From 62d342d6706069b4257611cb1a855f53b3fb4b02 Mon Sep 17 00:00:00 2001 From: Nicolas Boichat Date: Thu, 28 Mar 2019 20:43:42 -0700 Subject: [PATCH] mm: add support for kmem caches in DMA32 zone commit 6d6ea1e967a246f12cfe2f5fb743b70b2e608d4a upstream. Patch series "iommu/io-pgtable-arm-v7s: Use DMA32 zone for page tables", v6. This is a followup to the discussion in [1], [2]. IOMMUs using ARMv7 short-descriptor format require page tables (level 1 and 2) to be allocated within the first 4GB of RAM, even on 64-bit systems. For L1 tables that are bigger than a page, we can just use __get_free_pages with GFP_DMA32 (on arm64 systems only, arm would still use GFP_DMA). For L2 tables that only take 1KB, it would be a waste to allocate a full page, so we considered 3 approaches: 1. This series, adding support for GFP_DMA32 slab caches. 2. genalloc, which requires pre-allocating the maximum number of L2 page tables (4096, so 4MB of memory). 3. page_frag, which is not very memory-efficient as it is unable to reuse freed fragments until the whole page is freed. [3] This series is the most memory-efficient approach. stable@ note: We confirmed that this is a regression, and IOMMU errors happen on 4.19 and linux-next/master on MT8173 (elm, Acer Chromebook R13). The issue most likely starts from commit ad67f5a6545f ("arm64: replace ZONE_DMA with ZONE_DMA32"), i.e. 4.15, and presumably breaks a number of Mediatek platforms (and maybe others?). [1] https://lists.linuxfoundation.org/pipermail/iommu/2018-November/030876.html [2] https://lists.linuxfoundation.org/pipermail/iommu/2018-December/031696.html [3] https://patchwork.codeaurora.org/patch/671639/ This patch (of 3): IOMMUs using ARMv7 short-descriptor format require page tables to be allocated within the first 4GB of RAM, even on 64-bit systems. On arm64, this is done by passing GFP_DMA32 flag to memory allocation functions. For IOMMU L2 tables that only take 1KB, it would be a waste to allocate a full page using get_free_pages, so we considered 3 approaches: 1. This patch, adding support for GFP_DMA32 slab caches. 2. genalloc, which requires pre-allocating the maximum number of L2 page tables (4096, so 4MB of memory). 3. page_frag, which is not very memory-efficient as it is unable to reuse freed fragments until the whole page is freed. This change makes it possible to create a custom cache in DMA32 zone using kmem_cache_create, then allocate memory using kmem_cache_alloc. We do not create a DMA32 kmalloc cache array, as there are currently no users of kmalloc(..., GFP_DMA32). These calls will continue to trigger a warning, as we keep GFP_DMA32 in GFP_SLAB_BUG_MASK. This implies that calls to kmem_cache_*alloc on a SLAB_CACHE_DMA32 kmem_cache must _not_ use GFP_DMA32 (it is anyway redundant and unnecessary). Link: http://lkml.kernel.org/r/20181210011504.122604-2-drinkcat@chromium.org Signed-off-by: Nicolas Boichat Acked-by: Vlastimil Babka Acked-by: Will Deacon Cc: Robin Murphy Cc: Joerg Roedel Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Michal Hocko Cc: Mel Gorman Cc: Sasha Levin Cc: Huaisheng Ye Cc: Mike Rapoport Cc: Yong Wu Cc: Matthias Brugger Cc: Tomasz Figa Cc: Yingjoe Chen Cc: Christoph Hellwig Cc: Matthew Wilcox Cc: Hsin-Yi Wang Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/slab.h | 2 ++ mm/slab.c | 2 ++ mm/slab.h | 3 ++- mm/slab_common.c | 2 +- mm/slub.c | 5 +++++ 5 files changed, 12 insertions(+), 2 deletions(-) diff --git a/include/linux/slab.h b/include/linux/slab.h index ed9cbdd..d639341 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -32,6 +32,8 @@ #define SLAB_HWCACHE_ALIGN ((slab_flags_t __force)0x00002000U) /* Use GFP_DMA memory */ #define SLAB_CACHE_DMA ((slab_flags_t __force)0x00004000U) +/* Use GFP_DMA32 memory */ +#define SLAB_CACHE_DMA32 ((slab_flags_t __force)0x00008000U) /* DEBUG: Store the last owner for bug hunting */ #define SLAB_STORE_USER ((slab_flags_t __force)0x00010000U) /* Panic if kmem_cache_create() fails */ diff --git a/mm/slab.c b/mm/slab.c index fad6839..364e42d 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2124,6 +2124,8 @@ done: cachep->allocflags = __GFP_COMP; if (flags & SLAB_CACHE_DMA) cachep->allocflags |= GFP_DMA; + if (flags & SLAB_CACHE_DMA32) + cachep->allocflags |= GFP_DMA32; if (flags & SLAB_RECLAIM_ACCOUNT) cachep->allocflags |= __GFP_RECLAIMABLE; cachep->size = size; diff --git a/mm/slab.h b/mm/slab.h index 58c6c1c..9632772 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -127,7 +127,8 @@ static inline slab_flags_t kmem_cache_flags(unsigned int object_size, /* Legal flag mask for kmem_cache_create(), for various configurations */ -#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | SLAB_PANIC | \ +#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \ + SLAB_CACHE_DMA32 | SLAB_PANIC | \ SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS ) #if defined(CONFIG_DEBUG_SLAB) diff --git a/mm/slab_common.c b/mm/slab_common.c index 3a7ac4f..4d3c2e7 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -53,7 +53,7 @@ static DECLARE_WORK(slab_caches_to_rcu_destroy_work, SLAB_FAILSLAB | SLAB_KASAN) #define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \ - SLAB_ACCOUNT) + SLAB_CACHE_DMA32 | SLAB_ACCOUNT) /* * Merge control. If this is set then no merging of slab caches will occur. diff --git a/mm/slub.c b/mm/slub.c index 8da34a8..09c0e24 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3539,6 +3539,9 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) if (s->flags & SLAB_CACHE_DMA) s->allocflags |= GFP_DMA; + if (s->flags & SLAB_CACHE_DMA32) + s->allocflags |= GFP_DMA32; + if (s->flags & SLAB_RECLAIM_ACCOUNT) s->allocflags |= __GFP_RECLAIMABLE; @@ -5633,6 +5636,8 @@ static char *create_unique_id(struct kmem_cache *s) */ if (s->flags & SLAB_CACHE_DMA) *p++ = 'd'; + if (s->flags & SLAB_CACHE_DMA32) + *p++ = 'D'; if (s->flags & SLAB_RECLAIM_ACCOUNT) *p++ = 'a'; if (s->flags & SLAB_CONSISTENCY_CHECKS) -- 2.7.4