxor %xmm7,%xmm6"); + } + /* P/Q left side optimization */ + for ( z = start-1 ; z >= 0 ; z-- ) { + asm volatile("pxor %xmm5,%xmm5"); + asm volatile("pxor %xmm7,%xmm7"); + asm volatile("pcmpgtb %xmm4,%xmm5"); + asm volatile("pcmpgtb %xmm6,%xmm7"); + asm volatile("paddb %xmm4,%xmm4"); + asm volatile("paddb %xmm6,%xmm6"); + asm volatile("pand %xmm0,%xmm5"); + asm volatile("pand %xmm0,%xmm7"); + asm volatile("pxor %xmm5,%xmm4"); + asm volatile("pxor %xmm7,%xmm6"); + } + asm volatile("pxor %0,%%xmm4" : : "m" (q[d])); + asm volatile("pxor %0,%%xmm6" : : "m" (q[d+16])); + /* Don't use movntdq for r/w memory area < cache line */ + asm volatile("movdqa %%xmm4,%0" : "=m" (q[d])); + asm volatile("movdqa %%xmm6,%0" : "=m" (q[d+16])); + asm volatile("movdqa %%xmm2,%0" : "=m" (p[d])); + asm volatile("movdqa %%xmm3,%0" : "=m" (p[d+16])); + } + + asm volatile("sfence" : : : "memory"); + kernel_fpu_end(); + } + const struct raid6_calls raid6_sse2x2 = { raid6_sse22_gen_syndrome, + raid6_sse22_xor_syndrome, raid6_have_sse2, "sse2x2", 1 /* Has cache hints */ @@ -248,8 +366,117 @@ static void raid6_sse24_gen_syndrome(int disks, size_t bytes, void **ptrs) kernel_fpu_end(); } + static void raid6_sse24_xor_syndrome(int disks, int start, int stop, + size_t bytes, void **ptrs) + { + u8 **dptr = (u8 **)ptrs; + u8 *p, *q; + int d, z, z0; + + z0 = stop; /* P/Q right side optimization */ + p = dptr[disks-2]; /* XOR parity */ + q = dptr[disks-1]; /* RS syndrome */ + + kernel_fpu_begin(); + + asm volatile("movdqa %0,%%xmm0" :: "m" (raid6_sse_constants.x1d[0])); + + for ( d = 0 ; d < bytes ; d += 64 ) { + asm volatile("movdqa %0,%%xmm4" :: "m" (dptr[z0][d])); + asm volatile("movdqa %0,%%xmm6" :: "m" (dptr[z0][d+16])); + asm volatile("movdqa %0,%%xmm12" :: "m" (dptr[z0][d+32])); + asm volatile("movdqa %0,%%xmm14" :: "m" (dptr[z0][d+48])); + asm volatile("movdqa %0,%%xmm2" : : "m" (p[d])); + asm volatile("movdqa %0,%%xmm3" : : "m" (p[d+16])); + asm volatile("movdqa %0,%%xmm10" : : "m" (p[d+32])); + asm volatile("movdqa %0,%%xmm11" : : "m" (p[d+48])); + asm volatile("pxor %xmm4,%xmm2"); + asm volatile("pxor %xmm6,%xmm3"); + asm volatile("pxor %xmm12,%xmm10"); + asm volatile("pxor %xmm14,%xmm11"); + /* P/Q data pages */ + for ( z = z0-1 ; z >= start ; z-- ) { + asm volatile("prefetchnta %0" :: "m" (dptr[z][d])); + asm volatile("prefetchnta %0" :: "m" (dptr[z][d+32])); + asm volatile("pxor %xmm5,%xmm5"); + asm volatile("pxor %xmm7,%xmm7"); + asm volatile("pxor %xmm13,%xmm13"); + asm volatile("pxor %xmm15,%xmm15"); + asm volatile("pcmpgtb %xmm4,%xmm5"); + asm volatile("pcmpgtb %xmm6,%xmm7"); + asm volatile("pcmpgtb %xmm12,%xmm13"); + asm volatile("pcmpgtb %xmm14,%xmm15"); + asm volatile("paddb %xmm4,%xmm4"); + asm volatile("paddb %xmm6,%xmm6"); + asm volatile("paddb %xmm12,%xmm12"); + asm volatile("paddb %xmm14,%xmm14"); + asm volatile("pand %xmm0,%xmm5"); + asm volatile("pand %xmm0,%xmm7"); + asm volatile("pand %xmm0,%xmm13"); + asm volatile("pand %xmm0,%xmm15"); + asm volatile("pxor %xmm5,%xmm4"); + asm volatile("pxor %xmm7,%xmm6"); + asm volatile("pxor %xmm13,%xmm12"); + asm volatile("pxor %xmm15,%xmm14"); + asm volatile("movdqa %0,%%xmm5" :: "m" (dptr[z][d])); + asm volatile("movdqa %0,%%xmm7" :: "m" (dptr[z][d+16])); + asm volatile("movdqa %0,%%xmm13" :: "m" (dptr[z][d+32])); + asm volatile("movdqa %0,%%xmm15" :: "m" (dptr[z][d+48])); + asm volatile("pxor %xmm5,%xmm2"); + asm volatile("pxor %xmm7,%xmm3"); + asm volatile("pxor %xmm13,%xmm10"); + asm volatile("pxor %xmm15,%xmm11"); + asm volatile("pxor %xmm5,%xmm4"); + asm volatile("pxor %xmm7,%xmm6"); + asm volatile("pxor %xmm13,%xmm12"); + asm volatile("pxor %xmm15,%xmm14"); + } + asm volatile("prefetchnta %0" :: "m" (q[d])); + asm volatile("prefetchnta %0" :: "m" (q[d+32])); + /* P/Q left side optimization */ + for ( z = start-1 ; z >= 0 ; z-- ) { + asm volatile("pxor %xmm5,%xmm5"); + asm volatile("pxor %xmm7,%xmm7"); + asm volatile("pxor %xmm13,%xmm13"); + asm volatile("pxor %xmm15,%xmm15"); + asm volatile("pcmpgtb %xmm4,%xmm5"); + asm volatile("pcmpgtb %xmm6,%xmm7"); + asm volatile("pcmpgtb %xmm12,%xmm13"); + asm volatile("pcmpgtb %xmm14,%xmm15"); + asm volatile("paddb %xmm4,%xmm4"); + asm volatile("paddb %xmm6,%xmm6"); + asm volatile("paddb %xmm12,%xmm12"); + asm volatile("paddb %xmm14,%xmm14"); + asm volatile("pand %xmm0,%xmm5"); + asm volatile("pand %xmm0,%xmm7"); + asm volatile("pand %xmm0,%xmm13"); + asm volatile("pand %xmm0,%xmm15"); + asm volatile("pxor %xmm5,%xmm4"); + asm volatile("pxor %xmm7,%xmm6"); + asm volatile("pxor %xmm13,%xmm12"); + asm volatile("pxor %xmm15,%xmm14"); + } + asm volatile("movntdq %%xmm2,%0" : "=m" (p[d])); + asm volatile("movntdq %%xmm3,%0" : "=m" (p[d+16])); + asm volatile("movntdq %%xmm10,%0" : "=m" (p[d+32])); + asm volatile("movntdq %%xmm11,%0" : "=m" (p[d+48])); + asm volatile("pxor %0,%%xmm4" : : "m" (q[d])); + asm volatile("pxor %0,%%xmm6" : : "m" (q[d+16])); + asm volatile("pxor %0,%%xmm12" : : "m" (q[d+32])); + asm volatile("pxor %0,%%xmm14" : : "m" (q[d+48])); + asm volatile("movntdq %%xmm4,%0" : "=m" (q[d])); + asm volatile("movntdq %%xmm6,%0" : "=m" (q[d+16])); + asm volatile("movntdq %%xmm12,%0" : "=m" (q[d+32])); + asm volatile("movntdq %%xmm14,%0" : "=m" (q[d+48])); + } + asm volatile("sfence" : : : "memory"); + kernel_fpu_end(); + } + + const struct raid6_calls raid6_sse2x4 = { raid6_sse24_gen_syndrome, + raid6_sse24_xor_syndrome, raid6_have_sse2, "sse2x4", 1 /* Has cache hints */ diff --git a/lib/raid6/test/test.c b/lib/raid6/test/test.c index 5a485b7a7d3c..3bebbabdb510 100644 --- a/lib/raid6/test/test.c +++ b/lib/raid6/test/test.c @@ -28,11 +28,11 @@ char *dataptrs[NDISKS]; char data[NDISKS][PAGE_SIZE]; char recovi[PAGE_SIZE], recovj[PAGE_SIZE]; -static void makedata(void) +static void makedata(int start, int stop) { int i, j; - for (i = 0; i < NDISKS; i++) { + for (i = start; i <= stop; i++) { for (j = 0; j < PAGE_SIZE; j++) data[i][j] = rand(); @@ -91,34 +91,55 @@ int main(int argc, char *argv[]) { const struct raid6_calls *const *algo; const struct raid6_recov_calls *const *ra; - int i, j; + int i, j, p1, p2; int err = 0; - makedata(); + makedata(0, NDISKS-1); for (ra = raid6_recov_algos; *ra; ra++) { if ((*ra)->valid && !(*ra)->valid()) continue; + raid6_2data_recov = (*ra)->data2; raid6_datap_recov = (*ra)->datap; printf("using recovery %s\n", (*ra)->name); for (algo = raid6_algos; *algo; algo++) { - if (!(*algo)->valid || (*algo)->valid()) { - raid6_call = **algo; + if ((*algo)->valid && !(*algo)->valid()) + continue; + + raid6_call = **algo; + + /* Nuke syndromes */ + memset(data[NDISKS-2], 0xee, 2*PAGE_SIZE); + + /* Generate assumed good syndrome */ + raid6_call.gen_syndrome(NDISKS, PAGE_SIZE, + (void **)&dataptrs); + + for (i = 0; i < NDISKS-1; i++) + for (j = i+1; j < NDISKS; j++) + err += test_disks(i, j); + + if (!raid6_call.xor_syndrome) + continue; + + for (p1 = 0; p1 < NDISKS-2; p1++) + for (p2 = p1; p2 < NDISKS-2; p2++) { - /* Nuke syndromes */ - memset(data[NDISKS-2], 0xee, 2*PAGE_SIZE); + /* Simulate rmw run */ + raid6_call.xor_syndrome(NDISKS, p1, p2, PAGE_SIZE, + (void **)&dataptrs); + makedata(p1, p2); + raid6_call.xor_syndrome(NDISKS, p1, p2, PAGE_SIZE, + (void **)&dataptrs); - /* Generate assumed good syndrome */ - raid6_call.gen_syndrome(NDISKS, PAGE_SIZE, - (void **)&dataptrs); + for (i = 0; i < NDISKS-1; i++) + for (j = i+1; j < NDISKS; j++) + err += test_disks(i, j); + } - for (i = 0; i < NDISKS-1; i++) - for (j = i+1; j < NDISKS; j++) - err += test_disks(i, j); - } } printf("\n"); } diff --git a/lib/raid6/tilegx.uc b/lib/raid6/tilegx.uc index e7c29459cbcd..2dd291a11264 100644 --- a/lib/raid6/tilegx.uc +++ b/lib/raid6/tilegx.uc @@ -80,6 +80,7 @@ void raid6_tilegx$#_gen_syndrome(int disks, size_t bytes, void **ptrs) const struct raid6_calls raid6_tilegx$# = { raid6_tilegx$#_gen_syndrome, + NULL, /* XOR not yet implemented */ NULL, "tilegx$#", 0 diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 4898442b837f..a60a6d335a91 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -14,6 +14,7 @@ * published by the Free Software Foundation. */ +#include <linux/atomic.