From a37b0715ddf3007734c4e2424c14bc7efcdd1190 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 1 Jun 2020 21:48:18 -0700 Subject: mm/writeback: replace PF_LESS_THROTTLE with PF_LOCAL_THROTTLE PF_LESS_THROTTLE exists for loop-back nfsd (and a similar need in the loop block driver and callers of prctl(PR_SET_IO_FLUSHER)), where a daemon needs to write to one bdi (the final bdi) in order to free up writes queued to another bdi (the client bdi). The daemon sets PF_LESS_THROTTLE and gets a larger allowance of dirty pages, so that it can still dirty pages after other processses have been throttled. The purpose of this is to avoid deadlock that happen when the PF_LESS_THROTTLE process must write for any dirty pages to be freed, but it is being thottled and cannot write. This approach was designed when all threads were blocked equally, independently on which device they were writing to, or how fast it was. Since that time the writeback algorithm has changed substantially with different threads getting different allowances based on non-trivial heuristics. This means the simple "add 25%" heuristic is no longer reliable. The important issue is not that the daemon needs a *larger* dirty page allowance, but that it needs a *private* dirty page allowance, so that dirty pages for the "client" bdi that it is helping to clear (the bdi for an NFS filesystem or loop block device etc) do not affect the throttling of the daemon writing to the "final" bdi. This patch changes the heuristic so that the task is not throttled when the bdi it is writing to has a dirty page count below below (or equal to) the free-run threshold for that bdi. This ensures it will always be able to have some pages in flight, and so will not deadlock. In a steady-state, it is expected that PF_LOCAL_THROTTLE tasks might still be throttled by global threshold, but that is acceptable as it is only the deadlock state that is interesting for this flag. This approach of "only throttle when target bdi is busy" is consistent with the other use of PF_LESS_THROTTLE in current_may_throttle(), were it causes attention to be focussed only on the target bdi. So this patch - renames PF_LESS_THROTTLE to PF_LOCAL_THROTTLE, - removes the 25% bonus that that flag gives, and - If PF_LOCAL_THROTTLE is set, don't delay at all unless the global and the local free-run thresholds are exceeded. Note that previously realtime threads were treated the same as PF_LESS_THROTTLE threads. This patch does *not* change the behvaiour for real-time threads, so it is now different from the behaviour of nfsd and loop tasks. I don't know what is wanted for realtime. [akpm@linux-foundation.org: coding style fixes] Signed-off-by: NeilBrown Signed-off-by: Andrew Morton Reviewed-by: Jan Kara Acked-by: Chuck Lever [nfsd] Cc: Christoph Hellwig Cc: Michal Hocko Cc: Trond Myklebust Link: http://lkml.kernel.org/r/87ftbf7gs3.fsf@notabene.neil.brown.name Signed-off-by: Linus Torvalds --- kernel/sys.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sys.c b/kernel/sys.c index d325f3ab624a..180a2fa33f7f 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2262,7 +2262,7 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, return -EINVAL; } -#define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LESS_THROTTLE) +#define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE) SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) -- cgit v1.2.3 From 515e5b6d90d410a3b0b433853c367936830a45a4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:50:32 -0700 Subject: dma-mapping: use vmap insted of reimplementing it Replace the open coded instance of vmap with the actual function. In the non-contiguous (IOMMU) case this requires an extra find_vm_area, but given that this isn't a fast path function that is a small price to pay. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-6-hch@lst.de Signed-off-by: Linus Torvalds --- kernel/dma/remap.c | 48 ++++++++++++------------------------------------ 1 file changed, 12 insertions(+), 36 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index d14cbc83986a..914ff5a58dd5 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -20,23 +20,6 @@ struct page **dma_common_find_pages(void *cpu_addr) return area->pages; } -static struct vm_struct *__dma_common_pages_remap(struct page **pages, - size_t size, pgprot_t prot, const void *caller) -{ - struct vm_struct *area; - - area = get_vm_area_caller(size, VM_DMA_COHERENT, caller); - if (!area) - return NULL; - - if (map_vm_area(area, prot, pages)) { - vunmap(area->addr); - return NULL; - } - - return area; -} - /* * Remaps an array of PAGE_SIZE pages into another vm_area. * Cannot be used in non-sleeping contexts @@ -44,15 +27,12 @@ static struct vm_struct *__dma_common_pages_remap(struct page **pages, void *dma_common_pages_remap(struct