[PATCH kernel v3 0/4] powerpc/spapr/vfio: Put pages on VFIO container shutdown

[PATCH kernel v3 0/4] powerpc/spapr/vfio: Put pages on VFIO container shutdown

[Alexey Kardashevskiy]

These patches are to fix a bug when pages stay pinned hours
after QEMU which requested pinning exited. This time 4 patches
for easier reviewing.

Please comment. Thanks.


Alexey Kardashevskiy (4):
  powerpc/iommu: Pass mm_struct to init/cleanup helpers
  powerpc/iommu: Stop using @current in mm_iommu_xxx
  vfio/spapr: Cache mm in tce_container
  powerpc/mm/iommu, vfio/spapr: Put pages on VFIO container shutdown

 arch/powerpc/include/asm/mmu_context.h |  20 ++--
 arch/powerpc/kernel/setup-common.c     |   2 +-
 arch/powerpc/mm/mmu_context_book3s64.c |   6 +-
 arch/powerpc/mm/mmu_context_iommu.c    |  60 ++++-------
 drivers/vfio/vfio_iommu_spapr_tce.c    | 180 +++++++++++++++++++++++----------
 5 files changed, 156 insertions(+), 112 deletions(-)

-- 
2.5.0.rc3

[PATCH kernel v3 1/4] powerpc/iommu: Pass mm_struct to init/cleanup helpers

[Alexey Kardashevskiy]

We are going to get rid of @current references in mmu_context_boos3s64.c
and cache mm_struct in the VFIO container. Since mm_context_t does not
have reference counting, we will be using mm_struct which does have
the reference counter.

This changes mm_iommu_init/mm_iommu_cleanup to receive mm_struct rather
than mm_context_t (which is embedded into mm).

This should not cause any behavioral change.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 arch/powerpc/include/asm/mmu_context.h | 4 ++--
 arch/powerpc/kernel/setup-common.c     | 2 +-
 arch/powerpc/mm/mmu_context_book3s64.c | 4 ++--
 arch/powerpc/mm/mmu_context_iommu.c    | 9 +++++----
 4 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 5c45114..424844b 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -23,8 +23,8 @@ extern bool mm_iommu_preregistered(void);
 extern long mm_iommu_get(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 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(unsigned long ua,
 		unsigned long size);
 extern struct mm_iommu_table_group_mem_t *mm_iommu_find(unsigned long ua,
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 270ee30..f516ac5 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -915,7 +915,7 @@ 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 e0f1c33..ad2e575 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -373,16 +373,17 @@ 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);
 	}
-- 
2.5.0.rc3

Re: [PATCH kernel v3 1/4] powerpc/iommu: Pass mm_struct to init/cleanup helpers

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 4186 bytes --]

On Thu, Oct 20, 2016 at 02:03:47PM +1100, Alexey Kardashevskiy wrote:
> We are going to get rid of @current references in mmu_context_boos3s64.c
> and cache mm_struct in the VFIO container. Since mm_context_t does not
> have reference counting, we will be using mm_struct which does have
> the reference counter.
> 
> This changes mm_iommu_init/mm_iommu_cleanup to receive mm_struct rather
> than mm_context_t (which is embedded into mm).
> 
> This should not cause any behavioral change.
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

> ---
>  arch/powerpc/include/asm/mmu_context.h | 4 ++--
>  arch/powerpc/kernel/setup-common.c     | 2 +-
>  arch/powerpc/mm/mmu_context_book3s64.c | 4 ++--
>  arch/powerpc/mm/mmu_context_iommu.c    | 9 +++++----
>  4 files changed, 10 insertions(+), 9 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
> index 5c45114..424844b 100644
> --- a/arch/powerpc/include/asm/mmu_context.h
> +++ b/arch/powerpc/include/asm/mmu_context.h
> @@ -23,8 +23,8 @@ extern bool mm_iommu_preregistered(void);
>  extern long mm_iommu_get(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 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(unsigned long ua,
>  		unsigned long size);
>  extern struct mm_iommu_table_group_mem_t *mm_iommu_find(unsigned long ua,
> diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
> index 270ee30..f516ac5 100644
> --- a/arch/powerpc/kernel/setup-common.c
> +++ b/arch/powerpc/kernel/setup-common.c
> @@ -915,7 +915,7 @@ 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 e0f1c33..ad2e575 100644
> --- a/arch/powerpc/mm/mmu_context_iommu.c
> +++ b/arch/powerpc/mm/mmu_context_iommu.c
> @@ -373,16 +373,17 @@ 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);
>  	}

-- 
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

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]

[PATCH kernel v3 2/4] powerpc/iommu: Stop using @current in mm_iommu_xxx

[Alexey Kardashevskiy]

This changes mm_iommu_xxx helpers to take mm_struct as a parameter
instead of getting it from @current which in some situations may
not have a valid reference to mm.

This changes helpers to receive @mm and moves all references to @current
to the caller, including checks for !current and !current->mm;
checks in mm_iommu_preregistered() are removed as there is no caller
yet.

This moves the mm_iommu_adjust_locked_vm() call to the caller as
it receives mm_iommu_table_group_mem_t but it needs mm.

This should cause no behavioral change.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 arch/powerpc/include/asm/mmu_context.h | 16 ++++++------
 arch/powerpc/mm/mmu_context_iommu.c    | 46 +++++++++++++---------------------
 drivers/vfio/vfio_iommu_spapr_tce.c    | 14 ++++++++---
 3 files changed, 36 insertions(+), 40 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 424844b..b9e3f0a 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -19,16 +19,18 @@ extern void destroy_context(struct mm_struct *mm);
 struct mm_iommu_table_group_mem_t;
 
 extern int isolate_lru_page(struct page *page);	/* from internal.h */
-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 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(unsigned long ua,
-		unsigned long size);
-extern struct mm_iommu_table_group_mem_t *mm_iommu_find(unsigned long ua,
-		unsigned long entries);
+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/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index ad2e575..4c6db09 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -56,7 +56,7 @@ 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,
@@ -66,12 +66,9 @@ 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);
 
@@ -124,19 +121,16 @@ static int mm_iommu_move_page_from_cma(struct page *page)
 	return 0;
 }
 
-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;
@@ -154,7 +148,7 @@ 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;
 
@@ -215,11 +209,11 @@ 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);
 
@@ -264,17 +258,13 @@ 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);
 	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);
 
 	if (mem->used == 0) {
@@ -297,6 +287,8 @@ 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);
 
@@ -304,14 +296,12 @@ long mm_iommu_put(struct mm_iommu_table_group_mem_t *mem)
 }
 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))) {
@@ -324,14 +314,12 @@ 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;
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 80378dd..d0c38b2 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -107,14 +107,17 @@ static long tce_iommu_unregister_pages(struct tce_container *container,
 {
 	struct mm_iommu_table_group_mem_t *mem;
 
+	if (!current || !current->mm)
+		return -ESRCH; /* process exited */
+
 	if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK))
 		return -EINVAL;
 
-	mem = mm_iommu_find(vaddr, size >> PAGE_SHIFT);
+	mem = mm_iommu_find(current->mm, vaddr, size >> PAGE_SHIFT);
 	if (!mem)
 		return -ENOENT;
 
-	return mm_iommu_put(mem);
+	return mm_iommu_put(current->mm, mem);
 }
 
 static long tce_iommu_register_pages(struct tce_container *container,
@@ -124,11 +127,14 @@ static long tce_iommu_register_pages(struct tce_container *container,
 	struct mm_iommu_table_group_mem_t *mem = NULL;
 	unsigned long entries = size >> PAGE_SHIFT;
 
+	if (!current || !current->mm)
+		return -ESRCH; /* process exited */
+
 	if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK) ||
 			((vaddr + size) < vaddr))
 		return -EINVAL;
 
-	ret = mm_iommu_get(vaddr, entries, &mem);
+	ret = mm_iommu_get(current->mm, vaddr, entries, &mem);
 	if (ret)
 		return ret;
 
@@ -375,7 +381,7 @@ static int tce_iommu_prereg_ua_to_hpa(unsigned long tce, unsigned long size,
 	long ret = 0;
 	struct mm_iommu_table_group_mem_t *mem;
 
-	mem = mm_iommu_lookup(tce, size);
+	mem = mm_iommu_lookup(current->mm, tce, size);
 	if (!mem)
 		return -EINVAL;
 
-- 
2.5.0.rc3

Re: [PATCH kernel v3 2/4] powerpc/iommu: Stop using @current in mm_iommu_xxx

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 9497 bytes --]

On Thu, Oct 20, 2016 at 02:03:48PM +1100, Alexey Kardashevskiy wrote:
> This changes mm_iommu_xxx helpers to take mm_struct as a parameter
> instead of getting it from @current which in some situations may
> not have a valid reference to mm.
> 
> This changes helpers to receive @mm and moves all references to @current
> to the caller, including checks for !current and !current->mm;
> checks in mm_iommu_preregistered() are removed as there is no caller
> yet.
> 
> This moves the mm_iommu_adjust_locked_vm() call to the caller as
> it receives mm_iommu_table_group_mem_t but it needs mm.
> 
> This should cause no behavioral change.
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

