Re: [PATCH kernel 05/15] powerpc/iommu: Stop using @current in mm_iommu_xxx

On Fri, Aug 12, 2016 at 02:56:59PM +1000, Alexey Kardashevskiy wrote:

On 12/08/16 12:57, David Gibson wrote:

quoted

On Wed, Aug 03, 2016 at 06:40:46PM +1000, Alexey Kardashevskiy wrote:

quoted

In some situations the userspace memory context may live longer than
the userspace process itself so if we need to do proper memory context
cleanup, we better cache @mm and use it later when the process is gone
(@current or @current->mm are NULL).

This changes mm_iommu_xxx API to receive mm_struct instead of using one
from @current.

This is needed by the following patch to do proper cleanup in time.
This depends on "powerpc/powernv/ioda: Fix endianness when reading TCEs"
to do proper cleanup via tce_iommu_clear() patch.

To keep API consistent, this replaces mm_context_t with mm_struct;
we stick to mm_struct as mm_iommu_adjust_locked_vm() helper needs
access to &mm->mmap_sem.

This should cause no behavioral change.

Signed-off-by: Alexey Kardashevskiy <redacted>
---
 arch/powerpc/include/asm/mmu_context.h | 20 +++++++------
 arch/powerpc/kernel/setup-common.c     |  2 +-
 arch/powerpc/mm/mmu_context_book3s64.c |  4 +--
 arch/powerpc/mm/mmu_context_iommu.c    | 54 ++++++++++++++--------------------
 drivers/vfio/vfio_iommu_spapr_tce.c    | 41 ++++++++++++++++----------
 5 files changed, 62 insertions(+), 59 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 9d2cd0c..b85cc7b 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h

@@ -18,16 +18,18 @@ extern void destroy_context(struct mm_struct *mm);
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 struct mm_iommu_table_group_mem_t;
 
-extern bool mm_iommu_preregistered(void);
-extern long mm_iommu_get(unsigned long ua, unsigned long entries,
+extern bool mm_iommu_preregistered(struct mm_struct *mm);
+extern long mm_iommu_get(struct mm_struct *mm,
+		unsigned long ua, unsigned long entries,
 		struct mm_iommu_table_group_mem_t **pmem);
-extern long mm_iommu_put(struct mm_iommu_table_group_mem_t *mem);
-extern void mm_iommu_init(mm_context_t *ctx);
-extern void mm_iommu_cleanup(mm_context_t *ctx);
-extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(unsigned long ua,
-		unsigned long size);
-extern struct mm_iommu_table_group_mem_t *mm_iommu_find(unsigned long ua,
-		unsigned long entries);
+extern long mm_iommu_put(struct mm_struct *mm,
+		struct mm_iommu_table_group_mem_t *mem);
+extern void mm_iommu_init(struct mm_struct *mm);
+extern void mm_iommu_cleanup(struct mm_struct *mm);
+extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
+		unsigned long ua, unsigned long size);
+extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
+		unsigned long ua, unsigned long entries);
 extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 		unsigned long ua, unsigned long *hpa);
 extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);

diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 714b4ba..e90b68a 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c

@@ -905,7 +905,7 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.context.pte_frag = NULL;
 #endif
 #ifdef CONFIG_SPAPR_TCE_IOMMU
-	mm_iommu_init(&init_mm.context);
+	mm_iommu_init(&init_mm);
 #endif
 	irqstack_early_init();
 	exc_lvl_early_init();

diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index b114f8b..ad82735 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c

@@ -115,7 +115,7 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	mm->context.pte_frag = NULL;
 #endif
 #ifdef CONFIG_SPAPR_TCE_IOMMU
-	mm_iommu_init(&mm->context);
+	mm_iommu_init(mm);
 #endif
 	return 0;
 }

@@ -160,7 +160,7 @@ static inline void destroy_pagetable_page(struct mm_struct *mm)
 void destroy_context(struct mm_struct *mm)
 {
 #ifdef CONFIG_SPAPR_TCE_IOMMU
-	mm_iommu_cleanup(&mm->context);
+	mm_iommu_cleanup(mm);
 #endif
 
 #ifdef CONFIG_PPC_ICSWX

diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index da6a216..ee6685b 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c