page **pages, size_t size, pgprot_t prot, const void *caller) { - struct vm_struct *area; + void *vaddr; - area = __dma_common_pages_remap(pages, size, prot, caller); - if (!area) - return NULL; - - area->pages = pages; - - return area->addr; + vaddr = vmap(pages, size >> PAGE_SHIFT, VM_DMA_COHERENT, prot); + if (vaddr) + find_vm_area(vaddr)->pages = pages; + return vaddr; } /* @@ -62,24 +42,20 @@ void *dma_common_pages_remap(struct page **pages, size_t size, void *dma_common_contiguous_remap(struct page *page, size_t size, pgprot_t prot, const void *caller) { - int i; + int count = size >> PAGE_SHIFT; struct page **pages; - struct vm_struct *area; + void *vaddr; + int i; - pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL); + pages = kmalloc_array(count, sizeof(struct page *), GFP_KERNEL); if (!pages) return NULL; - - for (i = 0; i < (size >> PAGE_SHIFT); i++) + for (i = 0; i < count; i++) pages[i] = nth_page(page, i); - - area = __dma_common_pages_remap(pages, size, prot, caller); - + vaddr = vmap(pages, count, VM_DMA_COHERENT, prot); kfree(pages); - if (!area) - return NULL; - return area->addr; + return vaddr; } /* -- cgit v1.2.3 From 88dca4ca5a93d2c09e5bbc6a62fbfc3af83c4fca Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:40 -0700 Subject: mm: remove the pgprot argument to __vmalloc The pgprot argument to __vmalloc is always PAGE_KERNEL now, so remove it. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Reviewed-by: Michael Kelley [hyperv] Acked-by: Gao Xiang [erofs] Acked-by: Peter Zijlstra (Intel) Acked-by: Wei Liu Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-22-hch@lst.de Signed-off-by: Linus Torvalds --- arch/x86/hyperv/hv_init.c | 3 +-- arch/x86/include/asm/kvm_host.h | 3 +-- arch/x86/kvm/svm/sev.c | 3 +-- drivers/block/drbd/drbd_bitmap.c | 4 +--- drivers/gpu/drm/etnaviv/etnaviv_dump.c | 4 ++-- drivers/lightnvm/pblk-init.c | 5 ++--- drivers/md/dm-bufio.c | 4 ++-- drivers/mtd/ubi/io.c | 4 ++-- drivers/scsi/sd_zbc.c | 3 +-- fs/gfs2/dir.c | 9 ++++----- fs/gfs2/quota.c | 2 +- fs/nfs/blocklayout/extent_tree.c | 2 +- fs/ntfs/malloc.h | 2 +- fs/ubifs/debug.c | 2 +- fs/ubifs/lprops.c | 2 +- fs/ubifs/lpt_commit.c | 4 ++-- fs/ubifs/orphan.c | 2 +- fs/xfs/kmem.c | 2 +- include/linux/vmalloc.h | 2 +- kernel/bpf/core.c | 6 +++--- kernel/groups.c | 2 +- kernel/module.c | 3 +-- mm/nommu.c | 15 +++++++-------- mm/page_alloc.c | 2 +- mm/percpu.c | 2 +- mm/vmalloc.c | 4 ++-- net/bridge/netfilter/ebtables.c | 6 ++---- sound/core/memalloc.c | 2 +- sound/core/pcm_memory.c | 2 +- 29 files changed, 47 insertions(+), 59 deletions(-) (limited to 'kernel') diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 697ddd2afef9..e2137070386a 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -97,8 +97,7 @@ static int hv_cpu_init(unsigned int cpu) * not be stopped in the case of CPU offlining and the VM will hang. */ if (!*hvp) { - *hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO, - PAGE_KERNEL); + *hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO); } if (*hvp) { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 0a6b35353fc7..e94b3de564d6 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1279,8 +1279,7 @@ extern struct kmem_cache *x86_fpu_cache; #define __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) { - return __vmalloc(kvm_x86_ops.vm_size, - GFP_KERNEL_ACCOUNT | __GFP_ZERO, PAGE_KERNEL); + return __vmalloc(kvm_x86_ops.vm_size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); } void kvm_arch_free_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 89f7f3aebd31..5573a97f1520 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -336,8 +336,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, /* Avoid using vmalloc for smaller buffers. */ size = npages * sizeof(struct page *); if (size > PAGE_SIZE) - pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO, - PAGE_KERNEL); + pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); else pages = kmalloc(size, GFP_KERNEL_ACCOUNT); diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index 15e99697234a..df53dca5d02c 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -396,9 +396,7 @@ static struct page **bm_realloc_pages(struct drbd_bitmap *b, unsigned long want) bytes = sizeof(struct page *)*want; new_pages = kzalloc(bytes, GFP_NOIO | __GFP_NOWARN); if (!new_pages) { - new_pages = __vmalloc(bytes, - GFP_NOIO | __GFP_ZERO, - PAGE_KERNEL); + new_pages = __vmalloc(bytes, GFP_NOIO | __GFP_ZERO); if (!new_pages) return NULL; } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.c b/drivers/gpu/drm/etnaviv/etnaviv_dump.c index 648cf0207309..706af0304ca4 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_dump.