> ---
>  arch/powerpc/include/asm/mmu_context.h | 16 ++++++------
>  arch/powerpc/mm/mmu_context_iommu.c    | 46 +++++++++++++---------------------
>  drivers/vfio/vfio_iommu_spapr_tce.c    | 14 ++++++++---
>  3 files changed, 36 insertions(+), 40 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
> index 424844b..b9e3f0a 100644
> --- a/arch/powerpc/include/asm/mmu_context.h
> +++ b/arch/powerpc/include/asm/mmu_context.h
> @@ -19,16 +19,18 @@ extern void destroy_context(struct mm_struct *mm);
>  struct mm_iommu_table_group_mem_t;
>  
>  extern int isolate_lru_page(struct page *page);	/* from internal.h */
> -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 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(unsigned long ua,
> -		unsigned long size);
> -extern struct mm_iommu_table_group_mem_t *mm_iommu_find(unsigned long ua,
> -		unsigned long entries);
> +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/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
> index ad2e575..4c6db09 100644
> --- a/arch/powerpc/mm/mmu_context_iommu.c
> +++ b/arch/powerpc/mm/mmu_context_iommu.c
> @@ -56,7 +56,7 @@ 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,
> @@ -66,12 +66,9 @@ 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);
>  
> @@ -124,19 +121,16 @@ static int mm_iommu_move_page_from_cma(struct page *page)
>  	return 0;
>  }
>  
> -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;
> @@ -154,7 +148,7 @@ 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;
>  
> @@ -215,11 +209,11 @@ 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);
>  
> @@ -264,17 +258,13 @@ 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);
>  	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);
>  
>  	if (mem->used == 0) {
> @@ -297,6 +287,8 @@ 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);
>  
> @@ -304,14 +296,12 @@ long mm_iommu_put(struct mm_iommu_table_group_mem_t *mem)
>  }
>  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))) {
> @@ -324,14 +314,12 @@ 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;
> diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
> index 80378dd..d0c38b2 100644
> --- a/drivers/vfio/vfio_iommu_spapr_tce.c
> +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
> @@ -107,14 +107,17 @@ static long tce_iommu_unregister_pages(struct tce_container *container,
>  {
>  	struct mm_iommu_table_group_mem_t *mem;
>  
> +	if (!current || !current->mm)
> +		return -ESRCH; /* process exited */
> +
>  	if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK))
>  		return -EINVAL;
>  
> -	mem = mm_iommu_find(vaddr, size >> PAGE_SHIFT);
> +	mem = mm_iommu_find(current->mm, vaddr, size >> PAGE_SHIFT);
>  	if (!mem)
>  		return -ENOENT;
>  
> -	return mm_iommu_put(mem);
> +	return mm_iommu_put(current->mm, mem);
>  }
>  
>  static long tce_iommu_register_pages(struct tce_container *container,
> @@ -124,11 +127,14 @@ static long tce_iommu_register_pages(struct tce_container *container,
>  	struct mm_iommu_table_group_mem_t *mem = NULL;
>  	unsigned long entries = size >> PAGE_SHIFT;
>  
> +	if (!current || !current->mm)
> +		return -ESRCH; /* process exited */
> +
>  	if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK) ||
>  			((vaddr + size) < vaddr))
>  		return -EINVAL;
>  
> -	ret = mm_iommu_get(vaddr, entries, &mem);
> +	ret = mm_iommu_get(current->mm, vaddr, entries, &mem);
>  	if (ret)
>  		return ret;
>  
> @@ -375,7 +381,7 @@ static int tce_iommu_prereg_ua_to_hpa(unsigned long tce, unsigned long size,
>  	long ret = 0;
>  	struct mm_iommu_table_group_mem_t *mem;
>  
> -	mem = mm_iommu_lookup(tce, size);
> +	mem = mm_iommu_lookup(current->mm, tce, size);
>  	if (!mem)
>  		return -EINVAL;
>  

-- 
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

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]

[PATCH kernel v3 3/4] vfio/spapr: Cache mm in tce_container

[Alexey Kardashevskiy]

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 is NULL).

This references mm and stores the pointer in the container; this is done
when a container is just created so checking for !current->mm in other
places becomes pointless.

This replaces current->mm with container->mm everywhere except debug
prints.

This adds a check that current->mm is the same as the one stored in
the container to prevent userspace from registering memory in other
processes.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 drivers/vfio/vfio_iommu_spapr_tce.c | 127 ++++++++++++++++++++----------------
 1 file changed, 71 insertions(+), 56 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index d0c38b2..6b0b121 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -31,49 +31,46 @@
 static void tce_iommu_detach_group(void *iommu_data,
 		struct iommu_group *iommu_group);
 
-static long try_increment_locked_vm(long npages)
+static long try_increment_locked_vm(struct mm_struct *mm, long npages)
 {
 	long ret = 0, locked, lock_limit;
 
-	if (!current || !current->mm)
-		return -ESRCH; /* process exited */
-
 	if (!npages)
 		return 0;
 
-	down_write(&current->mm->mmap_sem);
-	locked = current->mm->locked_vm + npages;
+	down_write(&mm->mmap_sem);
+	locked = mm->locked_vm + npages;
 	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 	if (locked > lock_limit && !capable(CAP_IPC_LOCK))
 		ret = -ENOMEM;
 	else
-		current->mm->locked_vm += npages;
+		mm->locked_vm += npages;
 
 	pr_debug("[%d] RLIMIT_MEMLOCK +%ld %ld/%ld%s\n", current->pid,
 			npages << PAGE_SHIFT,
-			current->mm->locked_vm << PAGE_SHIFT,
+			mm->locked_vm << PAGE_SHIFT,
 			rlimit(RLIMIT_MEMLOCK),
 			ret ? " - exceeded" : "");
 
-	up_write(&current->mm->mmap_sem);
+	up_write(&mm->mmap_sem);
 
 	return ret;
 }
 
-static void decrement_locked_vm(long npages)
+static void decrement_locked_vm(struct mm_struct *mm, long npages)
 {
-	if (!current || !current->mm || !npages)
+	if (!mm || !npages)
 		return; /* process exited */
 
-	down_write(&current->mm->mmap_sem);
-	if (WARN_ON_ONCE(npages > current->mm->locked_vm))
-		npages = current->mm->locked_vm;
-	current->mm->locked_vm -= npages;
+	down_write(&mm->mmap_sem);
+	if (WARN_ON_ONCE(npages > mm->locked_vm))
+		npages = mm->locked_vm;
+	mm->locked_vm -= npages;
 	pr_debug("[%d] RLIMIT_MEMLOCK -%ld %ld/%ld\n", current->pid,
 			npages << PAGE_SHIFT,
-			current->mm->locked_vm << PAGE_SHIFT,
+			mm->locked_vm << PAGE_SHIFT,
 			rlimit(RLIMIT_MEMLOCK));
-	up_write(&current->mm->mmap_sem);
+	up_write(&mm->mmap_sem);
 }
 
 /*
@@ -98,6 +95,7 @@ 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;
 };
@@ -113,11 +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(current->mm, vaddr, size >> PAGE_SHIFT);
+	mem = mm_iommu_find(container->mm, vaddr, size >> PAGE_SHIFT);
 	if (!mem)
 		return -ENOENT;
 
-	return mm_iommu_put(current->mm, mem);
+	return mm_iommu_put(container->mm, mem);
 }
 
 static long tce_iommu_register_pages(struct tce_container *container,
@@ -134,7 +132,7 @@ static long tce_iommu_register_pages(struct tce_container *container,
 			((vaddr + size) < vaddr))
 		return -EINVAL;
 
-	ret = mm_iommu_get(current->mm, vaddr, entries, &mem);
+	ret = mm_iommu_get(container->mm, vaddr, entries, &mem);
 	if (ret)
 		return ret;
 
@@ -143,7 +141,8 @@ static long tce_iommu_register_pages(struct tce_container *container,
 	return 0;
 }
 
-static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
+static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl,
+		struct mm_struct *mm)
 {
 	unsigned long cb = _ALIGN_UP(sizeof(tbl->it_userspace[0]) *
 			tbl->it_size, PAGE_SIZE);
@@ -152,13 +151,13 @@ static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
 
 	BUG_ON(tbl->it_userspace);
 
-	ret = try_increment_locked_vm(cb >> PAGE_SHIFT);
+	ret = try_increment_locked_vm(mm, cb >> PAGE_SHIFT);
 	if (ret)
 		return ret;
 
 	uas = vzalloc(cb);
 	if (!uas) {
-		decrement_locked_vm(cb >> PAGE_SHIFT);
+		decrement_locked_vm(mm, cb >> PAGE_SHIFT);
 		return -ENOMEM;
 	}
 	tbl->it_userspace = uas;
@@ -166,7 +165,8 @@ static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
 	return 0;
 }
 
-static void tce_iommu_userspace_view_free(struct iommu_table *tbl)
+static void tce_iommu_userspace_view_free(struct iommu_table *tbl,
+		struct mm_struct *mm)
 {
 	unsigned long cb = _ALIGN_UP(sizeof(tbl->it_userspace[0]) *
 			tbl->it_size, PAGE_SIZE);
@@ -176,7 +176,7 @@ static void tce_iommu_userspace_view_free(struct iommu_table *tbl)
 
 	vfree(tbl->it_userspace);
 	tbl->it_userspace = NULL;
-	decrement_locked_vm(cb >> PAGE_SHIFT);
+	decrement_locked_vm(mm, cb >> PAGE_SHIFT);
 }
 
 static bool tce_page_is_contained(struct page *page, unsigned page_shift)
@@ -236,9 +236,6 @@ static int tce_iommu_enable(struct tce_container *container)
 	struct iommu_table_group *table_group;
 	struct tce_iommu_group *tcegrp;
 
-	if (!current->mm)
-		return -ESRCH; /* process exited */
-
 	if (container->enabled)
 		return -EBUSY;
 