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/log2.h> @@ -25,6 +26,7 @@ #include <linux/random.h> #include <linux/rhashtable.h> #include <linux/err.h> +#include <linux/export.h> #define HASH_DEFAULT_SIZE 64UL #define HASH_MIN_SIZE 4U @@ -405,13 +407,18 @@ int rhashtable_insert_rehash(struct rhashtable *ht) if (rht_grow_above_75(ht, tbl)) size *= 2; - /* More than two rehashes (not resizes) detected. */ - else if (WARN_ON(old_tbl != tbl && old_tbl->size == size)) + /* Do not schedule more than one rehash */ + else if (old_tbl != tbl) return -EBUSY; new_tbl = bucket_table_alloc(ht, size, GFP_ATOMIC); - if (new_tbl == NULL) + if (new_tbl == NULL) { + /* Schedule async resize/rehash to try allocation + * non-atomic context. + */ + schedule_work(&ht->run_work); return -ENOMEM; + } err = rhashtable_rehash_attach(ht, tbl, new_tbl); if (err) { @@ -441,6 +448,10 @@ int rhashtable_insert_slow(struct rhashtable *ht, const void *key, if (key && rhashtable_lookup_fast(ht, key, ht->p)) goto exit; + err = -E2BIG; + if (unlikely(rht_grow_above_max(ht, tbl))) + goto exit; + err = -EAGAIN; if (rhashtable_check_elasticity(ht, tbl, hash) || rht_grow_above_100(ht, tbl)) @@ -574,7 +585,6 @@ void *rhashtable_walk_next(struct rhashtable_iter *iter) struct bucket_table *tbl = iter->walker->tbl; struct rhashtable *ht = iter->ht; struct rhash_head *p = iter->p; - void *obj = NULL; if (p) { p = rht_dereference_bucket_rcu(p->next, tbl, iter->slot); @@ -594,8 +604,7 @@ next: if (!rht_is_a_nulls(p)) { iter->skip++; iter->p = p; - obj = rht_obj(ht, p); - goto out; + return rht_obj(ht, p); } iter->skip = 0; @@ -613,9 +622,7 @@ next: iter->p = NULL; -out: - - return obj; + return NULL; } EXPORT_SYMBOL_GPL(rhashtable_walk_next); @@ -733,6 +740,12 @@ int rhashtable_init(struct rhashtable *ht, if (params->max_size) ht->p.max_size = rounddown_pow_of_two(params->max_size); + if (params->insecure_max_entries) + ht->p.insecure_max_entries = + rounddown_pow_of_two(params->insecure_max_entries); + else + ht->p.insecure_max_entries = ht->p.max_size * 2; + ht->p.min_size = max(ht->p.min_size, HASH_MIN_SIZE); /* The maximum (not average) chain length grows with the diff --git a/lib/string.c b/lib/string.c index a5792019193c..bb3d4b6993c4 100644 --- a/lib/string.c +++ b/lib/string.c @@ -607,7 +607,7 @@ EXPORT_SYMBOL(memset); void memzero_explicit(void *s, size_t count) { memset(s, 0, count); - barrier(); + barrier_data(s); } EXPORT_SYMBOL(memzero_explicit); diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index a28df5206d95..fe9a32591c24 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -57,7 +57,8 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count, return res + find_zero(data) + 1 - align; } res += sizeof(unsigned long); - if (unlikely(max < sizeof(unsigned long))) + /* We already handled 'unsigned long' bytes. Did we do it all ? */ + if (unlikely(max <= sizeof(unsigned long))) break; max -= sizeof(unsigned long); if (unlikely(__get_user(c,(unsigned long __user *)(src+res)))) @@ -89,8 +90,15 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count, * Get the size of a NUL-terminated string in user space. * * Returns the size of the string INCLUDING the terminating NUL. - * If the string is too long, returns 'count+1'. + * If the string is too long, returns a number larger than @count. User + * has to check the return value against "> count". * On exception (or invalid count), returns 0. + * + * NOTE! You should basically never use this function. There is + * almost never any valid case for using the length of a user space + * string, since the string can be changed at any time by other + * threads. Use "strncpy_from_user()" instead to get a stable copy + * of the string. */ long strnlen_user(const char __user *str, long count) { diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 4abda074ea45..3c365ab6cf5f 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -537,8 +537,9 @@ EXPORT_SYMBOL_GPL(swiotlb_tbl_map_single); * Allocates bounce buffer and returns its kernel virtual address. */ -phys_addr_t map_single(struct device *hwdev, phys_addr_t phys, size_t size, - enum dma_data_direction dir) +static phys_addr_t +map_single(struct device *hwdev, phys_addr_t phys, size_t size, + enum dma_data_direction dir) { dma_addr_t start_dma_addr = phys_to_dma(hwdev, io_tlb_start); diff --git a/lib/test-hexdump.c b/lib/test-hexdump.c index 9846ff7428b3..c227cc43ec0a 100644 --- a/lib/test-hexdump.c +++ b/lib/test-hexdump.c @@ -48,7 +48,7 @@ static void __init test_hexdump(size_t len, int rowsize, int groupsize, char test[32 * 3 + 2 + 32 + 1]; char real[32 * 3 + 2 + 32 + 1]; char *p; - const char **result; + const char * const *result; size_t l = len; int gs = groupsize, rs = rowsize; unsigned int i; diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 80d78c51f65f..7f58c735d745 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -21,6 +21,7 @@ #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/if_vlan.h> +#include <linux/random.h> /* General test specific settings */ #define MAX_SUBTESTS 3 @@ -67,6 +68,10 @@ struct bpf_test { union { struct sock_filter insns[MAX_INSNS]; struct bpf_insn insns_int[MAX_INSNS]; + struct { + void *insns; + unsigned int len; + } ptr; } u; __u8 aux; __u8 data[MAX_DATA]; @@ -74,8 +79,282 @@ struct bpf_test { int data_size; __u32 result; } test[MAX_SUBTESTS]; + int (*fill_helper)(struct bpf_test *self); }; +/* Large test cases need separate allocation and fill handler. */ + +static int bpf_fill_maxinsns1(struct bpf_test *self) +{ + unsigned int len = BPF_MAXINSNS; + struct sock_filter *insn; + __u32 k = ~0; + int i; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + for (i = 0; i < len; i++, k--) + insn[i] = __BPF_STMT(BPF_RET | BPF_K, k); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + + return 0; +} + +static int bpf_fill_maxinsns2(struct bpf_test *self) +{ + unsigned int len = BPF_MAXINSNS; + struct sock_filter *insn; + int i; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + for (i = 0; i < len; i++) + insn[i] = __BPF_STMT(BPF_RET | BPF_K, 0xfefefefe); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + + return 0; +} + +static int bpf_fill_maxinsns3(struct bpf_test *self) +{ + unsigned int len = BPF_MAXINSNS; + struct sock_filter *insn; + struct rnd_state rnd; + int i; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + prandom_seed_state(&rnd, 3141592653589793238ULL); + + for (i = 0; i < len - 1; i++) { + __u32 k = prandom_u32_state(&rnd); + + insn[i] = __BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, k); + } + + insn[len - 1] = __BPF_STMT(BPF_RET | BPF_A, 0); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + + return 0; +} + +static int bpf_fill_maxinsns4(struct bpf_test *self) +{ + unsigned int len = BPF_MAXINSNS + 1; + struct sock_filter *insn; + int i; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + for (i = 0; i < len; i++) + insn[i] = __BPF_STMT(BPF_RET | BPF_K, 0xfefefefe); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + + return 0; +} + +static int bpf_fill_maxinsns5(struct bpf_test *self) +{ + unsigned int len = BPF_MAXINSNS; + struct sock_filter *insn; + int i; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + insn[0] = __BPF_JUMP(BPF_JMP | BPF_JA, len - 2, 0, 0); + + for (i = 1; i < len - 1; i++) + insn[i] = __BPF_STMT(BPF_RET | BPF_K, 0xfefefefe); + + insn[len - 1] = __BPF_STMT(BPF_RET | BPF_K, 0xabababab); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + + return 0; +} + +static int bpf_fill_maxinsns6(struct bpf_test *self) +{ + unsigned int len = BPF_MAXINSNS; + struct sock_filter *insn; + int i; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + for (i = 0; i < len - 1; i++) + insn[i] = __BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF + + SKF_AD_VLAN_TAG_PRESENT); + + insn[len - 1] = __BPF_STMT(BPF_RET | BPF_A, 0); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + + return 0; +} + +static int bpf_fill_maxinsns7(struct bpf_test *self) +{ + unsigned int len = BPF_MAXINSNS; + struct sock_filter *insn; + int i; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + for (i = 0; i < len - 4; i++) + insn[i] = __BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF + + SKF_AD_CPU); + + insn[len - 4] = __BPF_STMT(BPF_MISC | BPF_TAX, 0); + insn[len - 3] = __BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF + + SKF_AD_CPU); + insn[len - 2] = __BPF_STMT(BPF_ALU | BPF_SUB | BPF_X, 0); + insn[len - 1] = __BPF_STMT(BPF_RET | BPF_A, 0); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + + return 0; +} + +static int bpf_fill_maxinsns8(struct bpf_test *self) +{ + unsigned int len = BPF_MAXINSNS; + struct sock_filter *insn; + int i, jmp_off = len - 3; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + insn[0] = __BPF_STMT(BPF_LD | BPF_IMM, 0xffffffff); + + for (i = 1; i < len - 1; i++) + insn[i] = __BPF_JUMP(BPF_JMP | BPF_JGT, 0xffffffff, jmp_off--, 0); + + insn[len - 1] = __BPF_STMT(BPF_RET | BPF_A, 0); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + + return 0; +} + +static int bpf_fill_maxinsns9(struct bpf_test *self) +{ + unsigned int len = BPF_MAXINSNS; + struct bpf_insn *insn; + int i; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + insn[0] = BPF_JMP_IMM(BPF_JA, 0, 0, len - 2); + insn[1] = BPF_ALU32_IMM(BPF_MOV, R0, 0xcbababab); + insn[2] = BPF_EXIT_INSN(); + + for (i = 3; i < len - 2; i++) + insn[i] = BPF_ALU32_IMM(BPF_MOV, R0, 0xfefefefe); + + insn[len - 2] = BPF_EXIT_INSN(); + insn[len - 1] = BPF_JMP_IMM(BPF_JA, 0, 0, -(len - 1)); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + + return 0; +} + +static int bpf_fill_maxinsns10(struct bpf_test *self) +{ + unsigned int len = BPF_MAXINSNS, hlen = len - 2; + struct bpf_insn *insn; + int i; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + for (i = 0; i < hlen / 2; i++) + insn[i] = BPF_JMP_IMM(BPF_JA, 0, 0, hlen - 2 - 2 * i); + for (i = hlen - 1; i > hlen / 2; i--) + insn[i] = BPF_JMP_IMM(BPF_JA, 0, 0, hlen - 1 - 2 * i); + + insn[hlen / 2] = BPF_JMP_IMM(BPF_JA, 0, 0, hlen / 2 - 1); + insn[hlen] = BPF_ALU32_IMM(BPF_MOV, R0, 0xabababac); + insn[hlen + 1] = BPF_EXIT_INSN(); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + + return 0; +} + +static int __bpf_fill_ja(struct bpf_test *self, unsigned int len, + unsigned int plen) +{ + struct sock_filter *insn; + unsigned int rlen; + int i, j; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + rlen = (len % plen) - 1; + + for (i = 0; i + plen < len; i += plen) + for (j = 0; j < plen; j++) + insn[i + j] = __BPF_JUMP(BPF_JMP | BPF_JA, + plen - 1 - j, 0, 0); + for (j = 0; j < rlen; j++) + insn[i + j] = __BPF_JUMP(BPF_JMP | BPF_JA, rlen - 1 - j, + 0, 0); + + insn[len - 1] = __BPF_STMT(BPF_RET | BPF_K, 0xababcbac); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + + return 0; +} + +static int bpf_fill_maxinsns11(struct bpf_test *self) +{ + /* Hits 70 passes on x86_64, so cannot get JITed there. */ + return __bpf_fill_ja(self, BPF_MAXINSNS, 68); +} + +static int bpf_fill_ja(struct bpf_test *self) +{ + /* Hits exactly 11 passes on x86_64 JIT. */ + return __bpf_fill_ja(self, 12, 9); +} + static struct bpf_test tests[] = { { "TAX", @@ -1755,7 +2034,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), BPF_JMP_IMM(BPF_JEQ, R3, 0x1234, 1), BPF_EXIT_INSN(), - BPF_ALU64_IMM(BPF_MOV, R0, 1), + BPF_LD_IMM64(R0, 0x1ffffffffLL), + BPF_ALU64_IMM(BPF_RSH, R0, 32), /* R0 = 1 */ BPF_EXIT_INSN(), }, INTERNAL, @@ -1805,6 +2085,2313 @@ static struct bpf_test tests[] = { 0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6}, { { 38, 256 } } }, + /* BPF_ALU | BPF_MOV | BPF_X */ + { + "ALU_MOV_X: dst = 2", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R1, 2), + BPF_ALU32_REG(BPF_MOV, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU_MOV_X: dst = 4294967295", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R1, 4294967295U), + BPF_ALU32_REG(BPF_MOV, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 4294967295U } }, + }, + { + "ALU64_MOV_X: dst = 2", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R1, 2), + BPF_ALU64_REG(BPF_MOV, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU64_MOV_X: dst = 4294967295", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R1, 4294967295U), + BPF_ALU64_REG(BPF_MOV, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 4294967295U } }, + }, + /* BPF_ALU | BPF_MOV | BPF_K */ + { + "ALU_MOV_K: dst = 2", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 2), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU_MOV_K: dst = 4294967295", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 4294967295U), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 4294967295U } }, + }, + { + "ALU_MOV_K: 0x0000ffffffff0000 = 0x00000000ffffffff", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x0000ffffffff0000LL), + BPF_LD_IMM64(R3, 0x00000000ffffffffLL), + BPF_ALU32_IMM(BPF_MOV, R2, 0xffffffff), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + { + "ALU64_MOV_K: dst = 2", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 2), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU64_MOV_K: dst = 2147483647", + .u.insns_int = { + BPF_ALU64_IMM(BPF_MOV, R0, 2147483647), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2147483647 } }, + }, + { + "ALU64_OR_K: dst = 0x0", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x0000ffffffff0000LL), + BPF_LD_IMM64(R3, 0x0), + BPF_ALU64_IMM(BPF_MOV, R2, 0x0), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + { + "ALU64_MOV_K: dst = -1", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x0000ffffffff0000LL), + BPF_LD_IMM64(R3, 0xffffffffffffffffLL), + BPF_ALU64_IMM(BPF_MOV, R2, 0xffffffff), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + /* BPF_ALU | BPF_ADD | BPF_X */ + { + "ALU_ADD_X: 1 + 2 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_MOV, R1, 2), + BPF_ALU32_REG(BPF_ADD, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU_ADD_X: 1 + 4294967294 = 4294967295", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_MOV, R1, 4294967294U), + BPF_ALU32_REG(BPF_ADD, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 4294967295U } }, + }, + { + "ALU64_ADD_X: 1 + 2 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_MOV, R1, 2), + BPF_ALU64_REG(BPF_ADD, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU64_ADD_X: 1 + 4294967294 = 4294967295", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_MOV, R1, 4294967294U), + BPF_ALU64_REG(BPF_ADD, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 4294967295U } }, + }, + /* BPF_ALU | BPF_ADD | BPF_K */ + { + "ALU_ADD_K: 1 + 2 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_ADD, R0, 2), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU_ADD_K: 3 + 0 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU32_IMM(BPF_ADD, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU_ADD_K: 1 + 4294967294 = 4294967295", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_ADD, R0, 4294967294U), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 4294967295U } }, + }, + { + "ALU_ADD_K: 0 + (-1) = 0x00000000ffffffff", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x0), + BPF_LD_IMM64(R3, 0x00000000ffffffff), + BPF_ALU32_IMM(BPF_ADD, R2, 0xffffffff), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + { + "ALU64_ADD_K: 1 + 2 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU64_IMM(BPF_ADD, R0, 2), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU64_ADD_K: 3 + 0 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU64_IMM(BPF_ADD, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU64_ADD_K: 1 + 2147483646 = 2147483647", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU64_IMM(BPF_ADD, R0, 2147483646), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2147483647 } }, + }, + { + "ALU64_ADD_K: 2147483646 + -2147483647 = -1", + .u.insns_int = { + BPF_LD_IMM64(R0, 2147483646), + BPF_ALU64_IMM(BPF_ADD, R0, -2147483647), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, -1 } }, + }, + { + "ALU64_ADD_K: 1 + 0 = 1", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x1), + BPF_LD_IMM64(R3, 0x1), + BPF_ALU64_IMM(BPF_ADD, R2, 0x0), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + { + "ALU64_ADD_K: 0 + (-1) = 0xffffffffffffffff", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x0), + BPF_LD_IMM64(R3, 0xffffffffffffffffLL), + BPF_ALU64_IMM(BPF_ADD, R2, 0xffffffff), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + /* BPF_ALU | BPF_SUB | BPF_X */ + { + "ALU_SUB_X: 3 - 1 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU32_IMM(BPF_MOV, R1, 1), + BPF_ALU32_REG(BPF_SUB, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU_SUB_X: 4294967295 - 4294967294 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 4294967295U), + BPF_ALU32_IMM(BPF_MOV, R1, 4294967294U), + BPF_ALU32_REG(BPF_SUB, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU64_SUB_X: 3 - 1 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU32_IMM(BPF_MOV, R1, 1), + BPF_ALU64_REG(BPF_SUB, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU64_SUB_X: 4294967295 - 4294967294 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 4294967295U), + BPF_ALU32_IMM(BPF_MOV, R1, 4294967294U), + BPF_ALU64_REG(BPF_SUB, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_ALU | BPF_SUB | BPF_K */ + { + "ALU_SUB_K: 3 - 1 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU32_IMM(BPF_SUB, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU_SUB_K: 3 - 0 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU32_IMM(BPF_SUB, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU_SUB_K: 4294967295 - 4294967294 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 4294967295U), + BPF_ALU32_IMM(BPF_SUB, R0, 4294967294U), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU64_SUB_K: 3 - 1 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU64_IMM(BPF_SUB, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU64_SUB_K: 