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.c @@ -154,8 +154,8 @@ void etnaviv_core_dump(struct etnaviv_gem_submit *submit) file_size += sizeof(*iter.hdr) * n_obj; /* Allocate the file in vmalloc memory, it's likely to be big */ - iter.start = __vmalloc(file_size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY, - PAGE_KERNEL); + iter.start = __vmalloc(file_size, GFP_KERNEL | __GFP_NOWARN | + __GFP_NORETRY); if (!iter.start) { mutex_unlock(&gpu->mmu_context->lock); dev_warn(gpu->dev, "failed to allocate devcoredump file\n"); diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c index 9a967a2e83dd..6e677ff62cc9 100644 --- a/drivers/lightnvm/pblk-init.c +++ b/drivers/lightnvm/pblk-init.c @@ -145,9 +145,8 @@ static int pblk_l2p_init(struct pblk *pblk, bool factory_init) int ret = 0; map_size = pblk_trans_map_size(pblk); - pblk->trans_map = __vmalloc(map_size, GFP_KERNEL | __GFP_NOWARN - | __GFP_RETRY_MAYFAIL | __GFP_HIGHMEM, - PAGE_KERNEL); + pblk->trans_map = __vmalloc(map_size, GFP_KERNEL | __GFP_NOWARN | + __GFP_RETRY_MAYFAIL | __GFP_HIGHMEM); if (!pblk->trans_map) { pblk_err(pblk, "failed to allocate L2P (need %zu of memory)\n", map_size); diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 2d519c223562..d1786cfd7f22 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -400,13 +400,13 @@ static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask, */ if (gfp_mask & __GFP_NORETRY) { unsigned noio_flag = memalloc_noio_save(); - void *ptr = __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL); + void *ptr = __vmalloc(c->block_size, gfp_mask); memalloc_noio_restore(noio_flag); return ptr; } - return __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL); + return __vmalloc(c->block_size, gfp_mask); } /* diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c index b57b84fb97d0..14d890b00d2c 100644 --- a/drivers/mtd/ubi/io.c +++ b/drivers/mtd/ubi/io.c @@ -1297,7 +1297,7 @@ static int self_check_write(struct ubi_device *ubi, const void *buf, int pnum, if (!ubi_dbg_chk_io(ubi)) return 0; - buf1 = __vmalloc(len, GFP_NOFS, PAGE_KERNEL); + buf1 = __vmalloc(len, GFP_NOFS); if (!buf1) { ubi_err(ubi, "cannot allocate memory to check writes"); return 0; @@ -1361,7 +1361,7 @@ int ubi_self_check_all_ff(struct ubi_device *ubi, int pnum, int offset, int len) if (!ubi_dbg_chk_io(ubi)) return 0; - buf = __vmalloc(len, GFP_NOFS, PAGE_KERNEL); + buf = __vmalloc(len, GFP_NOFS); if (!buf) { ubi_err(ubi, "cannot allocate memory to check for 0xFFs"); return 0; diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index f45c22b09726..8be27426aa66 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -136,8 +136,7 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp, while (bufsize >= SECTOR_SIZE) { buf = __vmalloc(bufsize, - GFP_KERNEL | __GFP_ZERO | __GFP_NORETRY, - PAGE_KERNEL); + GFP_KERNEL | __GFP_ZERO | __GFP_NORETRY); if (buf) { *buflen = bufsize; return buf; diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index c3f7732415be..c0f2875c946c 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -354,7 +354,7 @@ static __be64 *gfs2_dir_get_hash_table(struct gfs2_inode *ip) hc = kmalloc(hsize, GFP_NOFS | __GFP_NOWARN); if (hc == NULL) - hc = __vmalloc(hsize, GFP_NOFS, PAGE_KERNEL); + hc = __vmalloc(hsize, GFP_NOFS); if (hc == NULL) return ERR_PTR(-ENOMEM); @@ -1166,7 +1166,7 @@ static int dir_double_exhash(struct gfs2_inode *dip) hc2 = kmalloc_array(hsize_bytes, 2, GFP_NOFS | __GFP_NOWARN); if (hc2 == NULL) - hc2 = __vmalloc(hsize_bytes * 2, GFP_NOFS, PAGE_KERNEL); + hc2 = __vmalloc(hsize_bytes * 2, GFP_NOFS); if (!hc2) return -ENOMEM; @@ -1327,7 +1327,7 @@ static void *gfs2_alloc_sort_buffer(unsigned size) if (size < KMALLOC_MAX_SIZE) ptr = kmalloc(size, GFP_NOFS | __GFP_NOWARN); if (!ptr) - ptr = __vmalloc(size, GFP_NOFS, PAGE_KERNEL); + ptr = __vmalloc(size, GFP_NOFS); return ptr; } @@ -1987,8 +1987,7 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len, ht = kzalloc(size, GFP_NOFS | __GFP_NOWARN); if (ht == NULL) - ht = __vmalloc(size, GFP_NOFS | __GFP_NOWARN | __GFP_ZERO, - PAGE_KERNEL); + ht = __vmalloc(size, GFP_NOFS | __GFP_NOWARN | __GFP_ZERO); if (!ht) return -ENOMEM; diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 8259fef3f986..4b67d47a7e00 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1365,7 +1365,7 @@ int gfs2_quota_init(struct gfs2_sbd *sdp) sdp->sd_quota_bitmap = kzalloc(bm_size, GFP_NOFS | __GFP_NOWARN); if (sdp->sd_quota_bitmap == NULL) sdp->sd_quota_bitmap = __vmalloc(bm_size, GFP_NOFS | - __GFP_ZERO, PAGE_KERNEL); + __GFP_ZERO); if (!sdp->sd_quota_bitmap) return error; diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c index 7a57ff2528af..8f7cff7a4293 100644 --- a/fs/nfs/blocklayout/extent_tree.c +++ b/fs/nfs/blocklayout/extent_tree.c @@ -582,7 +582,7 @@ retry: if (!arg->layoutupdate_pages) return -ENOMEM; - start_p = __vmalloc(buffer_size, GFP_NOFS, PAGE_KERNEL); + start_p = __vmalloc(buffer_size, GFP_NOFS); if (!start_p) { kfree(arg->layoutupdate_pages); return -ENOMEM; diff --git a/fs/ntfs/malloc.h b/fs/ntfs/malloc.h index 842b0bfc3ac9..7068425735f1 100644 --- a/fs/ntfs/malloc.h +++ b/fs/ntfs/malloc.h @@ -34,7 +34,7 @@ static inline void *__ntfs_malloc(unsigned long size, gfp_t gfp_mask) /* return (void *)__get_free_page(gfp_mask); */ } if (likely((size >> PAGE_SHIFT) < totalram_pages())) - return __vmalloc(size, gfp_mask, PAGE_KERNEL); + return __vmalloc(size, gfp_mask); return NULL; } diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 0f5a480fe264..31288d8fa2ce 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -815,7 +815,7 @@ void ubifs_dump_leb(const struct ubifs_info *c, int lnum) pr_err("(pid %d) start dumping LEB %d\n", current->pid, lnum); - buf = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL); + buf = __vmalloc(c->leb_size, GFP_NOFS); if (!buf) { ubifs_err(c, "cannot allocate memory for dumping LEB %d", lnum); return; diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c index 29826c51883a..22bfda158f7f 100644 --- a/fs/ubifs/lprops.c +++ b/fs/ubifs/lprops.c @@ -1095,7 +1095,7 @@ static int scan_check_cb(struct ubifs_info *c, return LPT_SCAN_CONTINUE; } - buf = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL); + buf = __vmalloc(c->leb_size, GFP_NOFS); if (!buf) return -ENOMEM; diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c index ff5e0411cf2d..d76a19e460cd 100644 --- a/fs/ubifs/lpt_commit.c +++ b/fs/ubifs/lpt_commit.c @@ -1596,7 +1596,7 @@ static int dbg_check_ltab_lnum(struct ubifs_info *c, int lnum) if (!dbg_is_chk_lprops(c)) return 0; - buf = p = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL); + buf = p = __vmalloc(c->leb_size, GFP_NOFS); if (!buf) { ubifs_err(c, "cannot allocate memory for ltab checking"); return 0; @@ -1845,7 +1845,7 @@ static void dump_lpt_leb(const struct ubifs_info *c, int lnum) void *buf, *p; pr_err("(pid %d) start dumping LEB %d\n", current->pid, lnum); - buf = p = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL); + buf = p = __vmalloc(c->leb_size, GFP_NOFS); if (!buf) { ubifs_err(c, "cannot allocate memory to dump LPT"); return; diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c index 283f9eb48410..2c294085ffed 100644 --- a/fs/ubifs/orphan.c +++ b/fs/ubifs/orphan.c @@ -977,7 +977,7 @@ static int dbg_scan_orphans(struct ubifs_info *c, struct check_info *ci) if (c->no_orphs) return 0; - buf = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL); + buf = __vmalloc(c->leb_size, GFP_NOFS); if (!buf) { ubifs_err(c, "cannot allocate memory to check orphans"); return 0; diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index 1da94237a8cf..f1366475c389 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -48,7 +48,7 @@ __kmem_vmalloc(size_t size, xfs_km_flags_t flags) if (flags & KM_NOFS) nofs_flag = memalloc_nofs_save(); - ptr = __vmalloc(size, lflags, PAGE_KERNEL); + ptr = __vmalloc(size, lflags); if (flags & KM_NOFS) memalloc_nofs_restore(nofs_flag); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 5488cea5ef11..1c278e030599 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -110,7 +110,7 @@ extern void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags); extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); -extern void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot); +extern void *__vmalloc(unsigned long size, gfp_t gfp_mask); extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 14aa1f74dd10..cf6fe9107f5c 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -82,7 +82,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag struct bpf_prog *fp; size = round_up(size, PAGE_SIZE); - fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); + fp = __vmalloc(size, gfp_flags); if (fp == NULL) return NULL; @@ -232,7 +232,7 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, if (ret) return NULL; - fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); + fp = __vmalloc(size, gfp_flags); if (fp == NULL) { __bpf_prog_uncharge(fp_old->aux->user, delta); } else { @@ -1089,7 +1089,7 @@ static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other, gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; - fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags, PAGE_KERNEL); + fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags); if (fp != NULL) { /* aux->prog still points to the fp_other one, so * when promoting the clone to the real program, diff --git a/kernel/groups.c b/kernel/groups.c index daae2f2dc6d4..6ee6691f6839 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -20,7 +20,7 @@ struct group_info *groups_alloc(int gidsetsize) len = sizeof(struct group_info) + sizeof(kgid_t) * gidsetsize; gi = kmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_NOWARN|__GFP_NORETRY); if (!gi) - gi = __vmalloc(len, GFP_KERNEL_ACCOUNT, PAGE_KERNEL); + gi = __vmalloc(len, GFP_KERNEL_ACCOUNT); if (!gi) return NULL; diff --git a/kernel/module.c b/kernel/module.c index 646f1e2330d2..086618a0058f 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2946,8 +2946,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len, return err; /* Suck in entire file: we'll want most of it. */ - info->hdr = __vmalloc(info->len, - GFP_KERNEL | __GFP_NOWARN, PAGE_KERNEL); + info->hdr = __vmalloc(info->len, GFP_KERNEL | __GFP_NOWARN); if (!info->hdr) return -ENOMEM; diff --git a/mm/nommu.c b/mm/nommu.c index 4f07b7ef0297..2df549adb22b 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -140,7 +140,7 @@ void vfree(const void *addr) } EXPORT_SYMBOL(vfree); -void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) +void *__vmalloc(unsigned long size, gfp_t gfp_mask) { /* * You can't specify __GFP_HIGHMEM with kmalloc() since kmalloc() @@ -152,14 +152,14 @@ EXPORT_SYMBOL(__vmalloc); void *__vmalloc_node_flags(unsigned long size, int node, gfp_t flags) { - return __vmalloc(size, flags, PAGE_KERNEL); + return __vmalloc(size, flags); } static void *__vmalloc_user_flags(unsigned long size, gfp_t flags) { void *ret; - ret = __vmalloc(size, flags, PAGE_KERNEL); + ret = __vmalloc(size, flags); if (ret) { struct vm_area_struct *vma; @@ -230,7 +230,7 @@ long vwrite(char *buf, char *addr, unsigned long count) */ void *vmalloc(unsigned long size) { - return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL); + return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM); } EXPORT_SYMBOL(vmalloc); @@ -248,8 +248,7 @@ EXPORT_SYMBOL(vmalloc); */ void *vzalloc(unsigned long size) { - return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, - PAGE_KERNEL); + return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); } EXPORT_SYMBOL(vzalloc); @@ -302,7 +301,7 @@ EXPORT_SYMBOL(vzalloc_node); void *vmalloc_exec(unsigned long size) { - return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC); + return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM); } /** @@ -314,7 +313,7 @@ void *vmalloc_exec(unsigned long size) */ void *vmalloc_32(unsigned long size) { - return __vmalloc(size, GFP_KERNEL, PAGE_KERNEL); + return __vmalloc(size, GFP_KERNEL); } EXPORT_SYMBOL(vmalloc_32); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cc406ee17ad9..45ad73122e82 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8244,7 +8244,7 @@ void *__init alloc_large_system_hash(const char *tablename, table = memblock_alloc_raw(size, SMP_CACHE_BYTES); } else if (get_order(size) >= MAX_ORDER || hashdist) { - table = __vmalloc(size, gfp_flags, PAGE_KERNEL); + table = __vmalloc(size, gfp_flags); virt = true; } else { /* diff --git a/mm/percpu.c b/mm/percpu.c index 7da7d7737dab..696367b18222 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -482,7 +482,7 @@ static void *pcpu_mem_zalloc(size_t size, gfp_t gfp) if (size <= PAGE_SIZE) return kzalloc(size, gfp); else - return __vmalloc(size, gfp | __GFP_ZERO, PAGE_KERNEL); + return __vmalloc(size, gfp | __GFP_ZERO); } /** diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 4d7c7108181a..11194ae18f23 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2564,9 +2564,9 @@ static void *__vmalloc_node(unsigned long size, unsigned long align, gfp_mask, prot, 0, node, caller); } -void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) +void *__vmalloc(unsigned long size, gfp_t gfp_mask) { - return __vmalloc_node(size, 1, gfp_mask, prot, NUMA_NO_NODE, + return __vmalloc_node(size, 1, gfp_mask, PAGE_KERNEL, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(__vmalloc); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 78db58c7aec2..7e869284e052 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1095,16 +1095,14 @@ static int do_replace(struct net *net, const void __user *user, tmp.name[sizeof(tmp.name) - 1] = 0; countersize = COUNTER_OFFSET(tmp.nentries) * nr_cpu_ids; - newinfo = __vmalloc(sizeof(*newinfo) + countersize, GFP_KERNEL_ACCOUNT, - PAGE_KERNEL); + newinfo = __vmalloc(sizeof(*newinfo) + countersize, GFP_KERNEL_ACCOUNT); if (!newinfo) return -ENOMEM; if (countersize) memset(newinfo->counters, 0, countersize); - newinfo->entries = __vmalloc(tmp.entries_size, GFP_KERNEL_ACCOUNT, - PAGE_KERNEL); + newinfo->entries = __vmalloc(tmp.entries_size, GFP_KERNEL_ACCOUNT); if (!newinfo->entries) { ret = -ENOMEM; goto free_newinfo; diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c index a83553fbedf0..bea46ed157a6 100644 --- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -143,7 +143,7 @@ int snd_dma_alloc_pages(int type, struct device *device, size_t size, break; case SNDRV_DMA_TYPE_VMALLOC: gfp = snd_mem_get_gfp_flags(device, GFP_KERNEL | __GFP_HIGHMEM); - dmab->area = __vmalloc(size, gfp, PAGE_KERNEL); + dmab->area = __vmalloc(size, gfp); dmab->addr = 0; break; #ifdef CONFIG_HAS_DMA diff --git a/sound/core/pcm_memory.c b/sound/core/pcm_memory.c index fcab37ea6641..860935e3aea4 100644 --- a/sound/core/pcm_memory.c +++ b/sound/core/pcm_memory.c @@ -460,7 +460,7 @@ int _snd_pcm_lib_alloc_vmalloc_buffer(struct snd_pcm_substream *substream, return 0; /* already large enough */ vfree(runtime->dma_area); } - runtime->dma_area = __vmalloc(size, gfp_flags, PAGE_KERNEL); + runtime->dma_area = __vmalloc(size, gfp_flags); if (!runtime->dma_area) return -ENOMEM; runtime->dma_bytes = size; -- cgit v1.2.3 From 2b9059489c839e67ca9254913325e18cea11a980 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:53 -0700 Subject: mm: remove __vmalloc_node_flags_caller Just use __vmalloc_node instead which gets and extra argument. To be able to to use __vmalloc_node in all caller make it available outside of vmalloc and implement it in nommu.c. [akpm@linux-foundation.org: fix nommu build] Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Cc: Stephen Rothwell Link: http://lkml.kernel.org/r/20200414131348.444715-25-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 4 ++-- kernel/bpf/syscall.c | 5 ++--- mm/nommu.c | 6 +++--- mm/util.c | 2 +- mm/vmalloc.c | 10 +--------- 5 files changed, 9 insertions(+), 18 deletions(-) (limited to 'kernel') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 91d143783458..964d58a060ca 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -115,8 +115,8 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller); -extern void *__vmalloc_node_flags_caller(unsigned long size, - int node, gfp_t flags, void *caller); +void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, + int node, const void *caller); extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4e6dee19a668..9c1cf7a87fb3 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -299,9 +299,8 @@ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) return vmalloc_user_node_flags(size, numa_node, GFP_KERNEL | __GFP_RETRY_MAYFAIL | flags); } - return __vmalloc_node_flags_caller(size, numa_node, - GFP_KERNEL | __GFP_RETRY_MAYFAIL | - flags, __builtin_return_address(0)); + return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_RETRY_MAYFAIL | flags, + numa_node, __builtin_return_address(0)); } void *bpf_map_area_alloc(u64 size, int numa_node) diff --git a/mm/nommu.c b/mm/nommu.c index 9553efa59787..08848fc18672 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -150,10 +150,10 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask) } EXPORT_SYMBOL(__vmalloc); -void *__vmalloc_node_flags_caller(unsigned long size, int node, gfp_t flags, - void *caller) +void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, + int node, const void *caller) { - return __vmalloc(size, flags); + return __vmalloc(size, gfp_mask); } static void *__vmalloc_user_flags(unsigned long size, gfp_t flags) diff --git a/mm/util.c b/mm/util.c index 988d11e6c17c..6d5868adbe18 100644 --- a/mm/util.c +++ b/mm/util.c @@ -580,7 +580,7 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) if (ret || size <= PAGE_SIZE) return ret; - return __vmalloc_node_flags_caller(size, node, flags, + return __vmalloc_node(size, 1, flags, node, __builtin_return_address(0)); } EXPORT_SYMBOL(kvmalloc_node); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e9f730092c81..88f9971a7d6e 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2401,8 +2401,6 @@ void *vmap(struct page **pages, unsigned int count, } EXPORT_SYMBOL(vmap); -static void *__vmalloc_node(unsigned long size, unsigned long align, - gfp_t gfp_mask, int node, const void *caller); static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot, int node) { @@ -2553,7 +2551,7 @@ EXPORT_SYMBOL_GPL(__vmalloc_node_range); * * Return: pointer to the allocated memory or %NULL on error */ -static void *__vmalloc_node(unsigned long size, unsigned long align, +void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) { return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, @@ -2567,12 +2565,6 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask) } EXPORT_SYMBOL(__vmalloc); -void *__vmalloc_node_flags_caller(unsigned long size, int node, gfp_t flags, - void *caller) -{ - return __vmalloc_node(size, 1, flags, node, caller); -} - /** * vmalloc - allocate virtually contiguous memory * @size: allocation size -- cgit v1.2.3 From 041de93ff86fc500aa73e5360039c95f4d31b95f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:52:02 -0700 Subject: mm: remove vmalloc_user_node_flags Open code it in __bpf_map_area_alloc, which is the only caller. Also clean up __bpf_map_area_alloc to have a single vmalloc call with slightly different flags instead of the current two different calls. For this to compile for the nommu case add a __vmalloc_node_range stub to nommu.c. [akpm@linux-foundation.org: fix nommu.c build] Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Cc: Stephen Rothwell Link: http://lkml.kernel.org/r/20200414131348.444715-27-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 1 - kernel/bpf/syscall.c | 24 ++++++++++++++---------- mm/nommu.c | 14 ++++++++------ mm/vmalloc.c | 20 -------------------- 4 files changed, 22 insertions(+), 37 deletions(-) (limited to 'kernel') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 964d58a060ca..3332926295d4 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -106,7 +106,6 @@ extern void *vzalloc(unsigned long size); extern void *vmalloc_user(unsigned long size); extern void *vmalloc_node(unsigned long size, int node); extern void *vzalloc_node(unsigned long size, int node); -extern void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags); extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 9c1cf7a87fb3..42c7a42fc9c8 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ @@ -281,26 +282,29 @@ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) * __GFP_RETRY_MAYFAIL to avoid such situations. */ - const gfp_t flags = __GFP_NOWARN | __GFP_ZERO; + const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO; + unsigned int flags = 0; + unsigned long align = 1; void *area; if (size >= SIZE_MAX) return NULL; /* kmalloc()'ed memory can't be mmap()'ed */ - if (!mmapable && size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { - area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags, + if (mmapable) { + BUG_ON(!PAGE_ALIGNED(size)); + align = SHMLBA; + flags = VM_USERMAP; + } else if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { + area = kmalloc_node(size, gfp | GFP_USER | __GFP_NORETRY, numa_node); if (area != NULL) return area; } - if (mmapable) { - BUG_ON(!PAGE_ALIGNED(size)); - return vmalloc_user_node_flags(size, numa_node, GFP_KERNEL | - __GFP_RETRY_MAYFAIL | flags); - } - return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_RETRY_MAYFAIL | flags, - numa_node, __builtin_return_address(0)); + + return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, + gfp | GFP_KERNEL | __GFP_RETRY_MAYFAIL, PAGE_KERNEL, + flags, numa_node, __builtin_return_address(0)); } void *bpf_map_area_alloc(u64 size, int numa_node) diff --git a/mm/nommu.c b/mm/nommu.c index 08848fc18672..371697bf372d 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -150,6 +150,14 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask) } EXPORT_SYMBOL(__vmalloc); +void *__vmalloc_node_range(unsigned long size, unsigned long align, + unsigned long start, unsigned long end, gfp_t gfp_mask, + pgprot_t prot, unsigned long vm_flags, int node, + const void *caller) +{ + return __vmalloc(size, gfp_mask); +} + void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) { @@ -180,12 +188,6 @@ void *vmalloc_user(unsigned long size) } EXPORT_SYMBOL(vmalloc_user); -void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags) -{ - return __vmalloc_user_flags(size, flags | __GFP_ZERO); -} -EXPORT_SYMBOL(vmalloc_user_node_flags); - struct page *vmalloc_to_page(const void *addr) { return virt_to_page(addr); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 931106654d1f..410bfe26ee73 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2659,26 +2659,6 @@ void *vzalloc_node(unsigned long size, int node) } EXPORT_SYMBOL(vzalloc_node); -/** - * vmalloc_user_node_flags - allocate memory for userspace on a specific node - * @size: allocation size - * @node: numa node - * @flags: flags for the page level allocator - * - * The resulting memory area is zeroed so it can be mapped to userspace - * without leaking data. - * - * Return: pointer to the allocated memory or %NULL on error - */ -void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags) -{ - return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END, - flags | __GFP_ZERO, PAGE_KERNEL, - VM_USERMAP, node, - __builtin_return_address(0)); -} -EXPORT_SYMBOL(vmalloc_user_node_flags); - /** * vmalloc_exec - allocate virtually contiguous, executable memory * @size: allocation size -- cgit v1.2.3 From 73f693c3a705756032c2863bfb37570276902d7d Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 1 Jun 2020 21:52:36 -0700 Subject: mm: remove vmalloc_sync_(un)mappings() These functions are not needed anymore because the vmalloc and ioremap mappings are now synchronized when they are created or torn down. Remove all callers and function definitions. Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Tested-by: Steven Rostedt (VMware) Acked-by: Andy Lutomirski Acked-by: Peter Zijlstra (Intel) Cc: Arnd Bergmann Cc: Christoph Hellwig Cc: Dave Hansen Cc: "H . Peter Anvin" Cc: Ingo Molnar Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: "Rafael J. Wysocki" Cc: Thomas Gleixner Cc: Vlastimil Babka Link: http://lkml.kernel.org/r/20200515140023.25469-7-joro@8bytes.org Signed-off-by: Linus Torvalds --- arch/x86/mm/fault.c | 37 ------------------------------------- drivers/acpi/apei/ghes.c | 6 ------ include/linux/vmalloc.h | 2 -- kernel/notifier.c | 1 - kernel/trace/trace.c | 12 ------------ mm/nommu.c | 12 ------------ mm/vmalloc.c | 21 --------------------- 7 files changed, 91 deletions(-) (limited to 'kernel') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index edeb2adaf31f..255fc631b042 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -214,26 +214,6 @@ void arch_sync_kernel_mappings(unsigned long start, unsigned long end) } } -static void vmalloc_sync(void) -{ - unsigned long address; - - if (SHARED_KERNEL_PMD) - return; - - arch_sync_kernel_mappings(VMALLOC_START, VMALLOC_END); -} - -void vmalloc_sync_mappings(void) -{ - vmalloc_sync(); -} - -void vmalloc_sync_unmappings(void) -{ - vmalloc_sync(); -} - /* * 32-bit: * @@ -336,23 +316,6 @@ out: #else /* CONFIG_X86_64: */ -void vmalloc_sync_mappings(void) -{ - /* - * 64-bit mappings might allocate new p4d/pud pages - * that need to be propagated to all tasks' PGDs. - */ - sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END); -} - -void vmalloc_sync_unmappings(void) -{ - /* - * Unmappings never allocate or free p4d/pud pages. - * No work is required here. - */ -} - /* * 64-bit: * diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 24c9642e8fc7..aabe9c5ee515 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -167,12 +167,6 @@ int ghes_estatus_pool_init(int num_ghes) if (!addr) goto err_pool_alloc; - /* - * New allocation must be visible in all pgd before it can be found by - * an NMI allocating from the pool. - */ - vmalloc_sync_mappings(); - rc = gen_pool_add(ghes_estatus_pool, addr, PAGE_ALIGN(len), -1); if (rc) goto err_pool_add; diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 0efc35dc5b25..48bb681e6c2a 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -130,8 +130,6 @@ extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); -void vmalloc_sync_mappings(void); -void vmalloc_sync_unmappings(void); /* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values diff --git a/kernel/notifier.c b/kernel/notifier.c index 5989bbb93039..84c987dfbe03 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -519,7 +519,6 @@ NOKPROBE_SYMBOL(notify_die); int register_die_notifier(struct notifier_block *nb) { - vmalloc_sync_mappings(); return atomic_notifier_chain_register(&die_chain, nb); } EXPORT_SYMBOL_GPL(register_die_notifier); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 29615f15a820..f12e99b387b2 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8527,18 +8527,6 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) allocate_snapshot = false; #endif - /* - * Because of some magic with the way alloc_percpu() works on - * x86_64, we need to synchronize the pgd of all the tables, - * otherwise the trace events that happen in x86_64 page fault - * handlers can't cope with accessing the chance that a - * alloc_percpu()'d memory might be touched in the page fault trace - * event. Oh, and we need to audit all other alloc_percpu() and vmalloc() - * calls in tracing, because something might get triggered within a - * page fault trace event! - */ - vmalloc_sync_mappings(); - return 0; } diff --git a/mm/nommu.c b/mm/nommu.c index 371697bf372d..dfae55f41901 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -371,18 +371,6 @@ void vm_unmap_aliases(void) } EXPORT_SYMBOL_GPL(vm_unmap_aliases); -/* - * Implement a stub for vmalloc_sync_[un]mapping() if the architecture - * chose not to have one. - */ -void __weak vmalloc_sync_mappings(void) -{ -} - -void __weak vmalloc_sync_unmappings(void) -{ -} - struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes) { BUG(); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 154e3396154c..1e94497b7388 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1353,12 +1353,6 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) if (unlikely(valist == NULL)) return false; - /* - * First make sure the mappings are removed from all page-tables - * before they are freed. - */ - vmalloc_sync_unmappings(); - /* * TODO: to calculate a flush range without looping. * The list can be up to lazy_max_pages() elements. @@ -3089,21 +3083,6 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, } EXPORT_SYMBOL(remap_vmalloc_range); -/* - * Implement stubs for vmalloc_sync_[un]mappings () if the architecture chose - * not to have one. - * - * The purpose of this function is to make sure the vmalloc area - * mappings are identical in all page-tables in the system. - */ -void __weak vmalloc_sync_mappings(void) -{ -} - -void __weak vmalloc_sync_unmappings(void) -{ -} - static int f(pte_t *pte, unsigned long addr, void *data) { pte_t ***p = data; -- cgit v1.2.3