@@ -284,7 +281,7 @@ static int tce_iommu_enable(struct tce_container *container)
 		return -EPERM;
 
 	locked = table_group->tce32_size >> PAGE_SHIFT;
-	ret = try_increment_locked_vm(locked);
+	ret = try_increment_locked_vm(container->mm, locked);
 	if (ret)
 		return ret;
 
@@ -302,10 +299,7 @@ static void tce_iommu_disable(struct tce_container *container)
 
 	container->enabled = false;
 
-	if (!current->mm)
-		return;
-
-	decrement_locked_vm(container->locked_pages);
+	decrement_locked_vm(container->mm, container->locked_pages);
 }
 
 static void *tce_iommu_open(unsigned long arg)
@@ -317,6 +311,9 @@ static void *tce_iommu_open(unsigned long arg)
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (!current->mm)
+		return ERR_PTR(-ESRCH); /* process exited */
+
 	container = kzalloc(sizeof(*container), GFP_KERNEL);
 	if (!container)
 		return ERR_PTR(-ENOMEM);
@@ -326,13 +323,17 @@ static void *tce_iommu_open(unsigned long arg)
 
 	container->v2 = arg == VFIO_SPAPR_TCE_v2_IOMMU;
 
+	container->mm = current->mm;
+	atomic_inc(&container->mm->mm_count);
+
 	return container;
 }
 
 static int tce_iommu_clear(struct tce_container *container,
 		struct iommu_table *tbl,
 		unsigned long entry, unsigned long pages);
-static void tce_iommu_free_table(struct iommu_table *tbl);
+static void tce_iommu_free_table(struct tce_container *container,
+		struct iommu_table *tbl);
 
 static void tce_iommu_release(void *iommu_data)
 {
@@ -357,10 +358,19 @@ static void tce_iommu_release(void *iommu_data)
 			continue;
 
 		tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
-		tce_iommu_free_table(tbl);
+		tce_iommu_free_table(container, tbl);
+	}
+
+	while (!list_empty(&container->prereg_list)) {
+		struct tce_iommu_prereg *tcemem;
+
+		tcemem = list_first_entry(&container->prereg_list,
+				struct tce_iommu_prereg, next);
+		tce_iommu_prereg_free(container, tcemem);
 	}
 
 	tce_iommu_disable(container);
+	mmdrop(container->mm);
 	mutex_destroy(&container->lock);
 
 	kfree(container);
@@ -375,13 +385,14 @@ 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(current->mm, tce, size);
+	mem = mm_iommu_lookup(container->mm, tce, size);
 	if (!mem)
 		return -EINVAL;
 
@@ -394,18 +405,18 @@ 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",
@@ -435,7 +446,7 @@ 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;
 		}
 
@@ -515,13 +526,16 @@ static long tce_iommu_build_v2(struct tce_container *container,
 	unsigned long hpa;
 	enum dma_data_direction dirtmp;
 
+	if (container->mm != current->mm)
+		return -ESRCH;
+
 	for (i = 0; i < pages; ++i) {
 		struct mm_iommu_table_group_mem_t *mem = NULL;
 		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;
 
@@ -542,7 +556,7 @@ 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);
@@ -550,7 +564,7 @@ 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;
 
@@ -578,7 +592,7 @@ static long tce_iommu_create_table(struct tce_container *container,
 	if (!table_size)
 		return -EINVAL;
 
-	ret = try_increment_locked_vm(table_size >> PAGE_SHIFT);
+	ret = try_increment_locked_vm(container->mm, table_size >> PAGE_SHIFT);
 	if (ret)
 		return ret;
 
@@ -589,24 +603,25 @@ static long tce_iommu_create_table(struct tce_container *container,
 	WARN_ON(!ret && ((*ptbl)->it_allocated_size != table_size));
 
 	if (!ret && container->v2) {
-		ret = tce_iommu_userspace_view_alloc(*ptbl);
+		ret = tce_iommu_userspace_view_alloc(*ptbl, container->mm);
 		if (ret)
 			(*ptbl)->it_ops->free(*ptbl);
 	}
 
 	if (ret)
-		decrement_locked_vm(table_size >> PAGE_SHIFT);
+		decrement_locked_vm(container->mm, table_size >> PAGE_SHIFT);
 
 	return ret;
 }
 
-static void tce_iommu_free_table(struct iommu_table *tbl)
+static void tce_iommu_free_table(struct tce_container *container,
+		struct iommu_table *tbl)
 {
 	unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT;
 
-	tce_iommu_userspace_view_free(tbl);
+	tce_iommu_userspace_view_free(tbl, container->mm);
 	tbl->it_ops->free(tbl);
-	decrement_locked_vm(pages);
+	decrement_locked_vm(container->mm, pages);
 }
 
 static long tce_iommu_create_window(struct tce_container *container,
@@ -669,7 +684,7 @@ static long tce_iommu_create_window(struct tce_container *container,
 		table_group = iommu_group_get_iommudata(tcegrp->grp);
 		table_group->ops->unset_window(table_group, num);
 	}
-	tce_iommu_free_table(tbl);
+	tce_iommu_free_table(container, tbl);
 
 	return ret;
 }
@@ -707,7 +722,7 @@ static long tce_iommu_remove_window(struct tce_container *container,
 
 	/* Free table */
 	tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
-	tce_iommu_free_table(tbl);
+	tce_iommu_free_table(container, tbl);
 	container->tables[num] = NULL;
 
 	return 0;
@@ -1049,7 +1064,7 @@ static void tce_iommu_release_ownership(struct tce_container *container,
 			continue;
 
 		tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
-		tce_iommu_userspace_view_free(tbl);
+		tce_iommu_userspace_view_free(tbl, container->mm);
 		if (tbl->it_map)
 			iommu_release_ownership(tbl);
 
@@ -1068,7 +1083,7 @@ static int tce_iommu_take_ownership(struct tce_container *container,
 		if (!tbl || !tbl->it_map)
 			continue;
 
-		rc = tce_iommu_userspace_view_alloc(tbl);
+		rc = tce_iommu_userspace_view_alloc(tbl, container->mm);
 		if (!rc)
 			rc = iommu_take_ownership(tbl);
 
-- 
2.5.0.rc3

Re: [PATCH kernel v3 3/4] vfio/spapr: Cache mm in tce_container

[Nicholas Piggin]

On Thu, 20 Oct 2016 14:03:49 +1100
Alexey Kardashevskiy <aik@ozlabs.ru> wrote:

> 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 is NULL).
> 
> This references mm and stores the pointer in the container; this is done
> when a container is just created so checking for !current->mm in other
> places becomes pointless.
> 
> This replaces current->mm with container->mm everywhere except debug
> prints.
> 
> This adds a check that current->mm is the same as the one stored in
> the container to prevent userspace from registering memory in other
> processes.
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> ---
>  drivers/vfio/vfio_iommu_spapr_tce.c | 127 ++++++++++++++++++++----------------
>  1 file changed, 71 insertions(+), 56 deletions(-)
> 
> diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
> index d0c38b2..6b0b121 100644
> --- a/drivers/vfio/vfio_iommu_spapr_tce.c
> +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
> @@ -31,49 +31,46 @@

Does it make sense to move the rest of these hunks into patch 2?
I think they're similarly just moving the mm reference into callers.


>  static void tce_iommu_detach_group(void *iommu_data,
>  		struct iommu_group *iommu_group);
>  
> -static long try_increment_locked_vm(long npages)
> +static long try_increment_locked_vm(struct mm_struct *mm, long npages)
>  {
>  	long ret = 0, locked, lock_limit;
>  
> -	if (!current || !current->mm)
> -		return -ESRCH; /* process exited */
> -
>  	if (!npages)
>  		return 0;
>  
> -	down_write(&current->mm->mmap_sem);
> -	locked = current->mm->locked_vm + npages;
> +	down_write(&mm->mmap_sem);
> +	locked = mm->locked_vm + npages;
>  	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
>  	if (locked > lock_limit && !capable(CAP_IPC_LOCK))
>  		ret = -ENOMEM;
>  	else
> -		current->mm->locked_vm += npages;
> +		mm->locked_vm += npages;
>  
>  	pr_debug("[%d] RLIMIT_MEMLOCK +%ld %ld/%ld%s\n", current->pid,
>  			npages << PAGE_SHIFT,
> -			current->mm->locked_vm << PAGE_SHIFT,
> +			mm->locked_vm << PAGE_SHIFT,
>  			rlimit(RLIMIT_MEMLOCK),
>  			ret ? " - exceeded" : "");
>  
> -	up_write(&current->mm->mmap_sem);
> +	up_write(&mm->mmap_sem);
>  
>  	return ret;
>  }
>  
> -static void decrement_locked_vm(long npages)
> +static void decrement_locked_vm(struct mm_struct *mm, long npages)
>  {
> -	if (!current || !current->mm || !npages)
> +	if (!mm || !npages)
>  		return; /* process exited */

I know you're trying to be defensive and change as little logic as possible,
but some cases should be an error, and I think some of the "process exited"
comments were wrong anyway.

Maybe pull the !mm test into the caller and make it WARN_ON?


> @@ -317,6 +311,9 @@ static void *tce_iommu_open(unsigned long arg)
>  		return ERR_PTR(-EINVAL);
>  	}
>  
> +	if (!current->mm)
> +		return ERR_PTR(-ESRCH); /* process exited */

A userspace thread in the kernel can't have its mm disappear, unless you
are actually in the exit code. !current->mm is more like a test for a kernel
thread.