3 - 0 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU64_IMM(BPF_SUB, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU64_SUB_K: 4294967294 - 4294967295 = -1", + .u.insns_int = { + BPF_LD_IMM64(R0, 4294967294U), + BPF_ALU64_IMM(BPF_SUB, R0, 4294967295U), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, -1 } }, + }, + { + "ALU64_ADD_K: 2147483646 - 2147483647 = -1", + .u.insns_int = { + BPF_LD_IMM64(R0, 2147483646), + BPF_ALU64_IMM(BPF_SUB, R0, 2147483647), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, -1 } }, + }, + /* BPF_ALU | BPF_MUL | BPF_X */ + { + "ALU_MUL_X: 2 * 3 = 6", + .u.insns_int = { + BPF_LD_IMM64(R0, 2), + BPF_ALU32_IMM(BPF_MOV, R1, 3), + BPF_ALU32_REG(BPF_MUL, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 6 } }, + }, + { + "ALU_MUL_X: 2 * 0x7FFFFFF8 = 0xFFFFFFF0", + .u.insns_int = { + BPF_LD_IMM64(R0, 2), + BPF_ALU32_IMM(BPF_MOV, R1, 0x7FFFFFF8), + BPF_ALU32_REG(BPF_MUL, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xFFFFFFF0 } }, + }, + { + "ALU_MUL_X: -1 * -1 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, -1), + BPF_ALU32_IMM(BPF_MOV, R1, -1), + BPF_ALU32_REG(BPF_MUL, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU64_MUL_X: 2 * 3 = 6", + .u.insns_int = { + BPF_LD_IMM64(R0, 2), + BPF_ALU32_IMM(BPF_MOV, R1, 3), + BPF_ALU64_REG(BPF_MUL, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 6 } }, + }, + { + "ALU64_MUL_X: 1 * 2147483647 = 2147483647", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_MOV, R1, 2147483647), + BPF_ALU64_REG(BPF_MUL, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2147483647 } }, + }, + /* BPF_ALU | BPF_MUL | BPF_K */ + { + "ALU_MUL_K: 2 * 3 = 6", + .u.insns_int = { + BPF_LD_IMM64(R0, 2), + BPF_ALU32_IMM(BPF_MUL, R0, 3), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 6 } }, + }, + { + "ALU_MUL_K: 3 * 1 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU32_IMM(BPF_MUL, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU_MUL_K: 2 * 0x7FFFFFF8 = 0xFFFFFFF0", + .u.insns_int = { + BPF_LD_IMM64(R0, 2), + BPF_ALU32_IMM(BPF_MUL, R0, 0x7FFFFFF8), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xFFFFFFF0 } }, + }, + { + "ALU_MUL_K: 1 * (-1) = 0x00000000ffffffff", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x1), + BPF_LD_IMM64(R3, 0x00000000ffffffff), + BPF_ALU32_IMM(BPF_MUL, R2, 0xffffffff), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + { + "ALU64_MUL_K: 2 * 3 = 6", + .u.insns_int = { + BPF_LD_IMM64(R0, 2), + BPF_ALU64_IMM(BPF_MUL, R0, 3), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 6 } }, + }, + { + "ALU64_MUL_K: 3 * 1 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU64_IMM(BPF_MUL, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU64_MUL_K: 1 * 2147483647 = 2147483647", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU64_IMM(BPF_MUL, R0, 2147483647), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2147483647 } }, + }, + { + "ALU64_MUL_K: 1 * -2147483647 = -2147483647", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU64_IMM(BPF_MUL, R0, -2147483647), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, -2147483647 } }, + }, + { + "ALU64_MUL_K: 1 * (-1) = 0xffffffffffffffff", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x1), + BPF_LD_IMM64(R3, 0xffffffffffffffffLL), + BPF_ALU64_IMM(BPF_MUL, R2, 0xffffffff), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + /* BPF_ALU | BPF_DIV | BPF_X */ + { + "ALU_DIV_X: 6 / 2 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 6), + BPF_ALU32_IMM(BPF_MOV, R1, 2), + BPF_ALU32_REG(BPF_DIV, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU_DIV_X: 4294967295 / 4294967295 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 4294967295U), + BPF_ALU32_IMM(BPF_MOV, R1, 4294967295U), + BPF_ALU32_REG(BPF_DIV, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU64_DIV_X: 6 / 2 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 6), + BPF_ALU32_IMM(BPF_MOV, R1, 2), + BPF_ALU64_REG(BPF_DIV, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU64_DIV_X: 2147483647 / 2147483647 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 2147483647), + BPF_ALU32_IMM(BPF_MOV, R1, 2147483647), + BPF_ALU64_REG(BPF_DIV, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU64_DIV_X: 0xffffffffffffffff / (-1) = 0x0000000000000001", + .u.insns_int = { + BPF_LD_IMM64(R2, 0xffffffffffffffffLL), + BPF_LD_IMM64(R4, 0xffffffffffffffffLL), + BPF_LD_IMM64(R3, 0x0000000000000001LL), + BPF_ALU64_REG(BPF_DIV, R2, R4), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + /* BPF_ALU | BPF_DIV | BPF_K */ + { + "ALU_DIV_K: 6 / 2 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 6), + BPF_ALU32_IMM(BPF_DIV, R0, 2), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU_DIV_K: 3 / 1 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU32_IMM(BPF_DIV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU_DIV_K: 4294967295 / 4294967295 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 4294967295U), + BPF_ALU32_IMM(BPF_DIV, R0, 4294967295U), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU_DIV_K: 0xffffffffffffffff / (-1) = 0x1", + .u.insns_int = { + BPF_LD_IMM64(R2, 0xffffffffffffffffLL), + BPF_LD_IMM64(R3, 0x1UL), + BPF_ALU32_IMM(BPF_DIV, R2, 0xffffffff), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + { + "ALU64_DIV_K: 6 / 2 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 6), + BPF_ALU64_IMM(BPF_DIV, R0, 2), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU64_DIV_K: 3 / 1 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU64_IMM(BPF_DIV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU64_DIV_K: 2147483647 / 2147483647 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 2147483647), + BPF_ALU64_IMM(BPF_DIV, R0, 2147483647), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU64_DIV_K: 0xffffffffffffffff / (-1) = 0x0000000000000001", + .u.insns_int = { + BPF_LD_IMM64(R2, 0xffffffffffffffffLL), + BPF_LD_IMM64(R3, 0x0000000000000001LL), + BPF_ALU64_IMM(BPF_DIV, R2, 0xffffffff), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + /* BPF_ALU | BPF_MOD | BPF_X */ + { + "ALU_MOD_X: 3 % 2 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU32_IMM(BPF_MOV, R1, 2), + BPF_ALU32_REG(BPF_MOD, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU_MOD_X: 4294967295 % 4294967293 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 4294967295U), + BPF_ALU32_IMM(BPF_MOV, R1, 4294967293U), + BPF_ALU32_REG(BPF_MOD, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU64_MOD_X: 3 % 2 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU32_IMM(BPF_MOV, R1, 2), + BPF_ALU64_REG(BPF_MOD, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU64_MOD_X: 2147483647 % 2147483645 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 2147483647), + BPF_ALU32_IMM(BPF_MOV, R1, 2147483645), + BPF_ALU64_REG(BPF_MOD, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + /* BPF_ALU | BPF_MOD | BPF_K */ + { + "ALU_MOD_K: 3 % 2 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU32_IMM(BPF_MOD, R0, 2), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU_MOD_K: 3 % 1 = 0", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU32_IMM(BPF_MOD, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + }, + { + "ALU_MOD_K: 4294967295 % 4294967293 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 4294967295U), + BPF_ALU32_IMM(BPF_MOD, R0, 4294967293U), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU64_MOD_K: 3 % 2 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU64_IMM(BPF_MOD, R0, 2), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU64_MOD_K: 3 % 1 = 0", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU64_IMM(BPF_MOD, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0 } }, + }, + { + "ALU64_MOD_K: 2147483647 % 2147483645 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 2147483647), + BPF_ALU64_IMM(BPF_MOD, R0, 2147483645), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + /* BPF_ALU | BPF_AND | BPF_X */ + { + "ALU_AND_X: 3 & 2 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU32_IMM(BPF_MOV, R1, 2), + BPF_ALU32_REG(BPF_AND, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU_AND_X: 0xffffffff & 0xffffffff = 0xffffffff", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xffffffff), + BPF_ALU32_IMM(BPF_MOV, R1, 0xffffffff), + BPF_ALU32_REG(BPF_AND, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffffffff } }, + }, + { + "ALU64_AND_X: 3 & 2 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU32_IMM(BPF_MOV, R1, 2), + BPF_ALU64_REG(BPF_AND, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU64_AND_X: 0xffffffff & 0xffffffff = 0xffffffff", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xffffffff), + BPF_ALU32_IMM(BPF_MOV, R1, 0xffffffff), + BPF_ALU64_REG(BPF_AND, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffffffff } }, + }, + /* BPF_ALU | BPF_AND | BPF_K */ + { + "ALU_AND_K: 3 & 2 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU32_IMM(BPF_AND, R0, 2), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU_AND_K: 0xffffffff & 0xffffffff = 0xffffffff", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xffffffff), + BPF_ALU32_IMM(BPF_AND, R0, 0xffffffff), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffffffff } }, + }, + { + "ALU64_AND_K: 3 & 2 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU64_IMM(BPF_AND, R0, 2), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU64_AND_K: 0xffffffff & 0xffffffff = 0xffffffff", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xffffffff), + BPF_ALU64_IMM(BPF_AND, R0, 0xffffffff), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffffffff } }, + }, + { + "ALU64_AND_K: 0x0000ffffffff0000 & 0x0 = 0x0000ffff00000000", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x0000ffffffff0000LL), + BPF_LD_IMM64(R3, 0x0000000000000000LL), + BPF_ALU64_IMM(BPF_AND, R2, 0x0), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + { + "ALU64_AND_K: 0x0000ffffffff0000 & -1 = 0x0000ffffffffffff", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x0000ffffffff0000LL), + BPF_LD_IMM64(R3, 0x0000ffffffff0000LL), + BPF_ALU64_IMM(BPF_AND, R2, 0xffffffff), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + { + "ALU64_AND_K: 0xffffffffffffffff & -1 = 0xffffffffffffffff", + .u.insns_int = { + BPF_LD_IMM64(R2, 0xffffffffffffffffLL), + BPF_LD_IMM64(R3, 0xffffffffffffffffLL), + BPF_ALU64_IMM(BPF_AND, R2, 0xffffffff), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + /* BPF_ALU | BPF_OR | BPF_X */ + { + "ALU_OR_X: 1 | 2 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_MOV, R1, 2), + BPF_ALU32_REG(BPF_OR, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU_OR_X: 0x0 | 0xffffffff = 0xffffffff", + .u.insns_int = { + BPF_LD_IMM64(R0, 0), + BPF_ALU32_IMM(BPF_MOV, R1, 0xffffffff), + BPF_ALU32_REG(BPF_OR, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffffffff } }, + }, + { + "ALU64_OR_X: 1 | 2 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_MOV, R1, 2), + BPF_ALU64_REG(BPF_OR, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU64_OR_X: 0 | 0xffffffff = 0xffffffff", + .u.insns_int = { + BPF_LD_IMM64(R0, 0), + BPF_ALU32_IMM(BPF_MOV, R1, 0xffffffff), + BPF_ALU64_REG(BPF_OR, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffffffff } }, + }, + /* BPF_ALU | BPF_OR | BPF_K */ + { + "ALU_OR_K: 1 | 2 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_OR, R0, 2), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU_OR_K: 0 & 0xffffffff = 0xffffffff", + .u.insns_int = { + BPF_LD_IMM64(R0, 0), + BPF_ALU32_IMM(BPF_OR, R0, 0xffffffff), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffffffff } }, + }, + { + "ALU64_OR_K: 1 | 2 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU64_IMM(BPF_OR, R0, 2), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU64_OR_K: 0 & 0xffffffff = 0xffffffff", + .u.insns_int = { + BPF_LD_IMM64(R0, 0), + BPF_ALU64_IMM(BPF_OR, R0, 0xffffffff), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffffffff } }, + }, + { + "ALU64_OR_K: 0x0000ffffffff0000 | 0x0 = 0x0000ffff00000000", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x0000ffffffff0000LL), + BPF_LD_IMM64(R3, 0x0000ffffffff0000LL), + BPF_ALU64_IMM(BPF_OR, R2, 0x0), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + { + "ALU64_OR_K: 0x0000ffffffff0000 | -1 = 0xffffffffffffffff", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x0000ffffffff0000LL), + BPF_LD_IMM64(R3, 0xffffffffffffffffLL), + BPF_ALU64_IMM(BPF_OR, R2, 0xffffffff), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + { + "ALU64_OR_K: 0x000000000000000 | -1 = 0xffffffffffffffff", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x0000000000000000LL), + BPF_LD_IMM64(R3, 0xffffffffffffffffLL), + BPF_ALU64_IMM(BPF_OR, R2, 0xffffffff), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + /* BPF_ALU | BPF_XOR | BPF_X */ + { + "ALU_XOR_X: 5 ^ 6 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 5), + BPF_ALU32_IMM(BPF_MOV, R1, 6), + BPF_ALU32_REG(BPF_XOR, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU_XOR_X: 0x1 ^ 0xffffffff = 0xfffffffe", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_MOV, R1, 0xffffffff), + BPF_ALU32_REG(BPF_XOR, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xfffffffe } }, + }, + { + "ALU64_XOR_X: 5 ^ 6 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 5), + BPF_ALU32_IMM(BPF_MOV, R1, 6), + BPF_ALU64_REG(BPF_XOR, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU64_XOR_X: 1 ^ 0xffffffff = 0xfffffffe", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_MOV, R1, 0xffffffff), + BPF_ALU64_REG(BPF_XOR, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xfffffffe } }, + }, + /* BPF_ALU | BPF_XOR | BPF_K */ + { + "ALU_XOR_K: 5 ^ 6 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 5), + BPF_ALU32_IMM(BPF_XOR, R0, 6), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU_XOR_K: 1 ^ 0xffffffff = 0xfffffffe", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_XOR, R0, 0xffffffff), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xfffffffe } }, + }, + { + "ALU64_XOR_K: 5 ^ 6 = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, 5), + BPF_ALU64_IMM(BPF_XOR, R0, 6), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU64_XOR_K: 1 & 0xffffffff = 0xfffffffe", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU64_IMM(BPF_XOR, R0, 0xffffffff), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xfffffffe } }, + }, + { + "ALU64_XOR_K: 0x0000ffffffff0000 ^ 0x0 = 0x0000ffffffff0000", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x0000ffffffff0000LL), + BPF_LD_IMM64(R3, 0x0000ffffffff0000LL), + BPF_ALU64_IMM(BPF_XOR, R2, 0x0), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + { + "ALU64_XOR_K: 0x0000ffffffff0000 ^ -1 = 0xffff00000000ffff", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x0000ffffffff0000LL), + BPF_LD_IMM64(R3, 0xffff00000000ffffLL), + BPF_ALU64_IMM(BPF_XOR, R2, 0xffffffff), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + { + "ALU64_XOR_K: 0x000000000000000 ^ -1 = 0xffffffffffffffff", + .u.insns_int = { + BPF_LD_IMM64(R2, 0x0000000000000000LL), + BPF_LD_IMM64(R3, 0xffffffffffffffffLL), + BPF_ALU64_IMM(BPF_XOR, R2, 0xffffffff), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + /* BPF_ALU | BPF_LSH | BPF_X */ + { + "ALU_LSH_X: 1 << 1 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_MOV, R1, 1), + BPF_ALU32_REG(BPF_LSH, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU_LSH_X: 1 << 31 = 0x80000000", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_MOV, R1, 31), + BPF_ALU32_REG(BPF_LSH, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x80000000 } }, + }, + { + "ALU64_LSH_X: 1 << 1 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_MOV, R1, 1), + BPF_ALU64_REG(BPF_LSH, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU64_LSH_X: 1 << 31 = 0x80000000", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_MOV, R1, 31), + BPF_ALU64_REG(BPF_LSH, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x80000000 } }, + }, + /* BPF_ALU | BPF_LSH | BPF_K */ + { + "ALU_LSH_K: 1 << 1 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_LSH, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU_LSH_K: 1 << 31 = 0x80000000", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU32_IMM(BPF_LSH, R0, 31), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x80000000 } }, + }, + { + "ALU64_LSH_K: 1 << 1 = 2", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU64_IMM(BPF_LSH, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 2 } }, + }, + { + "ALU64_LSH_K: 1 << 31 = 0x80000000", + .u.insns_int = { + BPF_LD_IMM64(R0, 1), + BPF_ALU64_IMM(BPF_LSH, R0, 31), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x80000000 } }, + }, + /* BPF_ALU | BPF_RSH | BPF_X */ + { + "ALU_RSH_X: 2 >> 1 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 2), + BPF_ALU32_IMM(BPF_MOV, R1, 1), + BPF_ALU32_REG(BPF_RSH, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU_RSH_X: 0x80000000 >> 31 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 0x80000000), + BPF_ALU32_IMM(BPF_MOV, R1, 31), + BPF_ALU32_REG(BPF_RSH, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU64_RSH_X: 2 >> 1 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 2), + BPF_ALU32_IMM(BPF_MOV, R1, 1), + BPF_ALU64_REG(BPF_RSH, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU64_RSH_X: 0x80000000 >> 31 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 