@@ -53,7 +53,7 @@ static long mm_iommu_adjust_locked_vm(struct mm_struct *mm,
 	}
 
 	pr_debug("[%d] RLIMIT_MEMLOCK HASH64 %c%ld %ld/%ld\n",
-			current->pid,
+			current ? current->pid : 0,
 			incr ? '+' : '-',
 			npages << PAGE_SHIFT,
 			mm->locked_vm << PAGE_SHIFT,

@@ -63,28 +63,22 @@ static long mm_iommu_adjust_locked_vm(struct mm_struct *mm,
 	return ret;
 }
 
-bool mm_iommu_preregistered(void)
+bool mm_iommu_preregistered(struct mm_struct *mm)
 {
-	if (!current || !current->mm)
-		return false;
-
-	return !list_empty(&current->mm->context.iommu_group_mem_list);
+	return !list_empty(&mm->context.iommu_group_mem_list);
 }
 EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
 
-long mm_iommu_get(unsigned long ua, unsigned long entries,
+long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 		struct mm_iommu_table_group_mem_t **pmem)
 {
 	struct mm_iommu_table_group_mem_t *mem;
 	long i, j, ret = 0, locked_entries = 0;
 	struct page *page = NULL;
 
-	if (!current || !current->mm)
-		return -ESRCH; /* process exited */
-
 	mutex_lock(&mem_list_mutex);
 
-	list_for_each_entry_rcu(mem, &current->mm->context.iommu_group_mem_list,
+	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list,
 			next) {
 		if ((mem->ua == ua) && (mem->entries == entries)) {
 			++mem->used;

@@ -102,7 +96,7 @@ long mm_iommu_get(unsigned long ua, unsigned long entries,
 
 	}
 
-	ret = mm_iommu_adjust_locked_vm(current->mm, entries, true);
+	ret = mm_iommu_adjust_locked_vm(mm, entries, true);
 	if (ret)
 		goto unlock_exit;
 

@@ -142,11 +136,11 @@ long mm_iommu_get(unsigned long ua, unsigned long entries,
 	mem->entries = entries;
 	*pmem = mem;
 
-	list_add_rcu(&mem->next, &current->mm->context.iommu_group_mem_list);
+	list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
 
 unlock_exit:
 	if (locked_entries && ret)
-		mm_iommu_adjust_locked_vm(current->mm, locked_entries, false);
+		mm_iommu_adjust_locked_vm(mm, locked_entries, false);
 
 	mutex_unlock(&mem_list_mutex);
 

@@ -191,16 +185,13 @@ static void mm_iommu_free(struct rcu_head *head)
 static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem)
 {
 	list_del_rcu(&mem->next);
-	mm_iommu_adjust_locked_vm(current->mm, mem->entries, false);

AFAICT, you've moved this call from _release() to _put().  Won't that cause a
behavioural change?

mm_iommu_put() calls mm_iommu_adjust_locked_vm() right after
m_iommu_release() so no, it does not look so.

Ah, I guess not.  It seems a bit arbitrary in the context of the rest
of the changes, though.

quoted

quoted

 	call_rcu(&mem->rcu, mm_iommu_free);
 }
 
-long mm_iommu_put(struct mm_iommu_table_group_mem_t *mem)
+long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
 {
 	long ret = 0;
 
-	if (!current || !current->mm)
-		return -ESRCH; /* process exited */
 
 	mutex_lock(&mem_list_mutex);
 

@@ -224,6 +215,8 @@ long mm_iommu_put(struct mm_iommu_table_group_mem_t *mem)
 	/* @mapped became 0 so now mappings are disabled, release the region */
 	mm_iommu_release(mem);
 
+	mm_iommu_adjust_locked_vm(mm, mem->entries, false);
+
 unlock_exit:
 	mutex_unlock(&mem_list_mutex);
 

@@ -231,14 +224,12 @@ unlock_exit:
 }
 EXPORT_SYMBOL_GPL(mm_iommu_put);
 
-struct mm_iommu_table_group_mem_t *mm_iommu_lookup(unsigned long ua,
-		unsigned long size)
+struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
+		unsigned long ua, unsigned long size)
 {
 	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
 