> +
>  	container = kzalloc(sizeof(*container), GFP_KERNEL);
>  	if (!container)
>  		return ERR_PTR(-ENOMEM);
> @@ -326,13 +323,17 @@ static void *tce_iommu_open(unsigned long arg)
>  
>  	container->v2 = arg == VFIO_SPAPR_TCE_v2_IOMMU;
>  
> +	container->mm = current->mm;
> +	atomic_inc(&container->mm->mm_count);
> +
>  	return container;

It's a nitpick if you respin the patch, but I guess it would better be
described as a reference than a cache of the object. "have tce_container
take a reference to mm_struct".


> @@ -515,13 +526,16 @@ static long tce_iommu_build_v2(struct tce_container *container,
>  	unsigned long hpa;
>  	enum dma_data_direction dirtmp;
>  
> +	if (container->mm != current->mm)
> +		return -ESRCH;

Good, is this condition now enforced on all entrypoints that use
container->mm (except the final teardown)? (The mlock/rlimit stuff,
as we talked about before, doesn't make sense if not).

Thanks,
Nick

Re: [PATCH kernel v3 3/4] vfio/spapr: Cache mm in tce_container

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 5458 bytes --]

On Thu, Oct 20, 2016 at 06:31:21PM +1100, Nicholas Piggin wrote:
> On Thu, 20 Oct 2016 14:03:49 +1100
> Alexey Kardashevskiy <aik@ozlabs.ru> wrote:
> 
> > 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 is NULL).
> > 
> > This references mm and stores the pointer in the container; this is done
> > when a container is just created so checking for !current->mm in other
> > places becomes pointless.
> > 
> > This replaces current->mm with container->mm everywhere except debug
> > prints.
> > 
> > This adds a check that current->mm is the same as the one stored in
> > the container to prevent userspace from registering memory in other
> > processes.
> > 
> > Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> > ---
> >  drivers/vfio/vfio_iommu_spapr_tce.c | 127 ++++++++++++++++++++----------------
> >  1 file changed, 71 insertions(+), 56 deletions(-)
> > 
> > diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
> > index d0c38b2..6b0b121 100644
> > --- a/drivers/vfio/vfio_iommu_spapr_tce.c
> > +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
> > @@ -31,49 +31,46 @@
> 
> Does it make sense to move the rest of these hunks into patch 2?
> I think they're similarly just moving the mm reference into callers.
> 
> 
> >  static void tce_iommu_detach_group(void *iommu_data,
> >  		struct iommu_group *iommu_group);
> >  
> > -static long try_increment_locked_vm(long npages)
> > +static long try_increment_locked_vm(struct mm_struct *mm, long npages)
> >  {
> >  	long ret = 0, locked, lock_limit;
> >  
> > -	if (!current || !current->mm)
> > -		return -ESRCH; /* process exited */
> > -
> >  	if (!npages)
> >  		return 0;
> >  
> > -	down_write(&current->mm->mmap_sem);
> > -	locked = current->mm->locked_vm + npages;
> > +	down_write(&mm->mmap_sem);
> > +	locked = mm->locked_vm + npages;
> >  	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
> >  	if (locked > lock_limit && !capable(CAP_IPC_LOCK))
> >  		ret = -ENOMEM;
> >  	else
> > -		current->mm->locked_vm += npages;
> > +		mm->locked_vm += npages;
> >  
> >  	pr_debug("[%d] RLIMIT_MEMLOCK +%ld %ld/%ld%s\n", current->pid,
> >  			npages << PAGE_SHIFT,
> > -			current->mm->locked_vm << PAGE_SHIFT,
> > +			mm->locked_vm << PAGE_SHIFT,
> >  			rlimit(RLIMIT_MEMLOCK),
> >  			ret ? " - exceeded" : "");
> >  
> > -	up_write(&current->mm->mmap_sem);
> > +	up_write(&mm->mmap_sem);
> >  
> >  	return ret;
> >  }
> >  
> > -static void decrement_locked_vm(long npages)
> > +static void decrement_locked_vm(struct mm_struct *mm, long npages)
> >  {
> > -	if (!current || !current->mm || !npages)
> > +	if (!mm || !npages)
> >  		return; /* process exited */
> 
> I know you're trying to be defensive and change as little logic as possible,
> but some cases should be an error, and I think some of the "process exited"
> comments were wrong anyway.
> 
> Maybe pull the !mm test into the caller and make it WARN_ON?
> 
> 
> > @@ -317,6 +311,9 @@ static void *tce_iommu_open(unsigned long arg)
> >  		return ERR_PTR(-EINVAL);
> >  	}
> >  
> > +	if (!current->mm)
> > +		return ERR_PTR(-ESRCH); /* process exited */
> 
> A userspace thread in the kernel can't have its mm disappear, unless you
> are actually in the exit code. !current->mm is more like a test for a kernel
> thread.
> 
> 
> > +
> >  	container = kzalloc(sizeof(*container), GFP_KERNEL);
> >  	if (!container)
> >  		return ERR_PTR(-ENOMEM);
> > @@ -326,13 +323,17 @@ static void *tce_iommu_open(unsigned long arg)
> >  
> >  	container->v2 = arg == VFIO_SPAPR_TCE_v2_IOMMU;
> >  
> > +	container->mm = current->mm;
> > +	atomic_inc(&container->mm->mm_count);
> > +
> >  	return container;
> 
> It's a nitpick if you respin the patch, but I guess it would better be
> described as a reference than a cache of the object. "have tce_container
> take a reference to mm_struct".
> 
> 
> > @@ -515,13 +526,16 @@ static long tce_iommu_build_v2(struct tce_container *container,
> >  	unsigned long hpa;
> >  	enum dma_data_direction dirtmp;
> >  
> > +	if (container->mm != current->mm)
> > +		return -ESRCH;
> 
> Good, is this condition now enforced on all entrypoints that use
> container->mm (except the final teardown)? (The mlock/rlimit stuff,
> as we talked about before, doesn't make sense if not).

Right.  I don't know that it's actually dangerous, but i think it
would be needlessly weird for one process to be able to manipulate
another process's mm via the container fd.  So all the entry points
that are directly called from userspace (basically, the ioctl()s)
should verify that current->mm matches container->mm (except the one
which initiallizes container->mm, obviously).

One other concern.  If I follow the logic correctly, if a process
created a container, passed the fd to another process then exited, the
container fd held by the other process would keep the original
process's mm alive indefinitely.  I'm not sure if that's a problem.
Nick?

-- 
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

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]

Re: [PATCH kernel v3 3/4] vfio/spapr: Cache mm in tce_container

[Nicholas Piggin]

On Fri, 21 Oct 2016 11:21:34 +1100
David Gibson <david@gibson.dropbear.id.au> wrote:

> On Thu, Oct 20, 2016 at 06:31:21PM +1100, Nicholas Piggin wrote:
> > On Thu, 20 Oct 2016 14:03:49 +1100
> > Alexey Kardashevskiy <aik@ozlabs.ru> wrote:
> >   
> > > 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 is NULL).
> > > 
> > > This references mm and stores the pointer in the container; this is done
> > > when a container is just created so checking for !current->mm in other
> > > places becomes pointless.
> > > 
> > > This replaces current->mm with container->mm everywhere except debug
> > > prints.
> > > 
> > > This adds a check that current->mm is the same as the one stored in
> > > the container to prevent userspace from registering memory in other
> > > processes.
> > > 
> > > Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> > > ---
> > >  drivers/vfio/vfio_iommu_spapr_tce.c | 127 ++++++++++++++++++++----------------
> > >  1 file changed, 71 insertions(+), 56 deletions(-)
> > > 
> > > diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
> > > index d0c38b2..6b0b121 100644
> > > --- a/drivers/vfio/vfio_iommu_spapr_tce.c
> > > +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
> > > @@ -31,49 +31,46 @@  
> > 
> > Does it make sense to move the rest of these hunks into patch 2?
> > I think they're similarly just moving the mm reference into callers.
> > 
> >   
> > >  static void tce_iommu_detach_group(void *iommu_data,
> > >  		struct iommu_group *iommu_group);
> > >  
> > > -static long try_increment_locked_vm(long npages)
> > > +static long try_increment_locked_vm(struct mm_struct *mm, long npages)
> > >  {
> > >  	long ret = 0, locked, lock_limit;
> > >  
> > > -	if (!current || !current->mm)
> > > -		return -ESRCH; /* process exited */
> > > -
> > >  	if (!npages)
> > >  		return 0;
> > >  
> > > -	down_write(&current->mm->mmap_sem);
> > > -	locked = current->mm->locked_vm + npages;
> > > +	down_write(&mm->mmap_sem);
> > > +	locked = mm->locked_vm + npages;
> > >  	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
> > >  	if (locked > lock_limit && !capable(CAP_IPC_LOCK))
> > >  		ret = -ENOMEM;
> > >  	else
> > > -		current->mm->locked_vm += npages;
> > > +		mm->locked_vm += npages;
> > >  
> > >  	pr_debug("[%d] RLIMIT_MEMLOCK +%ld %ld/%ld%s\n", current->pid,
> > >  			npages << PAGE_SHIFT,
> > > -			current->mm->locked_vm << PAGE_SHIFT,
> > > +			mm->locked_vm << PAGE_SHIFT,
> > >  			rlimit(RLIMIT_MEMLOCK),
> > >  			ret ? " - exceeded" : "");
> > >  
> > > -	up_write(&current->mm->mmap_sem);
> > > +	up_write(&mm->mmap_sem);
> > >  
> > >  	return ret;
> > >  }
> > >  
> > > -static void decrement_locked_vm(long npages)
> > > +static void decrement_locked_vm(struct mm_struct *mm, long npages)
> > >  {
> > > -	if (!current || !current->mm || !npages)
> > > +	if (!mm || !npages)
> > >  		return; /* process exited */  
> > 
> > I know you're trying to be defensive and change as little logic as possible,
> > but some cases should be an error, and I think some of the "process exited"
> > comments were wrong anyway.
> > 
> > Maybe pull the !mm test into the caller and make it WARN_ON?
> > 
> >   
> > > @@ -317,6 +311,9 @@ static void *tce_iommu_open(unsigned long arg)
> > >  		return ERR_PTR(-EINVAL);
> > >  	}
> > >  
> > > +	if (!current->mm)
> > > +		return ERR_PTR(-ESRCH); /* process exited */  
> > 
> > A userspace thread in the kernel can't have its mm disappear, unless you
> > are actually in the exit code. !current->mm is more like a test for a kernel
> > thread.
> > 
> >   
> > > +
> > >  	container = kzalloc(sizeof(*container), GFP_KERNEL);
> > >  	if (!container)
> > >  		return ERR_PTR(-ENOMEM);
> > > @@ -326,13 +323,17 @@ static void *tce_iommu_open(unsigned long arg)
> > >  
> > >  	container->v2 = arg == VFIO_SPAPR_TCE_v2_IOMMU;
> > >  
> > > +	container->mm = current->mm;
> > > +	atomic_inc(&container->mm->mm_count);
> > > +
> > >  	return container;  
> > 
> > It's a nitpick if you respin the patch, but I guess it would better be
> > described as a reference than a cache of the object. "have tce_container
> > take a reference to mm_struct".
> > 
> >   
> > > @@ -515,13 +526,16 @@ static long tce_iommu_build_v2(struct tce_container *container,
> > >  	unsigned long hpa;
> > >  	enum dma_data_direction dirtmp;
> > >  
> > > +	if (container->mm != current->mm)
> > > +		return -ESRCH;  
> > 
> > Good, is this condition now enforced on all entrypoints that use
> > container->mm (except the final teardown)? (The mlock/rlimit stuff,
> > as we talked about before, doesn't make sense if not).  
> 
> Right.  I don't know that it's actually dangerous, but i think it
> would be needlessly weird for one process to be able to manipulate
> another process's mm via the container fd.  So all the entry points
> that are directly called from userspace (basically, the ioctl()s)
> should verify that current->mm matches container->mm (except the one
> which initiallizes container->mm, obviously).
> 
> One other concern.  If I follow the logic correctly, if a process
> created a container, passed the fd to another process then exited, the
> container fd held by the other process would keep the original
> process's mm alive indefinitely.  I'm not sure if that's a problem.
> Nick?
> 