0x80000000), + BPF_ALU32_IMM(BPF_MOV, R1, 31), + BPF_ALU64_REG(BPF_RSH, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_ALU | BPF_RSH | BPF_K */ + { + "ALU_RSH_K: 2 >> 1 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 2), + BPF_ALU32_IMM(BPF_RSH, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU_RSH_K: 0x80000000 >> 31 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 0x80000000), + BPF_ALU32_IMM(BPF_RSH, R0, 31), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU64_RSH_K: 2 >> 1 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 2), + BPF_ALU64_IMM(BPF_RSH, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "ALU64_RSH_K: 0x80000000 >> 31 = 1", + .u.insns_int = { + BPF_LD_IMM64(R0, 0x80000000), + BPF_ALU64_IMM(BPF_RSH, R0, 31), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_ALU | BPF_ARSH | BPF_X */ + { + "ALU_ARSH_X: 0xff00ff0000000000 >> 40 = 0xffffffffffff00ff", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xff00ff0000000000LL), + BPF_ALU32_IMM(BPF_MOV, R1, 40), + BPF_ALU64_REG(BPF_ARSH, R0, R1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffff00ff } }, + }, + /* BPF_ALU | BPF_ARSH | BPF_K */ + { + "ALU_ARSH_K: 0xff00ff0000000000 >> 40 = 0xffffffffffff00ff", + .u.insns_int = { + BPF_LD_IMM64(R0, 0xff00ff0000000000LL), + BPF_ALU64_IMM(BPF_ARSH, R0, 40), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffff00ff } }, + }, + /* BPF_ALU | BPF_NEG */ + { + "ALU_NEG: -(3) = -3", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 3), + BPF_ALU32_IMM(BPF_NEG, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, -3 } }, + }, + { + "ALU_NEG: -(-3) = 3", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, -3), + BPF_ALU32_IMM(BPF_NEG, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + { + "ALU64_NEG: -(3) = -3", + .u.insns_int = { + BPF_LD_IMM64(R0, 3), + BPF_ALU64_IMM(BPF_NEG, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, -3 } }, + }, + { + "ALU64_NEG: -(-3) = 3", + .u.insns_int = { + BPF_LD_IMM64(R0, -3), + BPF_ALU64_IMM(BPF_NEG, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 3 } }, + }, + /* BPF_ALU | BPF_END | BPF_FROM_BE */ + { + "ALU_END_FROM_BE 16: 0x0123456789abcdef -> 0xcdef", + .u.insns_int = { + BPF_LD_IMM64(R0, 0x0123456789abcdefLL), + BPF_ENDIAN(BPF_FROM_BE, R0, 16), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, cpu_to_be16(0xcdef) } }, + }, + { + "ALU_END_FROM_BE 32: 0x0123456789abcdef -> 0x89abcdef", + .u.insns_int = { + BPF_LD_IMM64(R0, 0x0123456789abcdefLL), + BPF_ENDIAN(BPF_FROM_BE, R0, 32), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, cpu_to_be32(0x89abcdef) } }, + }, + { + "ALU_END_FROM_BE 64: 0x0123456789abcdef -> 0x89abcdef", + .u.insns_int = { + BPF_LD_IMM64(R0, 0x0123456789abcdefLL), + BPF_ENDIAN(BPF_FROM_BE, R0, 64), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, (u32) cpu_to_be64(0x0123456789abcdefLL) } }, + }, + /* BPF_ALU | BPF_END | BPF_FROM_LE */ + { + "ALU_END_FROM_LE 16: 0x0123456789abcdef -> 0xefcd", + .u.insns_int = { + BPF_LD_IMM64(R0, 0x0123456789abcdefLL), + BPF_ENDIAN(BPF_FROM_LE, R0, 16), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, cpu_to_le16(0xcdef) } }, + }, + { + "ALU_END_FROM_LE 32: 0x0123456789abcdef -> 0xefcdab89", + .u.insns_int = { + BPF_LD_IMM64(R0, 0x0123456789abcdefLL), + BPF_ENDIAN(BPF_FROM_LE, R0, 32), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, cpu_to_le32(0x89abcdef) } }, + }, + { + "ALU_END_FROM_LE 64: 0x0123456789abcdef -> 0x67452301", + .u.insns_int = { + BPF_LD_IMM64(R0, 0x0123456789abcdefLL), + BPF_ENDIAN(BPF_FROM_LE, R0, 64), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, (u32) cpu_to_le64(0x0123456789abcdefLL) } }, + }, + /* BPF_ST(X) | BPF_MEM | BPF_B/H/W/DW */ + { + "ST_MEM_B: Store/Load byte: max negative", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_ST_MEM(BPF_B, R10, -40, 0xff), + BPF_LDX_MEM(BPF_B, R0, R10, -40), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xff } }, + }, + { + "ST_MEM_B: Store/Load byte: max positive", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_ST_MEM(BPF_H, R10, -40, 0x7f), + BPF_LDX_MEM(BPF_H, R0, R10, -40), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x7f } }, + }, + { + "STX_MEM_B: Store/Load byte: max negative", + .u.insns_int = { + BPF_LD_IMM64(R0, 0), + BPF_LD_IMM64(R1, 0xffLL), + BPF_STX_MEM(BPF_B, R10, R1, -40), + BPF_LDX_MEM(BPF_B, R0, R10, -40), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xff } }, + }, + { + "ST_MEM_H: Store/Load half word: max negative", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_ST_MEM(BPF_H, R10, -40, 0xffff), + BPF_LDX_MEM(BPF_H, R0, R10, -40), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffff } }, + }, + { + "ST_MEM_H: Store/Load half word: max positive", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_ST_MEM(BPF_H, R10, -40, 0x7fff), + BPF_LDX_MEM(BPF_H, R0, R10, -40), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x7fff } }, + }, + { + "STX_MEM_H: Store/Load half word: max negative", + .u.insns_int = { + BPF_LD_IMM64(R0, 0), + BPF_LD_IMM64(R1, 0xffffLL), + BPF_STX_MEM(BPF_H, R10, R1, -40), + BPF_LDX_MEM(BPF_H, R0, R10, -40), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffff } }, + }, + { + "ST_MEM_W: Store/Load word: max negative", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_ST_MEM(BPF_W, R10, -40, 0xffffffff), + BPF_LDX_MEM(BPF_W, R0, R10, -40), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffffffff } }, + }, + { + "ST_MEM_W: Store/Load word: max positive", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_ST_MEM(BPF_W, R10, -40, 0x7fffffff), + BPF_LDX_MEM(BPF_W, R0, R10, -40), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x7fffffff } }, + }, + { + "STX_MEM_W: Store/Load word: max negative", + .u.insns_int = { + BPF_LD_IMM64(R0, 0), + BPF_LD_IMM64(R1, 0xffffffffLL), + BPF_STX_MEM(BPF_W, R10, R1, -40), + BPF_LDX_MEM(BPF_W, R0, R10, -40), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffffffff } }, + }, + { + "ST_MEM_DW: Store/Load double word: max negative", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_ST_MEM(BPF_DW, R10, -40, 0xffffffff), + BPF_LDX_MEM(BPF_DW, R0, R10, -40), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffffffff } }, + }, + { + "ST_MEM_DW: Store/Load double word: max negative 2", + .u.insns_int = { + BPF_LD_IMM64(R2, 0xffff00000000ffffLL), + BPF_LD_IMM64(R3, 0xffffffffffffffffLL), + BPF_ST_MEM(BPF_DW, R10, -40, 0xffffffff), + BPF_LDX_MEM(BPF_DW, R2, R10, -40), + BPF_JMP_REG(BPF_JEQ, R2, R3, 2), + BPF_MOV32_IMM(R0, 2), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x1 } }, + }, + { + "ST_MEM_DW: Store/Load double word: max positive", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_ST_MEM(BPF_DW, R10, -40, 0x7fffffff), + BPF_LDX_MEM(BPF_DW, R0, R10, -40), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x7fffffff } }, + }, + { + "STX_MEM_DW: Store/Load double word: max negative", + .u.insns_int = { + BPF_LD_IMM64(R0, 0), + BPF_LD_IMM64(R1, 0xffffffffffffffffLL), + BPF_STX_MEM(BPF_W, R10, R1, -40), + BPF_LDX_MEM(BPF_W, R0, R10, -40), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffffffff } }, + }, + /* BPF_STX | BPF_XADD | BPF_W/DW */ + { + "STX_XADD_W: Test: 0x12 + 0x10 = 0x22", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0x12), + BPF_ST_MEM(BPF_W, R10, -40, 0x10), + BPF_STX_XADD(BPF_W, R10, R0, -40), + BPF_LDX_MEM(BPF_W, R0, R10, -40), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x22 } }, + }, + { + "STX_XADD_DW: Test: 0x12 + 0x10 = 0x22", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0x12), + BPF_ST_MEM(BPF_DW, R10, -40, 0x10), + BPF_STX_XADD(BPF_DW, R10, R0, -40), + BPF_LDX_MEM(BPF_DW, R0, R10, -40), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0x22 } }, + }, + /* BPF_JMP | BPF_EXIT */ + { + "JMP_EXIT", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0x4711), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 0x4712), + }, + INTERNAL, + { }, + { { 0, 0x4711 } }, + }, + /* BPF_JMP | BPF_JA */ + { + "JMP_JA: Unconditional jump: if (true) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_JMP | BPF_JSGT | BPF_K */ + { + "JMP_JSGT_K: Signed jump: if (-1 > -2) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 0xffffffffffffffffLL), + BPF_JMP_IMM(BPF_JSGT, R1, -2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JSGT_K: Signed jump: if (-1 > -1) return 0", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_LD_IMM64(R1, 0xffffffffffffffffLL), + BPF_JMP_IMM(BPF_JSGT, R1, -1, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_JMP | BPF_JSGE | BPF_K */ + { + "JMP_JSGE_K: Signed jump: if (-1 >= -2) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 0xffffffffffffffffLL), + BPF_JMP_IMM(BPF_JSGE, R1, -2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JSGE_K: Signed jump: if (-1 >= -1) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 0xffffffffffffffffLL), + BPF_JMP_IMM(BPF_JSGE, R1, -1, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_JMP | BPF_JGT | BPF_K */ + { + "JMP_JGT_K: if (3 > 2) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_JMP_IMM(BPF_JGT, R1, 2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_JMP | BPF_JGE | BPF_K */ + { + "JMP_JGE_K: if (3 >= 2) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_JMP_IMM(BPF_JGE, R1, 2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_JMP | BPF_JGT | BPF_K jump backwards */ + { + "JMP_JGT_K: if (3 > 2) return 1 (jump backwards)", + .u.insns_int = { + BPF_JMP_IMM(BPF_JA, 0, 0, 2), /* goto start */ + BPF_ALU32_IMM(BPF_MOV, R0, 1), /* out: */ + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 0), /* start: */ + BPF_LD_IMM64(R1, 3), /* note: this takes 2 insns */ + BPF_JMP_IMM(BPF_JGT, R1, 2, -6), /* goto out */ + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JGE_K: if (3 >= 3) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_JMP_IMM(BPF_JGE, R1, 3, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_JMP | BPF_JNE | BPF_K */ + { + "JMP_JNE_K: if (3 != 2) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_JMP_IMM(BPF_JNE, R1, 2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_JMP | BPF_JEQ | BPF_K */ + { + "JMP_JEQ_K: if (3 == 3) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_JMP_IMM(BPF_JEQ, R1, 3, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_JMP | BPF_JSET | BPF_K */ + { + "JMP_JSET_K: if (0x3 & 0x2) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_JMP_IMM(BPF_JNE, R1, 2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JSET_K: if (0x3 & 0xffffffff) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_JMP_IMM(BPF_JNE, R1, 0xffffffff, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_JMP | BPF_JSGT | BPF_X */ + { + "JMP_JSGT_X: Signed jump: if (-1 > -2) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, -1), + BPF_LD_IMM64(R2, -2), + BPF_JMP_REG(BPF_JSGT, R1, R2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JSGT_X: Signed jump: if (-1 > -1) return 0", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_LD_IMM64(R1, -1), + BPF_LD_IMM64(R2, -1), + BPF_JMP_REG(BPF_JSGT, R1, R2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_JMP | BPF_JSGE | BPF_X */ + { + "JMP_JSGE_X: Signed jump: if (-1 >= -2) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, -1), + BPF_LD_IMM64(R2, -2), + BPF_JMP_REG(BPF_JSGE, R1, R2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JSGE_X: Signed jump: if (-1 >= -1) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, -1), + BPF_LD_IMM64(R2, -1), + BPF_JMP_REG(BPF_JSGE, R1, R2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_JMP | BPF_JGT | BPF_X */ + { + "JMP_JGT_X: if (3 > 2) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 2), + BPF_JMP_REG(BPF_JGT, R1, R2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_JMP | BPF_JGE | BPF_X */ + { + "JMP_JGE_X: if (3 >= 2) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 2), + BPF_JMP_REG(BPF_JGE, R1, R2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JGE_X: if (3 >= 3) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 3), + BPF_JMP_REG(BPF_JGE, R1, R2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_JMP | BPF_JNE | BPF_X */ + { + "JMP_JNE_X: if (3 != 2) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 2), + BPF_JMP_REG(BPF_JNE, R1, R2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_JMP | BPF_JEQ | BPF_X */ + { + "JMP_JEQ_X: if (3 == 3) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 3), + BPF_JMP_REG(BPF_JEQ, R1, R2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + /* BPF_JMP | BPF_JSET | BPF_X */ + { + "JMP_JSET_X: if (0x3 & 0x2) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 2), + BPF_JMP_REG(BPF_JNE, R1, R2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JSET_X: if (0x3 & 0xffffffff) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 0xffffffff), + BPF_JMP_REG(BPF_JNE, R1, R2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JA: Jump, gap, jump, ...", + { }, + CLASSIC | FLAG_NO_DATA, + { }, + { { 0, 0xababcbac } }, + .fill_helper = bpf_fill_ja, + }, + { /* Mainly checking JIT here. */ + "BPF_MAXINSNS: Maximum possible literals", + { }, + CLASSIC | FLAG_NO_DATA, + { }, + { { 0, 0xffffffff } }, + .fill_helper = bpf_fill_maxinsns1, + }, + { /* Mainly checking JIT here. */ + "BPF_MAXINSNS: Single literal", + { }, + CLASSIC | FLAG_NO_DATA, + { }, + { { 0, 0xfefefefe } }, + .fill_helper = bpf_fill_maxinsns2, + }, + { /* Mainly checking JIT here. */ + "BPF_MAXINSNS: Run/add until end", + { }, + CLASSIC | FLAG_NO_DATA, + { }, + { { 0, 0x947bf368 } }, + .fill_helper = bpf_fill_maxinsns3, + }, + { + "BPF_MAXINSNS: Too many instructions", + { }, + CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, + { }, + { }, + .fill_helper = bpf_fill_maxinsns4, + }, + { /* Mainly checking JIT here. */ + "BPF_MAXINSNS: Very long jump", + { }, + CLASSIC | FLAG_NO_DATA, + { }, + { { 0, 0xabababab } }, + .fill_helper = bpf_fill_maxinsns5, + }, + { /* Mainly checking JIT here. */ + "BPF_MAXINSNS: Ctx heavy transformations", + { }, + CLASSIC, + { }, + { + { 1, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) }, + { 10, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) } + }, + .fill_helper = bpf_fill_maxinsns6, + }, + { /* Mainly checking JIT here. */ + "BPF_MAXINSNS: Call heavy transformations", + { }, + CLASSIC | FLAG_NO_DATA, + { }, + { { 1, 0 }, { 10, 0 } }, + .fill_helper = bpf_fill_maxinsns7, + }, + { /* Mainly checking JIT here. */ + "BPF_MAXINSNS: Jump heavy test", + { }, + CLASSIC | FLAG_NO_DATA, + { }, + { { 0, 0xffffffff } }, + .fill_helper = bpf_fill_maxinsns8, + }, + { /* Mainly checking JIT here. */ + "BPF_MAXINSNS: Very long jump backwards", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 0xcbababab } }, + .fill_helper = bpf_fill_maxinsns9, + }, + { /* Mainly checking JIT here. */ + "BPF_MAXINSNS: Edge hopping nuthouse", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 0xabababac } }, + .fill_helper = bpf_fill_maxinsns10, + }, + { + "BPF_MAXINSNS: Jump, gap, jump, ...", + { }, + CLASSIC | FLAG_NO_DATA, + { }, + { { 0, 0xababcbac } }, + .fill_helper = bpf_fill_maxinsns11, + }, }; static struct net_device dev; @@ -1858,10 +4445,15 @@ static void release_test_data(const struct bpf_test *test, void *data) kfree_skb(data); } -static int probe_filter_length(struct sock_filter *fp) +static int filter_length(int which) { - int len = 0; + struct sock_filter *fp; + int len; + if (tests[which].fill_helper) + return tests[which].u.ptr.len; + + fp = tests[which].u.insns; for (len = MAX_INSNS - 1; len > 0; --len) if (fp[len].code != 0 || fp[len].k != 0) break; @@ -1869,16 +4461,25 @@ static int probe_filter_length(struct sock_filter *fp) return len + 1; } +static void *filter_pointer(int which) +{ + if (tests[which].fill_helper) + return tests[which].u.ptr.insns; + else + return tests[which].u.insns; +} + static struct bpf_prog *generate_filter(int which, int *err) { - struct bpf_prog *fp; - struct sock_fprog_kern fprog; - unsigned int flen = probe_filter_length(tests[which].u.insns); __u8 test_type = tests[which].aux & TEST_TYPE_MASK; + unsigned int flen = filter_length(which); + void *fptr = filter_pointer(which); + struct sock_fprog_kern fprog; + struct bpf_prog *fp; switch (test_type) { case CLASSIC: - fprog.filter = tests[which].u.insns; + fprog.filter = fptr; fprog.len = flen; *err = bpf_prog_create(&fp, &fprog); @@ -1914,8 +4515,7 @@ static struct bpf_prog *generate_filter(int which, int *err) } fp->len = flen; - memcpy(fp->insnsi, tests[which].u.insns_int, - fp->len * sizeof(struct bpf_insn)); + memcpy(fp->insnsi, fptr, fp->len * sizeof(struct bpf_insn)); bpf_prog_select_runtime(fp); break; @@ -1987,9 +4587,33 @@ static int run_one(const struct bpf_prog *fp, struct bpf_test *test) return err_cnt; } +static __init int prepare_bpf_tests(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + if (tests[i].fill_helper && + tests[i].fill_helper(&tests[i]) < 0) + return -ENOMEM; + } + + return 0; +} + +static __init void destroy_bpf_tests(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + if (tests[i].fill_helper) + kfree(tests[i].u.ptr.insns); + } +} + static __init int test_bpf(void) { int i, err_cnt = 0, pass_cnt = 0; + int jit_cnt = 0, run_cnt = 0; for (i = 0; i < ARRAY_SIZE(tests); i++) { struct bpf_prog *fp; @@ -2006,6 +4630,13 @@ static __init int test_bpf(void) return err; } + + pr_cont("jited:%u ", fp->jited); + + run_cnt++; + if (fp->jited) + jit_cnt++; + err = run_one(fp, &tests[i]); release_filter(fp, i); @@ -2018,13 +4649,24 @@ static __init int test_bpf(void) } } - pr_info("Summary: %d PASSED, %d FAILED\n", pass_cnt, err_cnt); + pr_info("Summary: %d PASSED, %d FAILED, [%d/%d JIT'ed]\n", + pass_cnt, err_cnt, jit_cnt, run_cnt); + return err_cnt ? -EINVAL : 0; } static int __init test_bpf_init(void) { - return test_bpf(); + int ret; + + ret = prepare_bpf_tests(); + if (ret < 0) + return ret; + + ret = test_bpf(); + + destroy_bpf_tests(); + return ret; } static void __exit test_bpf_exit(void) diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index b2957540d3c7..c90777eae1f8 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -1,14 +1,9 @@ /* * Resizable, Scalable, Concurrent Hash Table * - * Copyright (c) 2014 Thomas Graf <tgraf@suug.ch> + * Copyright (c) 2014-2015 Thomas Graf <tgraf@suug.ch> * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> * - * Based on the following paper: - * https://www.usenix.org/legacy/event/atc11/tech/final_files/Triplett.pdf - * - * Code partially derived from nft_hash - * * 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. @@ -26,20 +21,37 @@ #include <linux/rhashtable.h> #include <linux/slab.h> +#define MAX_ENTRIES 1000000 +#define TEST_INSERT_FAIL INT_MAX + +static int entries = 50000; +module_param(entries, int, 0); +MODULE_PARM_DESC(entries, "Number of entries to add (default: 50000)"); + +static int runs = 4; +module_param(runs, int, 0); +MODULE_PARM_DESC(runs, "Number of test runs per variant (default: 4)"); + +static int max_size = 65536; +module_param(max_size, int, 0); +MODULE_PARM_DESC(runs, "Maximum table size (default: 65536)"); -#define TEST_HT_SIZE 8 -#define TEST_ENTRIES 2048 -#define TEST_PTR ((void *) 0xdeadbeef) -#define TEST_NEXPANDS 4 +static bool shrinking = false; +module_param(shrinking, bool, 0); +MODULE_PARM_DESC(shrinking, "Enable automatic shrinking (default: off)"); + +static int size = 8; +module_param(size, int, 0); +MODULE_PARM_DESC(size, "Initial size hint of table (default: 8)"); struct test_obj { - void *ptr; int value; struct rhash_head node; }; -static const struct rhashtable_params test_rht_params = { - .nelem_hint = TEST_HT_SIZE, +static struct test_obj array[MAX_ENTRIES]; + +static struct rhashtable_params test_rht_params = { .head_offset = offsetof(struct test_obj, node), .key_offset = offsetof(struct test_obj, value), .key_len = sizeof(int), @@ -51,11 +63,14 @@ static int __init test_rht_lookup(struct rhashtable *ht) { unsigned int i; - for (i = 0; i < TEST_ENTRIES * 2; i++) { + for (i = 0; i < entries * 2; i++) { struct test_obj *obj; bool expected = !(i % 2); u32 key = i; + if (array[i / 2].value == TEST_INSERT_FAIL) + expected = false; + obj = rhashtable_lookup_fast(ht, &key, test_rht_params); if (expected && !obj) { @@ -66,9 +81,9 @@ static int __init test_rht_lookup(struct rhashtable *ht) key); return -EEXIST; } else if (expected && obj) { - if (obj->ptr != TEST_PTR || obj->value != i) { - pr_warn("Test failed: Lookup value mismatch %p!=%p, %u!=%u\n", - obj->ptr, TEST_PTR, obj->value, i); + if (obj->value != i) { + pr_warn("Test failed: Lookup value mismatch %u!=%u\n", + obj->value, i); return -EINVAL; } } @@ -77,129 +92,147 @@ static int __init test_rht_lookup(struct rhashtable *ht) return 0; } -static void test_bucket_stats(struct rhashtable *ht, bool quiet) +static void test_bucket_stats(struct rhashtable *ht) { - unsigned int cnt, rcu_cnt, i, total = 0; + unsigned int err, total = 0, chain_len = 0; + struct rhashtable_iter hti; struct rhash_head *pos; - struct test_obj *obj; - struct bucket_table *tbl; - tbl = rht_dereference_rcu(ht->tbl, ht); - for (i = 0; i < tbl->size; i++) { - rcu_cnt = cnt = 0; + err = rhashtable_walk_init(ht, &hti); + if (err) { + pr_warn("Test failed: allocation error"); + return; + } - if (!quiet) - pr_info(" [%#4x/%u]", i, tbl->size); + err = rhashtable_walk_start(&hti); + if (err && err != -EAGAIN) { + pr_warn("Test failed: iterator failed: %d\n", err); + return; + } - rht_for_each_entry_rcu(obj, pos, tbl, i, node) { - cnt++; - total++; - if (!quiet) - pr_cont(" [%p],", obj); + while ((pos = rhashtable_walk_next(&hti))) { + if (PTR_ERR(pos) == -EAGAIN) { + pr_info("Info: encountered resize\n"); + chain_len++; + continue; + } else if (IS_ERR(pos)) { + pr_warn("Test failed: rhashtable_walk_next() error: %ld\n", + PTR_ERR(pos)); + break; } - rht_for_each_entry_rcu(obj, pos, tbl, i, node) - rcu_cnt++; - - if (rcu_cnt != cnt) - pr_warn("Test failed: Chain count mismach %d != %d", - cnt, rcu_cnt); - - if (!quiet) - pr_cont("\n [%#x] first element: %p, chain length: %u\n", - i, tbl->buckets[i], cnt); + total++; } - pr_info(" Traversal complete: counted=%u, nelems=%u, entries=%d\n", - total, atomic_read(&ht->nelems), TEST_ENTRIES); + rhashtable_walk_stop(&hti); + rhashtable_walk_exit(&hti); + + pr_info(" Traversal complete: counted=%u, nelems=%u, entries=%d, table-jumps=%u\n", + total, atomic_read(&ht->nelems), entries, chain_len); - if (total != atomic_read(&ht->nelems) || total != TEST_ENTRIES) + if (total != atomic_read(&ht->nelems) || total != entries) pr_warn("Test failed: Total count mismatch ^^^"); } -static int __init test_rhashtable(struct rhashtable *ht) +static s64 __init test_rhashtable(struct rhashtable *ht) { - struct bucket_table *tbl; struct test_obj *obj; - struct rhash_head *pos, *next; int err; - unsigned int i; + unsigned int i, insert_fails = 0; + s64 start, end; /* * Insertion Test: - * Insert TEST_ENTRIES into table with all keys even numbers + * Insert entries into table with all keys even numbers */ - pr_info(" Adding %d keys\n", TEST_ENTRIES); - for (i = 0; i < TEST_ENTRIES; i++) { - struct test_obj *obj; - - obj = kzalloc(sizeof(*obj), GFP_KERNEL); - if (!obj) { - err = -ENOMEM; - goto error; - } + pr_info(" Adding %d keys\n", entries); + start = ktime_get_ns(); + for (i = 0; i < entries; i++) { + struct test_obj *obj = &array[i]; - obj->ptr = TEST_PTR; obj->value = i * 2; err = rhashtable_insert_fast(ht, &obj->node, test_rht_params); - if (err) { - kfree(obj); - goto error; + if (err == -ENOMEM || err == -EBUSY) { + /* Mark failed inserts but continue */ + obj->value = TEST_INSERT_FAIL; + insert_fails++; + } else if (err) { + return err; } } + if (insert_fails) + pr_info(" %u insertions failed due to memory pressure\n", + insert_fails); + + test_bucket_stats(ht); rcu_read_lock(); - test_bucket_stats(ht, true); test_rht_lookup(ht); rcu_read_unlock(); - rcu_read_lock(); - test_bucket_stats(ht, true); - rcu_read_unlock(); + test_bucket_stats(ht); - pr_info(" Deleting %d keys\n", TEST_ENTRIES); - for (i = 0; i < TEST_ENTRIES; i++) { + pr_info(" Deleting %d keys\n", entries); + for (i = 0; i < entries; i++) { u32 key = i * 2; - obj = rhashtable_lookup_fast(ht, &key, test_rht_params); - BUG_ON(!obj); + if (array[i].value != TEST_INSERT_FAIL) { + obj = rhashtable_lookup_fast(ht, &key, test_rht_params); + BUG_ON(!obj); - rhashtable_remove_fast(ht, &obj->node, test_rht_params); - kfree(obj); + rhashtable_remove_fast(ht, &obj->node, test_rht_params); + } } - return 0; - -error: - tbl = rht_dereference_rcu(ht->tbl, ht); - for (i = 0; i < tbl->size; i++) - rht_for_each_entry_safe(obj, pos, next, tbl, i, node) - kfree(obj); + end = ktime_get_ns(); + pr_info(" Duration of test: %lld ns\n", end - start); - return err; + return end - start; } static struct rhashtable ht; static int __init test_rht_init(void) { - int err; + int i, err; + u64 total_time = 0; - pr_info("Running resizable hashtable tests...\n"); + entries = min(entries, MAX_ENTRIES); - err = rhashtable_init(&ht, &test_rht_params); - if (err < 0) { - pr_warn("Test failed: Unable to initialize hashtable: %d\n", - err); - return err; - } + test_rht_params.automatic_shrinking = shrinking; + test_rht_params.max_size = max_size; + test_rht_params.nelem_hint = size; - err = test_rhashtable(&ht); + pr_info("Running rhashtable test nelem=%d, max_size=%d, shrinking=%d\n", + size, max_size, shrinking); - rhashtable_destroy(&ht); + for (i = 0; i < runs; i++) { + s64 time; - return err; + pr_info("Test %02d:\n", i); + memset(&array, 0, sizeof(array)); + err = rhashtable_init(&ht, &test_rht_params); + if (err < 0) { + pr_warn("Test failed: Unable to initialize hashtable: %d\n", + err); + continue; + } + + time = test_rhashtable(&ht); + rhashtable_destroy(&ht); + if (time < 0) { + pr_warn("Test failed: return code %lld\n", time); + return -EINVAL; + } + + total_time += time; + } + + do_div(total_time, runs); + pr_info("Average test time: %llu\n", total_time); + + return 0; } static void __exit test_rht_exit(void) |