-	list_for_each_entry_rcu(mem,
-			&current->mm->context.iommu_group_mem_list,
-			next) {
+	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) {
 		if ((mem->ua <= ua) &&
 				(ua + size <= mem->ua +
 				 (mem->entries << PAGE_SHIFT))) {

@@ -251,14 +242,12 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup(unsigned long ua,
 }
 EXPORT_SYMBOL_GPL(mm_iommu_lookup);
 
-struct mm_iommu_table_group_mem_t *mm_iommu_find(unsigned long ua,
-		unsigned long entries)
+struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
+		unsigned long ua, unsigned long entries)
 {
 	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
 
-	list_for_each_entry_rcu(mem,
-			&current->mm->context.iommu_group_mem_list,
-			next) {
+	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) {
 		if ((mem->ua == ua) && (mem->entries == entries)) {
 			ret = mem;
 			break;

@@ -300,16 +289,17 @@ void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem)
 }
 EXPORT_SYMBOL_GPL(mm_iommu_mapped_dec);
 
-void mm_iommu_init(mm_context_t *ctx)
+void mm_iommu_init(struct mm_struct *mm)
 {
-	INIT_LIST_HEAD_RCU(&ctx->iommu_group_mem_list);
+	INIT_LIST_HEAD_RCU(&mm->context.iommu_group_mem_list);
 }
 
-void mm_iommu_cleanup(mm_context_t *ctx)
+void mm_iommu_cleanup(struct mm_struct *mm)
 {
 	struct mm_iommu_table_group_mem_t *mem, *tmp;
 
-	list_for_each_entry_safe(mem, tmp, &ctx->iommu_group_mem_list, next) {
+	list_for_each_entry_safe(mem, tmp, &mm->context.iommu_group_mem_list,
+			next) {
 		list_del_rcu(&mem->next);
 		mm_iommu_do_free(mem);
 	}

diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 80378dd..9752e77 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c

@@ -98,6 +98,7 @@ struct tce_container {
 	bool enabled;
 	bool v2;
 	unsigned long locked_pages;
+	struct mm_struct *mm;
 	struct iommu_table *tables[IOMMU_TABLE_GROUP_MAX_TABLES];
 	struct list_head group_list;
 };

@@ -110,11 +111,11 @@ static long tce_iommu_unregister_pages(struct tce_container *container,
 	if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK))
 		return -EINVAL;
 
-	mem = mm_iommu_find(vaddr, size >> PAGE_SHIFT);
+	mem = mm_iommu_find(container->mm, vaddr, size >> PAGE_SHIFT);
 	if (!mem)
 		return -ENOENT;
 
-	return mm_iommu_put(mem);
+	return mm_iommu_put(container->mm, mem);
 }
 
 static long tce_iommu_register_pages(struct tce_container *container,

@@ -128,10 +129,17 @@ static long tce_iommu_register_pages(struct tce_container *container,
 			((vaddr + size) < vaddr))
 		return -EINVAL;
 
-	r<et = mm_iommu_get(vaddr, entries, &mem);
+	if (!container->mm) {
+		if (!current->mm)
+			return -ESRCH; /* process exited */

Can this ever happen?  Surely the ioctl() path shouldn't be called
after the process mm has been cleaned up?  i.e. should this be a
WARN_ON().

Not sure with SMP (one thread doing ioctl(), another - exiting QEMU) if it
is not that impossible but it is quite hard to trigger this check.

I'm pretty sure the mm can't be cleaned up until all threads have
definitely stopped executing.

quoted

quoted

+
+		atomic_inc(&current->mm->mm_count);

What balances this atomic_inc()?  Is it the mmdrop() added to
tce_iommu_release()?

Yes. Surprisingly there is no mmget(), there is mmget_not_zero() but it is
for mm->mm_users.

Ok.

quoted

quoted

+		container->mm = current->mm;
+	}

Surely you need an error (or else a BUG_ON()) if current->mm !=
container->mm != NULL.  I believe VFIO already assumes the container
is owned only by a single mm, but it looks like you should verify that here.

I am not sure I really want to enforce it, do I? Who knows what kind of a
crazy person would create a container, pin pages and fork() that userspace
tool which may not be QEMU but something custom using DPDK or something.