Keeping the mm alive indefinitely is okay. When a process exits, it
will tear down its user mappings, but the mm struct stays around for
other users. Kernel threads can pick these up and keep them alive for
example, which is what was causing the problem in the first place.

Thanks,
Nick

Re: [PATCH kernel v3 3/4] vfio/spapr: Cache mm in tce_container

[Alexey Kardashevskiy]

On 20/10/16 18:31, Nicholas Piggin wrote:
> On Thu, 20 Oct 2016 14:03:49 +1100
> Alexey Kardashevskiy <aik@ozlabs.ru> wrote:
> 
>> 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 is NULL).
>>
>> This references mm and stores the pointer in the container; this is done
>> when a container is just created so checking for !current->mm in other
>> places becomes pointless.
>>
>> This replaces current->mm with container->mm everywhere except debug
>> prints.
>>
>> This adds a check that current->mm is the same as the one stored in
>> the container to prevent userspace from registering memory in other
>> processes.
>>
>> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
>> ---
>>  drivers/vfio/vfio_iommu_spapr_tce.c | 127 ++++++++++++++++++++----------------
>>  1 file changed, 71 insertions(+), 56 deletions(-)
>>
>> diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
>> index d0c38b2..6b0b121 100644
>> --- a/drivers/vfio/vfio_iommu_spapr_tce.c
>> +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
>> @@ -31,49 +31,46 @@
> 
> Does it make sense to move the rest of these hunks into patch 2?
> I think they're similarly just moving the mm reference into callers.


Patch #2 is moving chunks between 2 maintainership areas - ppc64 and vfio,
this one changes only vfio code, usually it is easier to split patches this
way.

> 
> 
>>  static void tce_iommu_detach_group(void *iommu_data,
>>  		struct iommu_group *iommu_group);
>>  
>> -static long try_increment_locked_vm(long npages)
>> +static long try_increment_locked_vm(struct mm_struct *mm, long npages)
>>  {
>>  	long ret = 0, locked, lock_limit;
>>  
>> -	if (!current || !current->mm)
>> -		return -ESRCH; /* process exited */
>> -
>>  	if (!npages)
>>  		return 0;
>>  
>> -	down_write(&current->mm->mmap_sem);
>> -	locked = current->mm->locked_vm + npages;
>> +	down_write(&mm->mmap_sem);
>> +	locked = mm->locked_vm + npages;
>>  	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
>>  	if (locked > lock_limit && !capable(CAP_IPC_LOCK))
>>  		ret = -ENOMEM;
>>  	else
>> -		current->mm->locked_vm += npages;
>> +		mm->locked_vm += npages;
>>  
>>  	pr_debug("[%d] RLIMIT_MEMLOCK +%ld %ld/%ld%s\n", current->pid,
>>  			npages << PAGE_SHIFT,
>> -			current->mm->locked_vm << PAGE_SHIFT,
>> +			mm->locked_vm << PAGE_SHIFT,
>>  			rlimit(RLIMIT_MEMLOCK),
>>  			ret ? " - exceeded" : "");
>>  
>> -	up_write(&current->mm->mmap_sem);
>> +	up_write(&mm->mmap_sem);
>>  
>>  	return ret;
>>  }
>>  
>> -static void decrement_locked_vm(long npages)
>> +static void decrement_locked_vm(struct mm_struct *mm, long npages)
>>  {
>> -	if (!current || !current->mm || !npages)
>> +	if (!mm || !npages)
>>  		return; /* process exited */
> 
> I know you're trying to be defensive and change as little logic as possible,
> but some cases should be an error, and I think some of the "process exited"
> comments were wrong anyway.
> 
> Maybe pull the !mm test into the caller and make it WARN_ON?


No, the next patch should just drop this check as I am going to have a
valid mm pointer in a container all its lifetime.


> 
> 
>> @@ -317,6 +311,9 @@ static void *tce_iommu_open(unsigned long arg)
>>  		return ERR_PTR(-EINVAL);
>>  	}
>>  
>> +	if (!current->mm)
>> +		return ERR_PTR(-ESRCH); /* process exited */
> 
> A userspace thread in the kernel can't have its mm disappear, unless you
> are actually in the exit code. !current->mm is more like a test for a kernel
> thread.

Sorry, I am not following you here. I am going to use @mm, I need to check
if it is not NULL for whatever reason, I do this here, once, but it is
pointless anyway?


> 
> 
>> +
>>  	container = kzalloc(sizeof(*container), GFP_KERNEL);
>>  	if (!container)
>>  		return ERR_PTR(-ENOMEM);
>> @@ -326,13 +323,17 @@ static void *tce_iommu_open(unsigned long arg)
>>  
>>  	container->v2 = arg == VFIO_SPAPR_TCE_v2_IOMMU;
>>  
>> +	container->mm = current->mm;
>> +	atomic_inc(&container->mm->mm_count);
>> +
>>  	return container;
> 
> It's a nitpick if you respin the patch, but I guess it would better be
> described as a reference than a cache of the object. "have tce_container
> take a reference to mm_struct".

Ok, will do!


> 
> 
>> @@ -515,13 +526,16 @@ static long tce_iommu_build_v2(struct tce_container *container,
>>  	unsigned long hpa;
>>  	enum dma_data_direction dirtmp;
>>  
>> +	if (container->mm != current->mm)
>> +		return -ESRCH;
> 
> Good, is this condition now enforced on all entrypoints that use
> container->mm (except the final teardown)? (The mlock/rlimit stuff,
> as we talked about before, doesn't make sense if not).

After having a chat with Paul, I'll move this check (slightly improved) to
the beginning of tce_iommu_ioctl().



-- 
Alexey

Re: [PATCH kernel v3 3/4] vfio/spapr: Cache mm in tce_container

[Nicholas Piggin]

On Mon, 24 Oct 2016 15:25:34 +1100
Alexey Kardashevskiy <aik@ozlabs.ru> wrote:

> On 20/10/16 18:31, Nicholas Piggin wrote:
> > On Thu, 20 Oct 2016 14:03:49 +1100
> > Alexey Kardashevskiy <aik@ozlabs.ru> wrote:
> >   
> >> 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 is NULL).
> >>
> >> This references mm and stores the pointer in the container; this is done
> >> when a container is just created so checking for !current->mm in other
> >> places becomes pointless.
> >>
> >> This replaces current->mm with container->mm everywhere except debug
> >> prints.
> >>
> >> This adds a check that current->mm is the same as the one stored in
> >> the container to prevent userspace from registering memory in other
> >> processes.
> >>
> >> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> >> ---
> >>  drivers/vfio/vfio_iommu_spapr_tce.c | 127 ++++++++++++++++++++----------------
> >>  1 file changed, 71 insertions(+), 56 deletions(-)
> >>
> >> diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
> >> index d0c38b2..6b0b121 100644
> >> --- a/drivers/vfio/vfio_iommu_spapr_tce.c
> >> +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
> >> @@ -31,49 +31,46 @@  
> > 
> > Does it make sense to move the rest of these hunks into patch 2?
> > I think they're similarly just moving the mm reference into callers.  
> 
> 
> Patch #2 is moving chunks between 2 maintainership areas - ppc64 and vfio,
> this one changes only vfio code, usually it is easier to split patches this
> way.

