lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20190809225833.6657-18-ira.weiny@intel.com>
Date:   Fri,  9 Aug 2019 15:58:31 -0700
From:   ira.weiny@...el.com
To:     Andrew Morton <akpm@...ux-foundation.org>
Cc:     Jason Gunthorpe <jgg@...pe.ca>,
        Dan Williams <dan.j.williams@...el.com>,
        Matthew Wilcox <willy@...radead.org>, Jan Kara <jack@...e.cz>,
        "Theodore Ts'o" <tytso@....edu>,
        John Hubbard <jhubbard@...dia.com>,
        Michal Hocko <mhocko@...e.com>,
        Dave Chinner <david@...morbit.com>, linux-xfs@...r.kernel.org,
        linux-rdma@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-fsdevel@...r.kernel.org, linux-nvdimm@...ts.01.org,
        linux-ext4@...r.kernel.org, linux-mm@...ck.org,
        Ira Weiny <ira.weiny@...el.com>
Subject: [RFC PATCH v2 17/19] RDMA/umem: Convert to vaddr_[pin|unpin]* operations.

From: Ira Weiny <ira.weiny@...el.com>

In order to properly track the pinning information we need to keep a
vaddr_pin object around.  Store that within the umem object directly.

The vaddr_pin object allows the GUP code to associate any files it pins
with the RDMA file descriptor associated with this GUP.

Furthermore, use the vaddr_pin object to store the owning mm while we
are at it.

No references need to be taken on the owing file as the lifetime of that
object is tied to all the umems being destroyed first.

Signed-off-by: Ira Weiny <ira.weiny@...el.com>
---
 drivers/infiniband/core/umem.c     | 26 +++++++++++++++++---------
 drivers/infiniband/core/umem_odp.c | 16 ++++++++--------
 include/rdma/ib_umem.h             |  2 +-
 3 files changed, 26 insertions(+), 18 deletions(-)

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 965cf9dea71a..a9ce3e3816ef 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -54,7 +54,8 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
 
 	for_each_sg_page(umem->sg_head.sgl, &sg_iter, umem->sg_nents, 0) {
 		page = sg_page_iter_page(&sg_iter);
-		put_user_pages_dirty_lock(&page, 1, umem->writable && dirty);
+		vaddr_unpin_pages_dirty_lock(&page, 1, &umem->vaddr_pin,
+					     umem->writable && dirty);
 	}
 
 	sg_free_table(&umem->sg_head);
@@ -243,8 +244,15 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
 	umem->length     = size;
 	umem->address    = addr;
 	umem->writable   = ib_access_writable(access);
-	umem->owning_mm = mm = current->mm;
-	mmgrab(mm);
+	umem->vaddr_pin.mm = mm = current->mm;
+	mmgrab(umem->vaddr_pin.mm);
+
+	/* No need to get a reference to the core file object here.  The key is
+	 * that sys_file reference is held by the ufile.  Any duplication of
+	 * sys_file by the core will keep references active until all those
+	 * contexts are closed out.  No matter which process hold them open.
+	 */
+	umem->vaddr_pin.f_owner = context->ufile->sys_file;
 
 	if (access & IB_ACCESS_ON_DEMAND) {
 		if (WARN_ON_ONCE(!context->invalidate_range)) {
@@ -292,11 +300,11 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
 
 	while (npages) {
 		down_read(&mm->mmap_sem);
-		ret = get_user_pages(cur_base,
+		ret = vaddr_pin_pages(cur_base,
 				     min_t(unsigned long, npages,
 					   PAGE_SIZE / sizeof (struct page *)),
-				     gup_flags | FOLL_LONGTERM,
-				     page_list, NULL);
+				     gup_flags,
+				     page_list, &umem->vaddr_pin);
 		if (ret < 0) {
 			up_read(&mm->mmap_sem);
 			goto umem_release;
@@ -336,7 +344,7 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
 	free_page((unsigned long) page_list);
 umem_kfree:
 	if (ret) {
-		mmdrop(umem->owning_mm);
+		mmdrop(umem->vaddr_pin.mm);
 		kfree(umem);
 	}
 	return ret ? ERR_PTR(ret) : umem;
@@ -345,7 +353,7 @@ EXPORT_SYMBOL(ib_umem_get);
 
 static void __ib_umem_release_tail(struct ib_umem *umem)
 {
-	mmdrop(umem->owning_mm);
+	mmdrop(umem->vaddr_pin.mm);
 	if (umem->is_odp)
 		kfree(to_ib_umem_odp(umem));
 	else
@@ -369,7 +377,7 @@ void ib_umem_release(struct ib_umem *umem)
 
