| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <YoOXVptckAU3/Aaa@dhcp22.suse.cz>
Date: Tue, 17 May 2022 14:38:46 +0200
From: Michal Hocko <mhocko@...e.com>
To: Kristen Carlson Accardi <kristen@...ux.intel.com>
Cc: linux-sgx@...r.kernel.org, Jarkko Sakkinen <jarkko@...nel.org>,
Dave Hansen <dave.hansen@...ux.intel.com>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
x86@...nel.org, "H. Peter Anvin" <hpa@...or.com>,
linux-kernel@...r.kernel.org, Johannes Weiner <hannes@...xchg.org>,
Roman Gushchin <roman.gushchin@...ux.dev>,
Shakeel Butt <shakeelb@...gle.com>, linux-mm@...ck.org
Subject: Re: [RFC PATCH] x86/sgx: Set active memcg prior to shmem allocation
[CC memcg people and linux-mm]
On Mon 16-05-22 10:25:22, Kristen Carlson Accardi wrote:
> When the system runs out of enclave memory, SGX can reclaim EPC pages
> by swapping to normal RAM. These backing pages are allocated via a
> per-enclave shared memory area. Since SGX allows unlimited over
> commit on EPC memory, the reclaimer thread can allocate a large
> number of backing RAM pages in response to EPC memory pressure.
>
> When the shared memory backing RAM allocation occurs during
> the reclaimer thread context, the shared memory is charged to
> the root memory control group, and the shmem usage of the enclave
> is not properly accounted for, making cgroups ineffective at
> limiting the amount of RAM an enclave can consume.
>
> For example, when using a cgroup to launch a set of test
> enclaves, the kernel does not properly account for 50% - 75% of
> shmem page allocations on average. In the worst case, when
> nearly all allocations occur during the reclaimer thread, the
> kernel accounts less than a percent of the amount of shmem used
> by the enclave's cgroup to the correct cgroup.
>
> SGX currently stores a list of mm_structs that are associated with
> an enclave. In order to allow the enclave's cgroup to more accurately
> reflect the shmem usage, the memory control group (struct mem_cgroup)
> of one of these mm_structs can be set as the active memory cgroup
> prior to allocating any EPC backing pages. This will make any shmem
> allocations be charged to a memory control group associated with the
> enclave's cgroup. This will allow memory cgroup limits to restrict
> RAM usage more effectively.
>
> This patch will create a new function - sgx_encl_alloc_backing().
> This function will be used whenever a new backing storage page
> needs to be allocated. Previously the same function was used for
> page allocation as well as retrieving a previously allocated page.
> Prior to backing page allocation, if there is a mm_struct associated
> with the enclave that is requesting the allocation, it will be set
> as the active memory control group.
>
> Signed-off-by: Kristen Carlson Accardi <kristen@...ux.intel.com>
> ---
> arch/x86/kernel/cpu/sgx/encl.c | 89 +++++++++++++++++++++++++++++++++-
> arch/x86/kernel/cpu/sgx/encl.h | 6 ++-
> arch/x86/kernel/cpu/sgx/main.c | 4 +-
> 3 files changed, 93 insertions(+), 6 deletions(-)
>
> diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
> index 001808e3901c..fa017bc4f99e 100644
> --- a/arch/x86/kernel/cpu/sgx/encl.c
> +++ b/arch/x86/kernel/cpu/sgx/encl.c
> @@ -32,7 +32,7 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page,
> else
> page_index = PFN_DOWN(encl->size);
>
> - ret = sgx_encl_get_backing(encl, page_index, &b);
> + ret = sgx_encl_lookup_backing(encl, page_index, &b);
> if (ret)
> return ret;
>
> @@ -574,7 +574,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl,
> * 0 on success,
> * -errno otherwise.
