ib_umem_get() allocates an array of pointers to struct page for pin_user_pages_fast() calls during memory registration. This array can be allocated with kmalloc() as there's nothing special about it to go directly to the page allocator. kmalloc() provides a better API that does not require ugly casts and kfree() does not need to know the size of the freed object. Performance difference between kmalloc() and __get_free_pages() is not measurable as both allocators take an object/page from a per-CPU list for fast path allocations. For the slow path the performance is anyway determined by the amount of reclaim involved rather than by what allocator is used. Replace use of __get_free_page() with kmalloc() and free_page() with kfree(). Link: https://lore.kernel.org/all/635405e4-9423-4a25-a6e7-e03c8ea0bcbe@redhat.com Signed-off-by: Mike Rapoport (Microsoft) --- drivers/infiniband/core/umem.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 73498723a5d5..81f44dadfa52 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -209,7 +209,8 @@ static struct ib_umem *__ib_umem_get_va(struct ib_device *device, mmgrab(mm); - page_list = (struct page **) __get_free_page(GFP_KERNEL); + /* TODO: switch to "fast and as large as possible" allocation helper */ + page_list = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!page_list) { ret = -ENOMEM; goto umem_kfree; @@ -269,7 +270,7 @@ static struct ib_umem *__ib_umem_get_va(struct ib_device *device, __ib_umem_release(device, umem, 0); atomic64_sub(ib_umem_num_pages(umem), &mm->pinned_vm); out: - free_page((unsigned long) page_list); + kfree(page_list); umem_kfree: if (ret) { mmdrop(umem->owning_mm); -- 2.53.0 mlx5_ib_mr_wqe_pfault_handler() allocates a scratch buffer for parsing work queue entries during page fault handling. This buffer can be allocated with kmalloc() as there's nothing special about it to go directly to the page allocator. kmalloc() provides a better API that does not require ugly casts and kfree() does not need to know the size of the freed object. Performance difference between kmalloc() and __get_free_pages() is not measurable as both allocators take an object/page from a per-CPU list for fast path allocations. For the slow path the performance is anyway determined by the amount of reclaim involved rather than by what allocator is used. Replace use of __get_free_page() with kmalloc() and free_page() with kfree(). Link: https://lore.kernel.org/all/635405e4-9423-4a25-a6e7-e03c8ea0bcbe@redhat.com Signed-off-by: Mike Rapoport (Microsoft) --- drivers/infiniband/hw/mlx5/odp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 1badec9bf527..b8618610737a 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -37,6 +37,7 @@ #include #include #include +#include #include "mlx5_ib.h" #include "cmd.h" @@ -1414,7 +1415,8 @@ static void mlx5_ib_mr_wqe_pfault_handler(struct mlx5_ib_dev *dev, goto resolve_page_fault; } - wqe_start = (void *)__get_free_page(GFP_KERNEL); + /* TODO: switch to "fast and as large as possible" allocation helper */ + wqe_start = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!wqe_start) { mlx5_ib_err(dev, "Error allocating memory for IO page fault handling.\n"); goto resolve_page_fault; @@ -1475,7 +1477,7 @@ static void mlx5_ib_mr_wqe_pfault_handler(struct mlx5_ib_dev *dev, pfault->wqe.wq_num, resume_with_error, pfault->type); mlx5_core_res_put(res); - free_page((unsigned long)wqe_start); + kfree(wqe_start); } static void mlx5_ib_mr_rdma_pfault_handler(struct mlx5_ib_dev *dev, -- 2.53.0 mthca_reg_user_mr() allocates an array of DMA addresses during memory registration. This buffer can be allocated with kmalloc() as there's nothing special about it to go directly to the page allocator. kmalloc() provides a better API that does not require ugly casts and kfree() does not need to know the size of the freed object. Performance difference between kmalloc() and __get_free_pages() is not measurable as both allocators take an object/page from a per-CPU list for fast path allocations. For the slow path the performance is anyway determined by the amount of reclaim involved rather than by what allocator is used. Replace use of __get_free_page() with kmalloc() and free_page() with kfree(). Link: https://lore.kernel.org/all/635405e4-9423-4a25-a6e7-e03c8ea0bcbe@redhat.com Signed-off-by: Mike Rapoport (Microsoft) --- drivers/infiniband/hw/mthca/mthca_provider.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c index f90f67afc8fa..9940165781e1 100644 --- a/drivers/infiniband/hw/mthca/mthca_provider.c +++ b/drivers/infiniband/hw/mthca/mthca_provider.c @@ -895,7 +895,8 @@ static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, goto err_umem; } - pages = (u64 *) __get_free_page(GFP_KERNEL); + /* TODO: switch to "fast and as large as possible" allocation helper */ + pages = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!pages) { err = -ENOMEM; goto err_mtt; @@ -924,7 +925,7 @@ static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, if (i) err = mthca_write_mtt(dev, mr->mtt, n, pages, i); mtt_done: - free_page((unsigned long) pages); + kfree(pages); if (err) goto err_mtt; -- 2.53.0 mthca_array is essentially a sparse array of pointers and there is no need to allocate its memory using page allocator. kmalloc() provides a better API that does not require ugly casts and kfree() does not need to know the size of the freed object. Performance difference between kmalloc() and __get_free_pages() is not measurable as both allocators take an object/page from a per-CPU list for fast path allocations. For the slow path the performance is anyway determined by the amount of reclaim involved rather than by what allocator is used. Replace use of get_zeroed_page() with kzalloc() and free_page() with kfree(). Link: https://lore.kernel.org/all/635405e4-9423-4a25-a6e7-e03c8ea0bcbe@redhat.com Signed-off-by: Mike Rapoport (Microsoft) --- drivers/infiniband/hw/mthca/mthca_allocator.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/mthca/mthca_allocator.c b/drivers/infiniband/hw/mthca/mthca_allocator.c index dedc301235a0..117a070e784e 100644 --- a/drivers/infiniband/hw/mthca/mthca_allocator.c +++ b/drivers/infiniband/hw/mthca/mthca_allocator.c @@ -126,7 +126,7 @@ int mthca_array_set(struct mthca_array *array, int index, void *value) /* Allocate with GFP_ATOMIC because we'll be called with locks held. */ if (!array->page_list[p].page) - array->page_list[p].page = (void **) get_zeroed_page(GFP_ATOMIC); + array->page_list[p].page = kzalloc(PAGE_SIZE, GFP_ATOMIC); if (!array->page_list[p].page) return -ENOMEM; @@ -142,7 +142,7 @@ void mthca_array_clear(struct mthca_array *array, int index) int p = (index * sizeof (void *)) >> PAGE_SHIFT; if (--array->page_list[p].used == 0) { - free_page((unsigned long) array->page_list[p].page); + kfree(array->page_list[p].page); array->page_list[p].page = NULL; } else array->page_list[p].page[index & MTHCA_ARRAY_MASK] = NULL; @@ -174,7 +174,7 @@ void mthca_array_cleanup(struct mthca_array *array, int nent) int i; for (i = 0; i < (nent * sizeof (void *) + PAGE_SIZE - 1) / PAGE_SIZE; ++i) - free_page((unsigned long) array->page_list[i].page); + kfree(array->page_list[i].page); kfree(array->page_list); } -- 2.53.0 get_map_page() allocates bitmap pages using get_zeroed_page(). The bitmaps can be allocated with kmalloc() as there's nothing special about them to go directly to the page allocator. kmalloc() provides a better API that does not require ugly casts and kfree() does not need to know the size of the freed object. Performance difference between kmalloc() and __get_free_pages() is not measurable as both allocators take an object/page from a per-CPU list for fast path allocations. For the slow path the performance is anyway determined by the amount of reclaim involved rather than by what allocator is used. Replace use of get_zeroed_page() with kzalloc() and free_page() with kfree(). Link: https://lore.kernel.org/all/635405e4-9423-4a25-a6e7-e03c8ea0bcbe@redhat.com Signed-off-by: Mike Rapoport (Microsoft) --- drivers/infiniband/sw/rdmavt/qp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 70e7d08fdce6..c40cce69e945 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -263,7 +263,7 @@ static inline bool wss_exceeds_threshold(struct rvt_wss *wss) static void get_map_page(struct rvt_qpn_table *qpt, struct rvt_qpn_map *map) { - unsigned long page = get_zeroed_page(GFP_KERNEL); + void *page = kzalloc(PAGE_SIZE, GFP_KERNEL); /* * Free the page if someone raced with us installing it. @@ -271,9 +271,9 @@ static void get_map_page(struct rvt_qpn_table *qpt, spin_lock(&qpt->lock); if (map->page) - free_page(page); + kfree(page); else - map->page = (void *)page; + map->page = page; spin_unlock(&qpt->lock); } @@ -343,7 +343,7 @@ static void free_qpn_table(struct rvt_qpn_table *qpt) int i; for (i = 0; i < ARRAY_SIZE(qpt->map); i++) - free_page((unsigned long)qpt->map[i].page); + kfree(qpt->map[i].page); } /** -- 2.53.0