Okay.


> >> -static void decrement_locked_vm(long npages)
> >> +static void decrement_locked_vm(struct mm_struct *mm, long npages)
> >>  {
> >> -	if (!current || !current->mm || !npages)
> >> +	if (!mm || !npages)
> >>  		return; /* process exited */  
> > 
> > I know you're trying to be defensive and change as little logic as possible,
> > but some cases should be an error, and I think some of the "process exited"
> > comments were wrong anyway.
> > 
> > Maybe pull the !mm test into the caller and make it WARN_ON?  
> 
> 
> No, the next patch should just drop this check as I am going to have a
> valid mm pointer in a container all its lifetime.

That works too.


> >> @@ -317,6 +311,9 @@ static void *tce_iommu_open(unsigned long arg)
> >>  		return ERR_PTR(-EINVAL);
> >>  	}
> >>  
> >> +	if (!current->mm)
> >> +		return ERR_PTR(-ESRCH); /* process exited */  
> > 
> > A userspace thread in the kernel can't have its mm disappear, unless you
> > are actually in the exit code. !current->mm is more like a test for a kernel
> > thread.  
> 
> Sorry, I am not following you here. I am going to use @mm, I need to check
> if it is not NULL for whatever reason, I do this here, once, but it is
> pointless anyway?

If you are going to use mm, and it's mm of a normal process context,
then you don't have to check if it is NULL.

This looks like you are expecting the call to be made the middle of
exit(2), which surely is not the case?


> >> @@ -326,13 +323,17 @@ static void *tce_iommu_open(unsigned long arg)
> >>  
> >>  	container->v2 = arg == VFIO_SPAPR_TCE_v2_IOMMU;
> >>  
> >> +	container->mm = current->mm;
> >> +	atomic_inc(&container->mm->mm_count);
> >> +
> >>  	return container;  
> > 
> > It's a nitpick if you respin the patch, but I guess it would better be
> > described as a reference than a cache of the object. "have tce_container
> > take a reference to mm_struct".  
> 
> Ok, will do!
> 
> 
> > 
> >   
> >> @@ -515,13 +526,16 @@ static long tce_iommu_build_v2(struct tce_container *container,
> >>  	unsigned long hpa;
> >>  	enum dma_data_direction dirtmp;
> >>  
> >> +	if (container->mm != current->mm)
> >> +		return -ESRCH;  
> > 
> > Good, is this condition now enforced on all entrypoints that use
> > container->mm (except the final teardown)? (The mlock/rlimit stuff,
> > as we talked about before, doesn't make sense if not).  
> 
> After having a chat with Paul, I'll move this check (slightly improved) to
> the beginning of tce_iommu_ioctl().

Sounds good. I'll take another look when you repost them.

Thanks,
Nick

Re: [PATCH kernel v3 3/4] vfio/spapr: Cache mm in tce_container

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 14407 bytes --]

On Thu, Oct 20, 2016 at 02:03:49PM +1100, Alexey Kardashevskiy wrote:
> 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 is NULL).
> 
> This references mm and stores the pointer in the container; this is done
> when a container is just created so checking for !current->mm in other
> places becomes pointless.
> 
> This replaces current->mm with container->mm everywhere except debug
> prints.
> 
> This adds a check that current->mm is the same as the one stored in
> the container to prevent userspace from registering memory in other
> processes.
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> ---
>  drivers/vfio/vfio_iommu_spapr_tce.c | 127 ++++++++++++++++++++----------------
>  1 file changed, 71 insertions(+), 56 deletions(-)
> 
> diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
> index d0c38b2..6b0b121 100644
> --- a/drivers/vfio/vfio_iommu_spapr_tce.c
> +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
> @@ -31,49 +31,46 @@
>  static void tce_iommu_detach_group(void *iommu_data,
>  		struct iommu_group *iommu_group);
>  
> -static long try_increment_locked_vm(long npages)
> +static long try_increment_locked_vm(struct mm_struct *mm, long npages)
>  {
>  	long ret = 0, locked, lock_limit;
>  
> -	if (!current || !current->mm)
> -		return -ESRCH; /* process exited */
> -
>  	if (!npages)
>  		return 0;
>  
> -	down_write(&current->mm->mmap_sem);
> -	locked = current->mm->locked_vm + npages;
> +	down_write(&mm->mmap_sem);
> +	locked = mm->locked_vm + npages;
>  	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
>  	if (locked > lock_limit && !capable(CAP_IPC_LOCK))
>  		ret = -ENOMEM;
>  	else
> -		current->mm->locked_vm += npages;
> +		mm->locked_vm += npages;
>  
>  	pr_debug("[%d] RLIMIT_MEMLOCK +%ld %ld/%ld%s\n", current->pid,
>  			npages << PAGE_SHIFT,
> -			current->mm->locked_vm << PAGE_SHIFT,
> +			mm->locked_vm << PAGE_SHIFT,
>  			rlimit(RLIMIT_MEMLOCK),
>  			ret ? " - exceeded" : "");
>  
> -	up_write(&current->mm->mmap_sem);
> +	up_write(&mm->mmap_sem);
>  
>  	return ret;
>  }
>  
> -static void decrement_locked_vm(long npages)
> +static void decrement_locked_vm(struct mm_struct *mm, long npages)
>  {
> -	if (!current || !current->mm || !npages)
> +	if (!mm || !npages)
>  		return; /* process exited */
>  
> -	down_write(&current->mm->mmap_sem);
> -	if (WARN_ON_ONCE(npages > current->mm->locked_vm))
> -		npages = current->mm->locked_vm;
> -	current->mm->locked_vm -= npages;
> +	down_write(&mm->mmap_sem);
> +	if (WARN_ON_ONCE(npages > mm->locked_vm))
> +		npages = mm->locked_vm;
> +	mm->locked_vm -= npages;
>  	pr_debug("[%d] RLIMIT_MEMLOCK -%ld %ld/%ld\n", current->pid,
>  			npages << PAGE_SHIFT,
> -			current->mm->locked_vm << PAGE_SHIFT,
> +			mm->locked_vm << PAGE_SHIFT,
>  			rlimit(RLIMIT_MEMLOCK));
> -	up_write(&current->mm->mmap_sem);
> +	up_write(&mm->mmap_sem);
>  }
>  
>  /*
> @@ -98,6 +95,7 @@ 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;
>  };
> @@ -113,11 +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(current->mm, vaddr, size >> PAGE_SHIFT);
> +	mem = mm_iommu_find(container->mm, vaddr, size >> PAGE_SHIFT);
>  	if (!mem)
>  		return -ENOENT;
>  
> -	return mm_iommu_put(current->mm, mem);
> +	return mm_iommu_put(container->mm, mem);
>  }
>  
>  static long tce_iommu_register_pages(struct tce_container *container,
> @@ -134,7 +132,7 @@ static long tce_iommu_register_pages(struct tce_container *container,
>  			((vaddr + size) < vaddr))
>  		return -EINVAL;
>  
> -	ret = mm_iommu_get(current->mm, vaddr, entries, &mem);
> +	ret = mm_iommu_get(container->mm, vaddr, entries, &mem);
>  	if (ret)
>  		return ret;
>  
> @@ -143,7 +141,8 @@ static long tce_iommu_register_pages(struct tce_container *container,
>  	return 0;
>  }
>  
> -static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
> +static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl,
> +		struct mm_struct *mm)
>  {
>  	unsigned long cb = _ALIGN_UP(sizeof(tbl->it_userspace[0]) *
>  			tbl->it_size, PAGE_SIZE);
> @@ -152,13 +151,13 @@ static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
>  
>  	BUG_ON(tbl->it_userspace);
>  
> -	ret = try_increment_locked_vm(cb >> PAGE_SHIFT);
> +	ret = try_increment_locked_vm(mm, cb >> PAGE_SHIFT);
>  	if (ret)
>  		return ret;
>  
>  	uas = vzalloc(cb);
>  	if (!uas) {
> -		decrement_locked_vm(cb >> PAGE_SHIFT);
> +		decrement_locked_vm(mm, cb >> PAGE_SHIFT);
>  		return -ENOMEM;
>  	}
>  	tbl->it_userspace = uas;
> @@ -166,7 +165,8 @@ static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
>  	return 0;
>  }
>  
> -static void tce_iommu_userspace_view_free(struct iommu_table *tbl)
> +static void tce_iommu_userspace_view_free(struct iommu_table *tbl,
> +		struct mm_struct *mm)
>  {
>  	unsigned long cb = _ALIGN_UP(sizeof(tbl->it_userspace[0]) *
>  			tbl->it_size, PAGE_SIZE);
> @@ -176,7 +176,7 @@ static void tce_iommu_userspace_view_free(struct iommu_table *tbl)
>  
>  	vfree(tbl->it_userspace);
>  	tbl->it_userspace = NULL;
> -	decrement_locked_vm(cb >> PAGE_SHIFT);
> +	decrement_locked_vm(mm, cb >> PAGE_SHIFT);
>  }
>  
>  static bool tce_page_is_contained(struct page *page, unsigned page_shift)
> @@ -236,9 +236,6 @@ static int tce_iommu_enable(struct tce_container *container)
>  	struct iommu_table_group *table_group;
>  	struct tce_iommu_group *tcegrp;
>  
> -	if (!current->mm)
> -		return -ESRCH; /* process exited */
> -
>  	if (container->enabled)
>  		return -EBUSY;
>  
> @@ -284,7 +281,7 @@ static int tce_iommu_enable(struct tce_container *container)
>  		return -EPERM;
>  
>  	locked = table_group->tce32_size >> PAGE_SHIFT;
> -	ret = try_increment_locked_vm(locked);
> +	ret = try_increment_locked_vm(container->mm, locked);
>  	if (ret)
>  		return ret;
>  
> @@ -302,10 +299,7 @@ static void tce_iommu_disable(struct tce_container *container)
>  
>  	container->enabled = false;
>  
> -	if (!current->mm)
> -		return;
> -
> -	decrement_locked_vm(container->locked_pages);
> +	decrement_locked_vm(container->mm, container->locked_pages);
>  }
>  
>  static void *tce_iommu_open(unsigned long arg)
> @@ -317,6 +311,9 @@ static void *tce_iommu_open(unsigned long arg)
>  		return ERR_PTR(-EINVAL);
>  	}
>  
> +	if (!current->mm)
> +		return ERR_PTR(-ESRCH); /* process exited */
> +
>  	container = kzalloc(sizeof(*container), GFP_KERNEL);
>  	if (!container)
>  		return ERR_PTR(-ENOMEM);
> @@ -326,13 +323,17 @@ static void *tce_iommu_open(unsigned long arg)
>  
>  	container->v2 = arg == VFIO_SPAPR_TCE_v2_IOMMU;
>  
> +	container->mm = current->mm;
> +	atomic_inc(&container->mm->mm_count);
> +
>  	return container;
>  }
>  
>  static int tce_iommu_clear(struct tce_container *container,
>  		struct iommu_table *tbl,
>  		unsigned long entry, unsigned long pages);
> -static void tce_iommu_free_table(struct iommu_table *tbl);
> +static void tce_iommu_free_table(struct tce_container *container,
> +		struct iommu_table *tbl);
>  
>  static void tce_iommu_release(void *iommu_data)
>  {
> @@ -357,10 +358,19 @@ static void tce_iommu_release(void *iommu_data)
>  			continue;
>  
>  		tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
> -		tce_iommu_free_table(tbl);
> +		tce_iommu_free_table(container, tbl);
> +	}
> +
> +	while (!list_empty(&container->prereg_list)) {

Uuh.. I think this breaks bisection.  The container->prereg_list is
only added in the next patch.

> +		struct tce_iommu_prereg *tcemem;
> +
> +		tcemem = list_first_entry(&container->prereg_list,
> +				struct tce_iommu_prereg, next);
> +		tce_iommu_prereg_free(container, tcemem);
>  	}
>  
>  	tce_iommu_disable(container);
> +	mmdrop(container->mm);
>  	mutex_destroy(&container->lock);
>  
>  	kfree(container);
> @@ -375,13 +385,14 @@ 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(current->mm, tce, size);
> +	mem = mm_iommu_lookup(container->mm, tce, size);
>  	if (!mem)
>  		return -EINVAL;
>  
> @@ -394,18 +405,18 @@ 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",
> @@ -435,7 +446,7 @@ 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;
>  		}
>  
> @@ -515,13 +526,16 @@ static long tce_iommu_build_v2(struct tce_container *container,
>  	unsigned long hpa;
>  	enum dma_data_direction dirtmp;
>  
> +	if (container->mm != current->mm)
> +		return -ESRCH;
> +
>  	for (i = 0; i < pages; ++i) {
>  		struct mm_iommu_table_group_mem_t *mem = NULL;
>  		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;
>  
> @@ -542,7 +556,7 @@ 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);
> @@ -550,7 +564,7 @@ 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;
>  
> @@ -578,7 +592,7 @@ static long tce_iommu_create_table(struct tce_container *container,
>  	if (!table_size)
>  		return -EINVAL;
>  
> -	ret = try_increment_locked_vm(table_size >> PAGE_SHIFT);
> +	ret = try_increment_locked_vm(container->mm, table_size >> PAGE_SHIFT);
>  	if (ret)
>  		return ret;
>  
> @@ -589,24 +603,25 @@ static long tce_iommu_create_table(struct tce_container *container,
>  	WARN_ON(!ret && ((*ptbl)->it_allocated_size != table_size));
>  
>  	if (!ret && container->v2) {
> -		ret = tce_iommu_userspace_view_alloc(*ptbl);
> +		ret = tce_iommu_userspace_view_alloc(*ptbl, container->mm);
>  		if (ret)
>  			(*ptbl)->it_ops->free(*ptbl);
>  	}
>  
>  	if (ret)
> -		decrement_locked_vm(table_size >> PAGE_SHIFT);
> +		decrement_locked_vm(container->mm, table_size >> PAGE_SHIFT);
>  
>  	return ret;
>  }
>  
> -static void tce_iommu_free_table(struct iommu_table *tbl)
> +static void tce_iommu_free_table(struct tce_container *container,
> +		struct iommu_table *tbl)
>  {
>  	unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT;
>  
> -	tce_iommu_userspace_view_free(tbl);
> +	tce_iommu_userspace_view_free(tbl, container->mm);
>  	tbl->it_ops->free(tbl);
> -	decrement_locked_vm(pages);
> +	decrement_locked_vm(container->mm, pages);
>  }
>  
>  static long tce_iommu_create_window(struct tce_container *container,
> @@ -669,7 +684,7 @@ static long tce_iommu_create_window(struct tce_container *container,
>  		table_group = iommu_group_get_iommudata(tcegrp->grp);
>  		table_group->ops->unset_window(table_group, num);
>  	}
> -	tce_iommu_free_table(tbl);
> +	tce_iommu_free_table(container, tbl);
>  
>  	return ret;
>  }
> @@ -707,7 +722,7 @@ static long tce_iommu_remove_window(struct tce_container *container,
>  
>  	/* Free table */
>  	tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
> -	tce_iommu_free_table(tbl);
> +	tce_iommu_free_table(container, tbl);
>  	container->tables[num] = NULL;
>  
>  	return 0;
> @@ -1049,7 +1064,7 @@ static void tce_iommu_release_ownership(struct tce_container *container,
>  			continue;
>  
>  		tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
> -		tce_iommu_userspace_view_free(tbl);
> +		tce_iommu_userspace_view_free(tbl, container->mm);
>  		if (tbl->it_map)
>  			iommu_release_ownership(tbl);
>  
> @@ -1068,7 +1083,7 @@ static int tce_iommu_take_ownership(struct tce_container *container,
>  		if (!tbl || !tbl->it_map)
>  			continue;
>  
> -		rc = tce_iommu_userspace_view_alloc(tbl);
> +		rc = tce_iommu_userspace_view_alloc(tbl, container->mm);
>  		if (!rc)
>  			rc = iommu_take_ownership(tbl);
>  

-- 
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

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]

[PATCH kernel v3 4/4] powerpc/mm/iommu, vfio/spapr: Put pages on VFIO container shutdown

[Alexey Kardashevskiy]

At the moment the userspace tool is expected to request pinning of
the entire guest RAM when VFIO IOMMU SPAPR v2 driver is present.
When the userspace process finishes, all the pinned pages need to
be put; this is done as a part of the userspace memory context (MM)
destruction which happens on the very last mmdrop().

This approach has a problem that a MM of the userspace process
may live longer than the userspace process itself as kernel threads
use userspace process MMs which was runnning on a CPU where
the kernel thread was scheduled to. If this happened, the MM remains
referenced until this exact kernel thread wakes up again
and releases the very last reference to the MM, on an idle system this
can take even hours.

This moves preregistered regions tracking from MM to VFIO; insteads of
using mm_iommu_table_group_mem_t::used, tce_container::prereg_list is
added so each container releases regions which it has pre-registered.

This changes the userspace interface to return EBUSY if a memory
region is already registered in a container. However it should not
have any practical effect as the only userspace tool available now
does register memory region once per container anyway.

As tce_iommu_register_pages/tce_iommu_unregister_pages are called
under container->lock, this does not need additional locking.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
---
Changes:
v3:
* moved tce_iommu_prereg_free() call out of list_for_each_entry()

v2:
* updated commit log
---
 arch/powerpc/mm/mmu_context_book3s64.c |  4 ---
 arch/powerpc/mm/mmu_context_iommu.c    | 11 --------
 drivers/vfio/vfio_iommu_spapr_tce.c    | 49 +++++++++++++++++++++++++++++++++-
 3 files changed, 48 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index ad82735..1a07969 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -159,10 +159,6 @@ 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);
-#endif
-
 #ifdef CONFIG_PPC_ICSWX
 	drop_cop(mm->context.acop, mm);
 	kfree(mm->context.cop_lockp);
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index 4c6db09..104bad0 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -365,14 +365,3 @@ void mm_iommu_init(struct mm_struct *mm)
 {
 	INIT_LIST_HEAD_RCU(&mm->context.iommu_group_mem_list);
 }
-
-void mm_iommu_cleanup(struct mm_struct *mm)
-{
-	struct mm_iommu_table_group_mem_t *mem, *tmp;
-
-	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 6b0b121..3e2f757 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -86,6 +86,15 @@ struct tce_iommu_group {
 };
 