> */
> -int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
> +static int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
> struct sgx_backing *backing)
> {
> pgoff_t pcmd_index = PFN_DOWN(encl->size) + 1 + (page_index >> 5);
> @@ -601,6 +601,91 @@ int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
> return 0;
> }
>
> +static struct mem_cgroup * sgx_encl_set_active_memcg(struct sgx_encl *encl)
> +{
> + struct mm_struct *mm = current->mm;
> + struct sgx_encl_mm *encl_mm;
> + struct mem_cgroup *memcg;
> + int idx;
> +
> + memcg = get_mem_cgroup_from_mm(mm);
> +
> + if (mm)
> + return memcg;
> +
> + idx = srcu_read_lock(&encl->srcu);
> +
> + list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) {
> + if (encl_mm->mm == NULL)
> + continue;
> +
> + mm = encl_mm->mm;
> + break;
> +
> + }
> +
> + srcu_read_unlock(&encl->srcu, idx);
> +
> + if (!mm)
> + return memcg;
> +
> + memcg = get_mem_cgroup_from_mm(mm);
> +
> + return set_active_memcg(memcg);
> +}
> +
> +/**
> + * sgx_encl_alloc_backing() - allocate a new backing storage page
> + * @encl: an enclave pointer
> + * @page_index: enclave page index
> + * @backing: data for accessing backing storage for the page
> + *
> + * If this function is called from the kernel thread, it will set
> + * the active memcg to one of the enclaves mm's in order to ensure
> + * that shmem page allocations are charged to the enclave when they
> + * are retrieved. Upon exit, the old memcg (if it existed at all)
> + * will be restored.
> + *
> + * Return:
> + * 0 on success,
> + * -errno otherwise.
> + */
> +int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
> + struct sgx_backing *backing)
> +{
> + struct mem_cgroup *old_memcg;
> + int ret;
> +
> + old_memcg = sgx_encl_set_active_memcg(encl);
> +
> + ret = sgx_encl_get_backing(encl, page_index, backing);
> +
> + set_active_memcg(old_memcg);
> +
> + return ret;
> +}
> +
> +/**
> + * sgx_encl_lookup_backing() - retrieve an existing backing storage page
> + * @encl: an enclave pointer
> + * @page_index: enclave page index
> + * @backing: data for accessing backing storage for the page
> + *
> + * Retrieve a backing page for loading data back into an EPC page with ELDU.
> + * It is the caller's responsibility to ensure that it is appropriate to use
> + * sgx_encl_lookup_backing() rather than sgx_encl_alloc_backing(). If lookup is
> + * not used correctly, this will cause an allocation which is not accounted for.
> + *
> + * Return:
> + * 0 on success,
> + * -errno otherwise.
> + */
> +int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
> + struct sgx_backing *backing)
> +{
> + return sgx_encl_get_backing(encl, page_index, backing);
> +}
> +
> /**
> * sgx_encl_put_backing() - Unpin the backing storage
> * @backing: data for accessing backing storage for the page
> diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h
> index fec43ca65065..7816cfe8f832 100644
> --- a/arch/x86/kernel/cpu/sgx/encl.h
> +++ b/arch/x86/kernel/cpu/sgx/encl.h
> @@ -105,8 +105,10 @@ int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start,
>
> void sgx_encl_release(struct kref *ref);
> int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm);
> -int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
> - struct sgx_backing *backing);
> +int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
> + struct sgx_backing *backing);
> +int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
> + struct sgx_backing *backing);
> void sgx_encl_put_backing(struct sgx_backing *backing, bool do_write);
> int sgx_encl_test_and_clear_young(struct mm_struct *mm,
> struct sgx_encl_page *page);
> diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
> index 4b41efc9e367..7d41c8538795 100644
> --- a/arch/x86/kernel/cpu/sgx/main.c
> +++ b/arch/x86/kernel/cpu/sgx/main.c
> @@ -310,7 +310,7 @@ static void sgx_reclaimer_write(struct sgx_epc_page *epc_page,
> encl->secs_child_cnt--;
>
> if (!encl->secs_child_cnt && test_bit(SGX_ENCL_INITIALIZED, &encl->flags)) {
> - ret = sgx_encl_get_backing(encl, PFN_DOWN(encl->size),
> + ret = sgx_encl_alloc_backing(encl, PFN_DOWN(encl->size),
> &secs_backing);
> if (ret)
> goto out;
> @@ -381,7 +381,7 @@ static void sgx_reclaim_pages(void)
> goto skip;
>
> page_index = PFN_DOWN(encl_page->desc - encl_page->encl->base);
> - ret = sgx_encl_get_backing(encl_page->encl, page_index, &backing[i]);
> + ret = sgx_encl_alloc_backing(encl_page->encl, page_index, &backing[i]);
> if (ret)
> goto skip;
>
> --
> 2.20.1
--
Michal Hocko
SUSE Labs
Powered by blists - more mailing lists