 	__ib_umem_release(umem->context->device, umem, 1);
 
-	atomic64_sub(ib_umem_num_pages(umem), &umem->owning_mm->pinned_vm);
+	atomic64_sub(ib_umem_num_pages(umem), &umem->vaddr_pin.mm->pinned_vm);
 	__ib_umem_release_tail(umem);
 }
 EXPORT_SYMBOL(ib_umem_release);
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 2a75c6f8d827..53085896d718 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -278,11 +278,11 @@ static int get_per_mm(struct ib_umem_odp *umem_odp)
 	 */
 	mutex_lock(&ctx->per_mm_list_lock);
 	list_for_each_entry(per_mm, &ctx->per_mm_list, ucontext_list) {
-		if (per_mm->mm == umem_odp->umem.owning_mm)
+		if (per_mm->mm == umem_odp->umem.vaddr_pin.mm)
 			goto found;
 	}
 
-	per_mm = alloc_per_mm(ctx, umem_odp->umem.owning_mm);
+	per_mm = alloc_per_mm(ctx, umem_odp->umem.vaddr_pin.mm);
 	if (IS_ERR(per_mm)) {
 		mutex_unlock(&ctx->per_mm_list_lock);
 		return PTR_ERR(per_mm);
@@ -355,8 +355,8 @@ struct ib_umem_odp *ib_alloc_odp_umem(struct ib_umem_odp *root,
 	umem->writable   = root->umem.writable;
 	umem->is_odp = 1;
 	odp_data->per_mm = per_mm;
-	umem->owning_mm  = per_mm->mm;
-	mmgrab(umem->owning_mm);
+	umem->vaddr_pin.mm  = per_mm->mm;
+	mmgrab(umem->vaddr_pin.mm);
 
 	mutex_init(&odp_data->umem_mutex);
 	init_completion(&odp_data->notifier_completion);
@@ -389,7 +389,7 @@ struct ib_umem_odp *ib_alloc_odp_umem(struct ib_umem_odp *root,
 out_page_list:
 	vfree(odp_data->page_list);
 out_odp_data:
-	mmdrop(umem->owning_mm);
+	mmdrop(umem->vaddr_pin.mm);
 	kfree(odp_data);
 	return ERR_PTR(ret);
 }
@@ -399,10 +399,10 @@ int ib_umem_odp_get(struct ib_umem_odp *umem_odp, int access)
 {
 	struct ib_umem *umem = &umem_odp->umem;
 	/*
-	 * NOTE: This must called in a process context where umem->owning_mm
+	 * NOTE: This must called in a process context where umem->vaddr_pin.mm
 	 * == current->mm
 	 */
-	struct mm_struct *mm = umem->owning_mm;
+	struct mm_struct *mm = umem->vaddr_pin.mm;
 	int ret_val;
 
 	umem_odp->page_shift = PAGE_SHIFT;
@@ -581,7 +581,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 			      unsigned long current_seq)
 {
 	struct task_struct *owning_process  = NULL;
-	struct mm_struct *owning_mm = umem_odp->umem.owning_mm;
+	struct mm_struct *owning_mm = umem_odp->umem.vaddr_pin.mm;
 	struct page       **local_page_list = NULL;
 	u64 page_mask, off;
 	int j, k, ret = 0, start_idx, npages = 0;
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 1052d0d62be7..ab677c799e29 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -43,7 +43,6 @@ struct ib_umem_odp;
 
 struct ib_umem {
 	struct ib_ucontext     *context;
-	struct mm_struct       *owning_mm;
 	size_t			length;
 	unsigned long		address;
 	u32 writable : 1;
@@ -52,6 +51,7 @@ struct ib_umem {
 	struct sg_table sg_head;
 	int             nmap;
 	unsigned int    sg_nents;
+	struct vaddr_pin vaddr_pin;
 };
 
 /* Returns the offset of the umem start relative to the first page. */
-- 
2.20.1

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