What harm can not having this BUG_ON() cause?

Hrm.  Well, if nothing else it lets one process lock (or unlock) pages
in an essentially unrelated process, which is pretty weird.  I don't
see any obvious way it will cause more serious problems.  But, as a
general rule it makes debugging easier if you check / enforce required
assumptions at the earliest possible point.

quoted

quoted

+
+	ret = mm_iommu_get(container->mm, vaddr, entries, &mem);
 	if (ret)
 		return ret;
-
 	container->enabled = true;
 
 	return 0;

@@ -354,6 +362,8 @@ static void tce_iommu_release(void *iommu_data)
 		tce_iommu_free_table(tbl);
 	}
 
+	if (container->mm)
+		mmdrop(container->mm);
 	tce_iommu_disable(container);
 	mutex_destroy(&container->lock);
 

@@ -369,13 +379,14 @@ static void tce_iommu_unuse_page(struct tce_container *container,
 	put_page(page);
 }
 
-static int tce_iommu_prereg_ua_to_hpa(unsigned long tce, unsigned long size,
+static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container,
+		unsigned long tce, unsigned long size,
 		unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem)
 {
 	long ret = 0;
 	struct mm_iommu_table_group_mem_t *mem;
 
-	mem = mm_iommu_lookup(tce, size);
+	mem = mm_iommu_lookup(container->mm, tce, size);
 	if (!mem)
 		return -EINVAL;
 

@@ -388,18 +399,18 @@ static int tce_iommu_prereg_ua_to_hpa(unsigned long tce, unsigned long size,
 	return 0;
 }
 
-static void tce_iommu_unuse_page_v2(struct iommu_table *tbl,
-		unsigned long entry)
+static void tce_iommu_unuse_page_v2(struct tce_container *container,
+		struct iommu_table *tbl, unsigned long entry)
 {
 	struct mm_iommu_table_group_mem_t *mem = NULL;
 	int ret;
 	unsigned long hpa = 0;
 	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
 
-	if (!pua || !current || !current->mm)
+	if (!pua)
 		return;
 
-	ret = tce_iommu_prereg_ua_to_hpa(*pua, IOMMU_PAGE_SIZE(tbl),
+	ret = tce_iommu_prereg_ua_to_hpa(container, *pua, IOMMU_PAGE_SIZE(tbl),
 			&hpa, &mem);
 	if (ret)
 		pr_debug("%s: tce %lx at #%lx was not cached, ret=%d\n",

@@ -429,7 +440,7 @@ static int tce_iommu_clear(struct tce_container *container,
 			continue;
 
 		if (container->v2) {
-			tce_iommu_unuse_page_v2(tbl, entry);
+			tce_iommu_unuse_page_v2(container, tbl, entry);
 			continue;
 		}
 

@@ -514,8 +525,8 @@ static long tce_iommu_build_v2(struct tce_container *container,
 		unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl,
 				entry + i);
 
-		ret = tce_iommu_prereg_ua_to_hpa(tce, IOMMU_PAGE_SIZE(tbl),
-				&hpa, &mem);
+		ret = tce_iommu_prereg_ua_to_hpa(container,
+				tce, IOMMU_PAGE_SIZE(tbl), &hpa, &mem);
 		if (ret)
 			break;
 

@@ -536,7 +547,7 @@ static long tce_iommu_build_v2(struct tce_container *container,
 		ret = iommu_tce_xchg(tbl, entry + i, &hpa, &dirtmp);
 		if (ret) {
 			/* dirtmp cannot be DMA_NONE here */
-			tce_iommu_unuse_page_v2(tbl, entry + i);
+			tce_iommu_unuse_page_v2(container, tbl, entry + i);
 			pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%ld\n",
 					__func__, entry << tbl->it_page_shift,
 					tce, ret);

@@ -544,7 +555,7 @@ static long tce_iommu_build_v2(struct tce_container *container,
 		}
 
 		if (dirtmp != DMA_NONE)
-			tce_iommu_unuse_page_v2(tbl, entry + i);
+			tce_iommu_unuse_page_v2(container, tbl, entry + i);
 
 		*pua = tce;
 

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson