From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ozlabs.org (ozlabs.org [103.22.144.67]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 3tCZmN6dcqzDvZ7 for ; Tue, 8 Nov 2016 14:39:00 +1100 (AEDT) Date: Tue, 8 Nov 2016 14:33:44 +1100 From: David Gibson To: Alexey Kardashevskiy Cc: linuxppc-dev@lists.ozlabs.org, Alex Williamson , Nicholas Piggin , Paul Mackerras Subject: Re: [PATCH kernel v4 3/4] vfio/spapr: Reference mm in tce_container Message-ID: <20161108033344.GJ28688@umbus.fritz.box> References: <1477291990-2872-1-git-send-email-aik@ozlabs.ru> <1477291990-2872-4-git-send-email-aik@ozlabs.ru> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="F4+N/OgRSdC8YnqX" In-Reply-To: <1477291990-2872-4-git-send-email-aik@ozlabs.ru> List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , --F4+N/OgRSdC8YnqX Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Mon, Oct 24, 2016 at 05:53:09PM +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 have tce_container take a reference to mm_struct and > use it later when the process is gone (@current or @current->mm is NULL). >=20 > 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. >=20 > This replaces current->mm with container->mm everywhere except debug > prints. >=20 > This adds a check that current->mm is the same as the one stored in > the container to prevent userspace from making changes to a memory > context of other processes; in order to add this check, > VFIO_CHECK_EXTENSION is moved out of the switch(cmd) as it is > quite special anyway - it is the only ioctl() called when neither > container nor container->mm is initialized. >=20 > Signed-off-by: Alexey Kardashevskiy Reviewed-by: David Gibson > --- > Changes: > v4: > * added check for container->mm!=3Dcurrent->mm in tce_iommu_ioctl() > for all ioctls and removed other redundand checks > --- > drivers/vfio/vfio_iommu_spapr_tce.c | 131 ++++++++++++++++++------------= ------ > 1 file changed, 66 insertions(+), 65 deletions(-) >=20 > diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iomm= u_spapr_tce.c > index d0c38b2..81ab93f 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); > =20 > -static long try_increment_locked_vm(long npages) > +static long try_increment_locked_vm(struct mm_struct *mm, long npages) > { > long ret =3D 0, locked, lock_limit; > =20 > - if (!current || !current->mm) > - return -ESRCH; /* process exited */ > - > if (!npages) > return 0; > =20 > - down_write(¤t->mm->mmap_sem); > - locked =3D current->mm->locked_vm + npages; > + down_write(&mm->mmap_sem); > + locked =3D mm->locked_vm + npages; > lock_limit =3D rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; > if (locked > lock_limit && !capable(CAP_IPC_LOCK)) > ret =3D -ENOMEM; > else > - current->mm->locked_vm +=3D npages; > + mm->locked_vm +=3D npages; > =20 > 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" : ""); > =20 > - up_write(¤t->mm->mmap_sem); > + up_write(&mm->mmap_sem); > =20 > return ret; > } > =20 > -static void decrement_locked_vm(long npages) > +static void decrement_locked_vm(struct mm_struct *mm, long npages) > { > - if (!current || !current->mm || !npages) > - return; /* process exited */ > + if (!npages) > + return; > =20 > - down_write(¤t->mm->mmap_sem); > - if (WARN_ON_ONCE(npages > current->mm->locked_vm)) > - npages =3D current->mm->locked_vm; > - current->mm->locked_vm -=3D npages; > + down_write(&mm->mmap_sem); > + if (WARN_ON_ONCE(npages > mm->locked_vm)) > + npages =3D mm->locked_vm; > + mm->locked_vm -=3D 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(¤t->mm->mmap_sem); > + up_write(&mm->mmap_sem); > } > =20 > /* > @@ -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; > }; > @@ -107,17 +105,14 @@ static long tce_iommu_unregister_pages(struct tce_c= ontainer *container, > { > struct mm_iommu_table_group_mem_t *mem; > =20 > - if (!current || !current->mm) > - return -ESRCH; /* process exited */ > - > if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK)) > return -EINVAL; > =20 > - mem =3D mm_iommu_find(current->mm, vaddr, size >> PAGE_SHIFT); > + mem =3D mm_iommu_find(container->mm, vaddr, size >> PAGE_SHIFT); > if (!mem) > return -ENOENT; > =20 > - return mm_iommu_put(current->mm, mem); > + return mm_iommu_put(container->mm, mem); > } > =20 > static long tce_iommu_register_pages(struct tce_container *container, > @@ -127,14 +122,11 @@ static long tce_iommu_register_pages(struct tce_con= tainer *container, > struct mm_iommu_table_group_mem_t *mem =3D NULL; > unsigned long entries =3D size >> PAGE_SHIFT; > =20 > - if (!current || !current->mm) > - return -ESRCH; /* process exited */ > - > if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK) || > ((vaddr + size) < vaddr)) > return -EINVAL; > =20 > - ret =3D mm_iommu_get(current->mm, vaddr, entries, &mem); > + ret =3D mm_iommu_get(container->mm, vaddr, entries, &mem); > if (ret) > return ret; > =20 > @@ -143,7 +135,8 @@ static long tce_iommu_register_pages(struct tce_conta= iner *container, > return 0; > } > =20 > -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 =3D _ALIGN_UP(sizeof(tbl->it_userspace[0]) * > tbl->it_size, PAGE_SIZE); > @@ -152,13 +145,13 @@ static long tce_iommu_userspace_view_alloc(struct i= ommu_table *tbl) > =20 > BUG_ON(tbl->it_userspace); > =20 > - ret =3D try_increment_locked_vm(cb >> PAGE_SHIFT); > + ret =3D try_increment_locked_vm(mm, cb >> PAGE_SHIFT); > if (ret) > return ret; > =20 > uas =3D vzalloc(cb); > if (!uas) { > - decrement_locked_vm(cb >> PAGE_SHIFT); > + decrement_locked_vm(mm, cb >> PAGE_SHIFT); > return -ENOMEM; > } > tbl->it_userspace =3D uas; > @@ -166,7 +159,8 @@ static long tce_iommu_userspace_view_alloc(struct iom= mu_table *tbl) > return 0; > } > =20 > -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 =3D _ALIGN_UP(sizeof(tbl->it_userspace[0]) * > tbl->it_size, PAGE_SIZE); > @@ -176,7 +170,7 @@ static void tce_iommu_userspace_view_free(struct iomm= u_table *tbl) > =20 > vfree(tbl->it_userspace); > tbl->it_userspace =3D NULL; > - decrement_locked_vm(cb >> PAGE_SHIFT); > + decrement_locked_vm(mm, cb >> PAGE_SHIFT); > } > =20 > static bool tce_page_is_contained(struct page *page, unsigned page_shift) > @@ -236,9 +230,6 @@ static int tce_iommu_enable(struct tce_container *con= tainer) > struct iommu_table_group *table_group; > struct tce_iommu_group *tcegrp; > =20 > - if (!current->mm) > - return -ESRCH; /* process exited */ > - > if (container->enabled) > return -EBUSY; > =20 > @@ -284,7 +275,7 @@ static int tce_iommu_enable(struct tce_container *con= tainer) > return -EPERM; > =20 > locked =3D table_group->tce32_size >> PAGE_SHIFT; > - ret =3D try_increment_locked_vm(locked); > + ret =3D try_increment_locked_vm(container->mm, locked); > if (ret) > return ret; > =20 > @@ -302,10 +293,7 @@ static void tce_iommu_disable(struct tce_container *= container) > =20 > container->enabled =3D false; > =20 > - if (!current->mm) > - return; > - > - decrement_locked_vm(container->locked_pages); > + decrement_locked_vm(container->mm, container->locked_pages); > } > =20 > static void *tce_iommu_open(unsigned long arg) > @@ -326,13 +314,18 @@ static void *tce_iommu_open(unsigned long arg) > =20 > container->v2 =3D arg =3D=3D VFIO_SPAPR_TCE_v2_IOMMU; > =20 > + /* current->mm cannot be NULL in this context */ > + container->mm =3D current->mm; > + atomic_inc(&container->mm->mm_count); > + > return container; > } > =20 > 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); > =20 > static void tce_iommu_release(void *iommu_data) > { > @@ -357,10 +350,11 @@ static void tce_iommu_release(void *iommu_data) > continue; > =20 > tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size); > - tce_iommu_free_table(tbl); > + tce_iommu_free_table(container, tbl); > } > =20 > tce_iommu_disable(container); > + mmdrop(container->mm); > mutex_destroy(&container->lock); > =20 > kfree(container); > @@ -375,13 +369,14 @@ static void tce_iommu_unuse_page(struct tce_contain= er *container, > put_page(page); > } > =20 > -static int tce_iommu_prereg_ua_to_hpa(unsigned long tce, unsigned long s= ize, > +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 =3D 0; > struct mm_iommu_table_group_mem_t *mem; > =20 > - mem =3D mm_iommu_lookup(current->mm, tce, size); > + mem =3D mm_iommu_lookup(container->mm, tce, size); > if (!mem) > return -EINVAL; > =20 > @@ -394,18 +389,18 @@ static int tce_iommu_prereg_ua_to_hpa(unsigned long= tce, unsigned long size, > return 0; > } > =20 > -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 =3D NULL; > int ret; > unsigned long hpa =3D 0; > unsigned long *pua =3D IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry); > =20 > - if (!pua || !current || !current->mm) > + if (!pua) > return; > =20 > - ret =3D tce_iommu_prereg_ua_to_hpa(*pua, IOMMU_PAGE_SIZE(tbl), > + ret =3D 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=3D%d\n", > @@ -435,7 +430,7 @@ static int tce_iommu_clear(struct tce_container *cont= ainer, > continue; > =20 > if (container->v2) { > - tce_iommu_unuse_page_v2(tbl, entry); > + tce_iommu_unuse_page_v2(container, tbl, entry); > continue; > } > =20 > @@ -520,8 +515,8 @@ static long tce_iommu_build_v2(struct tce_container *= container, > unsigned long *pua =3D IOMMU_TABLE_USERSPACE_ENTRY(tbl, > entry + i); > =20 > - ret =3D tce_iommu_prereg_ua_to_hpa(tce, IOMMU_PAGE_SIZE(tbl), > - &hpa, &mem); > + ret =3D tce_iommu_prereg_ua_to_hpa(container, > + tce, IOMMU_PAGE_SIZE(tbl), &hpa, &mem); > if (ret) > break; > =20 > @@ -542,7 +537,7 @@ static long tce_iommu_build_v2(struct tce_container *= container, > ret =3D 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=3D%lx, tce=3D%lx, ret=3D%ld\n", > __func__, entry << tbl->it_page_shift, > tce, ret); > @@ -550,7 +545,7 @@ static long tce_iommu_build_v2(struct tce_container *= container, > } > =20 > if (dirtmp !=3D DMA_NONE) > - tce_iommu_unuse_page_v2(tbl, entry + i); > + tce_iommu_unuse_page_v2(container, tbl, entry + i); > =20 > *pua =3D tce; > =20 > @@ -578,7 +573,7 @@ static long tce_iommu_create_table(struct tce_contain= er *container, > if (!table_size) > return -EINVAL; > =20 > - ret =3D try_increment_locked_vm(table_size >> PAGE_SHIFT); > + ret =3D try_increment_locked_vm(container->mm, table_size >> PAGE_SHIFT= ); > if (ret) > return ret; > =20 > @@ -589,24 +584,25 @@ static long tce_iommu_create_table(struct tce_conta= iner *container, > WARN_ON(!ret && ((*ptbl)->it_allocated_size !=3D table_size)); > =20 > if (!ret && container->v2) { > - ret =3D tce_iommu_userspace_view_alloc(*ptbl); > + ret =3D tce_iommu_userspace_view_alloc(*ptbl, container->mm); > if (ret) > (*ptbl)->it_ops->free(*ptbl); > } > =20 > if (ret) > - decrement_locked_vm(table_size >> PAGE_SHIFT); > + decrement_locked_vm(container->mm, table_size >> PAGE_SHIFT); > =20 > return ret; > } > =20 > -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 =3D tbl->it_allocated_size >> PAGE_SHIFT; > =20 > - 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); > } > =20 > static long tce_iommu_create_window(struct tce_container *container, > @@ -669,7 +665,7 @@ static long tce_iommu_create_window(struct tce_contai= ner *container, > table_group =3D 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); > =20 > return ret; > } > @@ -707,7 +703,7 @@ static long tce_iommu_remove_window(struct tce_contai= ner *container, > =20 > /* 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] =3D NULL; > =20 > return 0; > @@ -720,8 +716,7 @@ static long tce_iommu_ioctl(void *iommu_data, > unsigned long minsz, ddwsz; > long ret; > =20 > - switch (cmd) { > - case VFIO_CHECK_EXTENSION: > + if (cmd =3D=3D VFIO_CHECK_EXTENSION) { > switch (arg) { > case VFIO_SPAPR_TCE_IOMMU: > case VFIO_SPAPR_TCE_v2_IOMMU: > @@ -733,7 +728,13 @@ static long tce_iommu_ioctl(void *iommu_data, > } > =20 > return (ret < 0) ? 0 : ret; > + } > =20 > + /* tce_iommu_open() initializes container->mm so it can't be NULL here = */ > + if (container->mm !=3D current->mm) > + return -ESRCH; > + > + switch (cmd) { > case VFIO_IOMMU_SPAPR_TCE_GET_INFO: { > struct vfio_iommu_spapr_tce_info info; > struct tce_iommu_group *tcegrp; > @@ -1049,7 +1050,7 @@ static void tce_iommu_release_ownership(struct tce_= container *container, > continue; > =20 > 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); > =20 > @@ -1068,7 +1069,7 @@ static int tce_iommu_take_ownership(struct tce_cont= ainer *container, > if (!tbl || !tbl->it_map) > continue; > =20 > - rc =3D tce_iommu_userspace_view_alloc(tbl); > + rc =3D tce_iommu_userspace_view_alloc(tbl, container->mm); > if (!rc) > rc =3D iommu_take_ownership(tbl); > =20 --=20 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 --F4+N/OgRSdC8YnqX Content-Type: application/pgp-signature; name="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQIcBAEBCAAGBQJYIUeYAAoJEGw4ysog2bOSkrYP/0TbajkYLkw5UBi5f6erzqGY U2pK92QR9H5SSDSIO5qeK+5d+0AzZoQeLwsq9Pacg3PObLxAXEJw/qYJAhvKVA5l Y2Far/itZhQ8DXXtUd0Q/diog60IVpTWR88vwjMrGtknVhSqXYo04rSFJCU2htZ9 rmwjDcFMON9nSI/RbarnyacDTqqtwui0dxNDQOW9MGiSQOc1evqcXmG5pg8ZbpID Shb009P6Sma8VbXQ2nqn+k2gYGVlkoLq/9HSXwxTjVMJvFsEAuGKA1EU4+hkifl9 ohQqRdHCG2lqfLP2baY3qx/DgNt4l5JRBBfSPAM1Lc+ftxcP0QoKrULKHEn1/rQz GWlv7GXDQcl+PDp/iDzRlMWxuKwV530lWzO+WwWMxt+XbfuCGVt534AH+XzcMQ0r dzHMdrToVD2eI9EWXq3/7JXiSdP8SPxb4Z7hGUefJ9KV+CzvtMFocqwKj+wnu26G SAbqdrnd6Fvz28jOB9W6fHynE5mFLlDuEZGyo56NZ9brEs8bJpjfJ/egDla9/wqd xScFvbRRJVHVppWfSw16wn7kyM1x2tFUtQ0HqAewQncfAjwCy0sYmfa5Kn19O7UN m2lAYamjXGyqqjSMlEVbsOHbU8Ungi2O6Zmf49tlQCXgiaahRbEla7tavldICVfz dEZymahJhLDhmHw9Rm25 =MZ8z -----END PGP SIGNATURE----- --F4+N/OgRSdC8YnqX--