 /*
+ * A container needs to remember which preregistered region  it has
+ * referenced to do proper cleanup at the userspace process exit.
+ */
+struct tce_iommu_prereg {
+	struct list_head next;
+	struct mm_iommu_table_group_mem_t *mem;
+};
+
+/*
  * The container descriptor supports only a single group per container.
  * Required by the API as the container is not supplied with the IOMMU group
  * at the moment of initialization.
@@ -98,12 +107,27 @@ struct tce_container {
 	struct mm_struct *mm;
 	struct iommu_table *tables[IOMMU_TABLE_GROUP_MAX_TABLES];
 	struct list_head group_list;
+	struct list_head prereg_list;
 };
 
+static long tce_iommu_prereg_free(struct tce_container *container,
+		struct tce_iommu_prereg *tcemem)
+{
+	long ret;
+
+	list_del(&tcemem->next);
+	ret = mm_iommu_put(container->mm, tcemem->mem);
+	kfree(tcemem);
+
+	return ret;
+}
+
 static long tce_iommu_unregister_pages(struct tce_container *container,
 		__u64 vaddr, __u64 size)
 {
 	struct mm_iommu_table_group_mem_t *mem;
+	struct tce_iommu_prereg *tcemem;
+	bool found = false;
 
 	if (!current || !current->mm)
 		return -ESRCH; /* process exited */
@@ -115,7 +139,17 @@ static long tce_iommu_unregister_pages(struct tce_container *container,
 	if (!mem)
 		return -ENOENT;
 
-	return mm_iommu_put(container->mm, mem);
+	list_for_each_entry(tcemem, &container->prereg_list, next) {
+		if (tcemem->mem == mem) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found)
+		return -ENOENT;
+
+	return tce_iommu_prereg_free(container, tcemem);
 }
 
 static long tce_iommu_register_pages(struct tce_container *container,
@@ -123,6 +157,7 @@ static long tce_iommu_register_pages(struct tce_container *container,
 {
 	long ret = 0;
 	struct mm_iommu_table_group_mem_t *mem = NULL;
+	struct tce_iommu_prereg *tcemem;
 	unsigned long entries = size >> PAGE_SHIFT;
 
 	if (!current || !current->mm)
@@ -136,6 +171,17 @@ static long tce_iommu_register_pages(struct tce_container *container,
 	if (ret)
 		return ret;
 
+	list_for_each_entry(tcemem, &container->prereg_list, next) {
+		if (tcemem->mem == mem) {
+			mm_iommu_put(container->mm, mem);
+			return -EBUSY;
+		}
+	}
+
+	tcemem = kzalloc(sizeof(*tcemem), GFP_KERNEL);
+	tcemem->mem = mem;
+	list_add(&tcemem->next, &container->prereg_list);
+
 	container->enabled = true;
 
 	return 0;
@@ -320,6 +366,7 @@ static void *tce_iommu_open(unsigned long arg)
 
 	mutex_init(&container->lock);
 	INIT_LIST_HEAD_RCU(&container->group_list);
+	INIT_LIST_HEAD_RCU(&container->prereg_list);
 
 	container->v2 = arg == VFIO_SPAPR_TCE_v2_IOMMU;
 
-- 
2.5.0.rc3

Re: [PATCH kernel v3 4/4] powerpc/mm/iommu, vfio/spapr: Put pages on VFIO container shutdown

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 6615 bytes --]

On Thu, Oct 20, 2016 at 02:03:50PM +1100, Alexey Kardashevskiy wrote:
> At the moment the userspace tool is expected to request pinning of
> the entire guest RAM when VFIO IOMMU SPAPR v2 driver is present.
> When the userspace process finishes, all the pinned pages need to
> be put; this is done as a part of the userspace memory context (MM)
> destruction which happens on the very last mmdrop().
> 
> This approach has a problem that a MM of the userspace process
> may live longer than the userspace process itself as kernel threads
> use userspace process MMs which was runnning on a CPU where
> the kernel thread was scheduled to. If this happened, the MM remains
> referenced until this exact kernel thread wakes up again
> and releases the very last reference to the MM, on an idle system this
> can take even hours.
> 
> This moves preregistered regions tracking from MM to VFIO; insteads of
> using mm_iommu_table_group_mem_t::used, tce_container::prereg_list is
> added so each container releases regions which it has pre-registered.
> 
> This changes the userspace interface to return EBUSY if a memory
> region is already registered in a container. However it should not
> have any practical effect as the only userspace tool available now
> does register memory region once per container anyway.
> 
> As tce_iommu_register_pages/tce_iommu_unregister_pages are called
> under container->lock, this does not need additional locking.
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
> ---
> Changes:
> v3:
> * moved tce_iommu_prereg_free() call out of list_for_each_entry()
> 
> v2:
> * updated commit log
> ---
>  arch/powerpc/mm/mmu_context_book3s64.c |  4 ---
>  arch/powerpc/mm/mmu_context_iommu.c    | 11 --------
>  drivers/vfio/vfio_iommu_spapr_tce.c    | 49 +++++++++++++++++++++++++++++++++-
>  3 files changed, 48 insertions(+), 16 deletions(-)
> 
> diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
> index ad82735..1a07969 100644
> --- a/arch/powerpc/mm/mmu_context_book3s64.c
> +++ b/arch/powerpc/mm/mmu_context_book3s64.c
> @@ -159,10 +159,6 @@ 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);
> -#endif
> -
>  #ifdef CONFIG_PPC_ICSWX
>  	drop_cop(mm->context.acop, mm);
>  	kfree(mm->context.cop_lockp);
> diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
> index 4c6db09..104bad0 100644
> --- a/arch/powerpc/mm/mmu_context_iommu.c
> +++ b/arch/powerpc/mm/mmu_context_iommu.c
> @@ -365,14 +365,3 @@ void mm_iommu_init(struct mm_struct *mm)
>  {
>  	INIT_LIST_HEAD_RCU(&mm->context.iommu_group_mem_list);
>  }
> -
> -void mm_iommu_cleanup(struct mm_struct *mm)
> -{
> -	struct mm_iommu_table_group_mem_t *mem, *tmp;
> -
> -	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 6b0b121..3e2f757 100644
> --- a/drivers/vfio/vfio_iommu_spapr_tce.c
> +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
> @@ -86,6 +86,15 @@ struct tce_iommu_group {
>  };
>  
>  /*
> + * A container needs to remember which preregistered region  it has
> + * referenced to do proper cleanup at the userspace process exit.
> + */
> +struct tce_iommu_prereg {
> +	struct list_head next;
> +	struct mm_iommu_table_group_mem_t *mem;
> +};
> +
> +/*
>   * The container descriptor supports only a single group per container.
>   * Required by the API as the container is not supplied with the IOMMU group
>   * at the moment of initialization.
> @@ -98,12 +107,27 @@ struct tce_container {
>  	struct mm_struct *mm;
>  	struct iommu_table *tables[IOMMU_TABLE_GROUP_MAX_TABLES];
>  	struct list_head group_list;
> +	struct list_head prereg_list;
>  };
>  
> +static long tce_iommu_prereg_free(struct tce_container *container,
> +		struct tce_iommu_prereg *tcemem)
> +{
> +	long ret;
> +
> +	list_del(&tcemem->next);
> +	ret = mm_iommu_put(container->mm, tcemem->mem);
> +	kfree(tcemem);
> +
> +	return ret;
> +}
> +
>  static long tce_iommu_unregister_pages(struct tce_container *container,
>  		__u64 vaddr, __u64 size)
>  {
>  	struct mm_iommu_table_group_mem_t *mem;
> +	struct tce_iommu_prereg *tcemem;
> +	bool found = false;
>  
>  	if (!current || !current->mm)
>  		return -ESRCH; /* process exited */
> @@ -115,7 +139,17 @@ static long tce_iommu_unregister_pages(struct tce_container *container,
>  	if (!mem)
>  		return -ENOENT;
>  
> -	return mm_iommu_put(container->mm, mem);
> +	list_for_each_entry(tcemem, &container->prereg_list, next) {
> +		if (tcemem->mem == mem) {
> +			found = true;
> +			break;
> +		}
> +	}
> +
> +	if (!found)
> +		return -ENOENT;
> +
> +	return tce_iommu_prereg_free(container, tcemem);
>  }
>  
>  static long tce_iommu_register_pages(struct tce_container *container,
> @@ -123,6 +157,7 @@ static long tce_iommu_register_pages(struct tce_container *container,
>  {
>  	long ret = 0;
>  	struct mm_iommu_table_group_mem_t *mem = NULL;
> +	struct tce_iommu_prereg *tcemem;
>  	unsigned long entries = size >> PAGE_SHIFT;
>  
>  	if (!current || !current->mm)
> @@ -136,6 +171,17 @@ static long tce_iommu_register_pages(struct tce_container *container,
>  	if (ret)
>  		return ret;
>  
> +	list_for_each_entry(tcemem, &container->prereg_list, next) {
> +		if (tcemem->mem == mem) {
> +			mm_iommu_put(container->mm, mem);
> +			return -EBUSY;
> +		}
> +	}

Wouldn't it make more sense to do this duplicate check before the
mm_iommu_get(), so you don't have to roll it back on this error path.

> +
> +	tcemem = kzalloc(sizeof(*tcemem), GFP_KERNEL);
> +	tcemem->mem = mem;
> +	list_add(&tcemem->next, &container->prereg_list);
> +
>  	container->enabled = true;
>  
>  	return 0;
> @@ -320,6 +366,7 @@ static void *tce_iommu_open(unsigned long arg)
>  
>  	mutex_init(&container->lock);
>  	INIT_LIST_HEAD_RCU(&container->group_list);
> +	INIT_LIST_HEAD_RCU(&container->prereg_list);
>  
>  	container->v2 = arg == VFIO_SPAPR_TCE_v2_IOMMU;
>  

-- 
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

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]