From: Robin Murphy Date: Mon, 10 Dec 2018 14:00:33 +0000 (+0000) Subject: dma-debug: Batch dma_debug_entry allocation X-Git-Url: http://git.cdn.openwrt.org/?a=commitdiff_plain;h=ad78dee0b630527bdfed809d1f5ed95c601886ae;p=openwrt%2Fstaging%2Fblogic.git dma-debug: Batch dma_debug_entry allocation DMA debug entries are one of those things which aren't that useful individually - we will always want some larger quantity of them - and which we don't really need to manage the exact number of - we only care about having 'enough'. In that regard, the current behaviour of creating them one-by-one leads to a lot of unwarranted function call overhead and memory wasted on alignment padding. Now that we don't have to worry about freeing anything via dma_debug_resize_entries(), we can optimise the allocation behaviour by grabbing whole pages at once, which will save considerably on the aforementioned overheads, and probably offer a little more cache/TLB locality benefit for traversing the lists under normal operation. This should also give even less reason for an architecture-level override of the preallocation size, so make the definition unconditional - if there is still any desire to change the compile-time value for some platforms it would be better off as a Kconfig option anyway. Since freeing a whole page of entries at once becomes enough of a challenge that it's not really worth complicating dma_debug_init(), we may as well tweak the preallocation behaviour such that as long as we manage to allocate *some* pages, we can leave debugging enabled on a best-effort basis rather than otherwise wasting them. Signed-off-by: Robin Murphy Tested-by: Qian Cai Signed-off-by: Christoph Hellwig --- diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt index 7a7d8a415ce8..016eb6909b8a 100644 --- a/Documentation/DMA-API.txt +++ b/Documentation/DMA-API.txt @@ -747,7 +747,9 @@ driver afterwards. This filter can be disabled or changed later using debugfs. When the code disables itself at runtime this is most likely because it ran out of dma_debug_entries and was unable to allocate more on-demand. 65536 entries are preallocated at boot - if this is too low for you boot with -'dma_debug_entries=' to overwrite the default. The +'dma_debug_entries=' to overwrite the default. Note +that the code allocates entries in batches, so the exact number of +preallocated entries may be greater than the actual number requested. The code will print to the kernel log each time it has dynamically allocated as many entries as were initially preallocated. This is to indicate that a larger preallocation size may be appropriate, or if it happens continually diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 36a42874b05f..20ab0f6c1b70 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -43,12 +43,9 @@ #define HASH_FN_SHIFT 13 #define HASH_FN_MASK (HASH_SIZE - 1) -/* allow architectures to override this if absolutely required */ -#ifndef PREALLOC_DMA_DEBUG_ENTRIES #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16) -#endif /* If the pool runs out, add this many new entries at once */ -#define DMA_DEBUG_DYNAMIC_ENTRIES 256 +#define DMA_DEBUG_DYNAMIC_ENTRIES (PAGE_SIZE / sizeof(struct dma_debug_entry)) enum { dma_debug_single, @@ -648,32 +645,22 @@ static void add_dma_entry(struct dma_debug_entry *entry) */ } -static int dma_debug_create_entries(u32 num_entries, gfp_t gfp) +static int dma_debug_create_entries(gfp_t gfp) { - struct dma_debug_entry *entry, *next_entry; + struct dma_debug_entry *entry; int i; - for (i = 0; i < num_entries; ++i) { - entry = kzalloc(sizeof(*entry), gfp); - if (!entry) - goto out_err; + entry = (void *)get_zeroed_page(gfp); + if (!entry) + return -ENOMEM; - list_add_tail(&entry->list, &free_entries); - } + for (i = 0; i < DMA_DEBUG_DYNAMIC_ENTRIES; i++) + list_add_tail(&entry[i].list, &free_entries); - num_free_entries += num_entries; - nr_total_entries += num_entries; + num_free_entries += DMA_DEBUG_DYNAMIC_ENTRIES; + nr_total_entries += DMA_DEBUG_DYNAMIC_ENTRIES; return 0; - -out_err: - - list_for_each_entry_safe(entry, next_entry, &free_entries, list) { - list_del(&entry->list); - kfree(entry); - } - - return -ENOMEM; } static struct dma_debug_entry *__dma_entry_alloc(void) @@ -715,8 +702,7 @@ static struct dma_debug_entry *dma_entry_alloc(void) spin_lock_irqsave(&free_entries_lock, flags); if (num_free_entries == 0) { - if (dma_debug_create_entries(DMA_DEBUG_DYNAMIC_ENTRIES, - GFP_ATOMIC)) { + if (dma_debug_create_entries(GFP_ATOMIC)) { global_disable = true; spin_unlock_irqrestore(&free_entries_lock, flags); pr_err("debugging out of memory - disabling\n"); @@ -987,7 +973,7 @@ void dma_debug_add_bus(struct bus_type *bus) static int dma_debug_init(void) { - int i; + int i, nr_pages; /* Do not use dma_debug_initialized here, since we really want to be * called to set dma_debug_initialized @@ -1007,15 +993,21 @@ static int dma_debug_init(void) return 0; } - if (dma_debug_create_entries(nr_prealloc_entries, GFP_KERNEL) != 0) { + nr_pages = DIV_ROUND_UP(nr_prealloc_entries, DMA_DEBUG_DYNAMIC_ENTRIES); + for (i = 0; i < nr_pages; ++i) + dma_debug_create_entries(GFP_KERNEL); + if (num_free_entries >= nr_prealloc_entries) { + pr_info("preallocated %d debug entries\n", nr_total_entries); + } else if (num_free_entries > 0) { + pr_warn("%d debug entries requested but only %d allocated\n", + nr_prealloc_entries, nr_total_entries); + } else { pr_err("debugging out of memory error - disabled\n"); global_disable = true; return 0; } - min_free_entries = num_free_entries; - pr_info("preallocated %d debug entries\n", nr_total_entries); dma_debug_initialized = true;