From 659c0ce1cb9efc7f58d380ca4bb2a51ae9e30553 Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Fri, 17 Feb 2023 17:21:54 +0100 Subject: kernel/sys.c: fix and improve control flow in __sys_setres[ug]id() Linux Security Modules (LSMs) that implement the "capable" hook will usually emit an access denial message to the audit log whenever they "block" the current task from using the given capability based on their security policy. The occurrence of a denial is used as an indication that the given task has attempted an operation that requires the given access permission, so the callers of functions that perform LSM permission checks must take care to avoid calling them too early (before it is decided if the permission is actually needed to perform the requested operation). The __sys_setres[ug]id() functions violate this convention by first calling ns_capable_setid() and only then checking if the operation requires the capability or not. It means that any caller that has the capability granted by DAC (task's capability set) but not by MAC (LSMs) will generate a "denied" audit record, even if is doing an operation for which the capability is not required. Fix this by reordering the checks such that ns_capable_setid() is checked last and -EPERM is returned immediately if it returns false. While there, also do two small optimizations: * move the capability check before prepare_creds() and * bail out early in case of a no-op. Link: https://lkml.kernel.org/r/20230217162154.837549-1-omosnace@redhat.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Ondrej Mosnacek Cc: Eric W. Biederman Cc: Signed-off-by: Andrew Morton --- kernel/sys.c | 69 +++++++++++++++++++++++++++++++++++------------------------- 1 file changed, 40 insertions(+), 29 deletions(-) (limited to 'kernel/sys.c') diff --git a/kernel/sys.c b/kernel/sys.c index 495cd87d9bf4..351de7916302 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -664,6 +664,7 @@ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) struct cred *new; int retval; kuid_t kruid, keuid, ksuid; + bool ruid_new, euid_new, suid_new; kruid = make_kuid(ns, ruid); keuid = make_kuid(ns, euid); @@ -678,25 +679,29 @@ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) if ((suid != (uid_t) -1) && !uid_valid(ksuid)) return -EINVAL; + old = current_cred(); + + /* check for no-op */ + if ((ruid == (uid_t) -1 || uid_eq(kruid, old->uid)) && + (euid == (uid_t) -1 || (uid_eq(keuid, old->euid) && + uid_eq(keuid, old->fsuid))) && + (suid == (uid_t) -1 || uid_eq(ksuid, old->suid))) + return 0; + + ruid_new = ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && + !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid); + euid_new = euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && + !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid); + suid_new = suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && + !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid); + if ((ruid_new || euid_new || suid_new) && + !ns_capable_setid(old->user_ns, CAP_SETUID)) + return -EPERM; + new = prepare_creds(); if (!new) return -ENOMEM; - old = current_cred(); - - retval = -EPERM; - if (!ns_capable_setid(old->user_ns, CAP_SETUID)) { - if (ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && - !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid)) - goto error; - if (euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && - !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid)) - goto error; - if (suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && - !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid)) - goto error; - } - if (ruid != (uid_t) -1) { new->uid = kruid; if (!uid_eq(kruid, old->uid)) { @@ -761,6 +766,7 @@ long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) struct cred *new; int retval; kgid_t krgid, kegid, ksgid; + bool rgid_new, egid_new, sgid_new; krgid = make_kgid(ns, rgid); kegid = make_kgid(ns, egid); @@ -773,23 +779,28 @@ long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) if ((sgid != (gid_t) -1) && !gid_valid(ksgid)) return -EINVAL; + old = current_cred(); + + /* check for no-op */ + if ((rgid == (gid_t) -1 || gid_eq(krgid, old->gid)) && + (egid == (gid_t) -1 || (gid_eq(kegid, old->egid) && + gid_eq(kegid, old->fsgid))) && + (sgid == (gid_t) -1 || gid_eq(ksgid, old->sgid))) + return 0; + + rgid_new = rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && + !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid); + egid_new = egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && + !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid); + sgid_new = sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && + !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid); + if ((rgid_new || egid_new || sgid_new) && + !ns_capable_setid(old->user_ns, CAP_SETGID)) + return -EPERM; + new = prepare_creds(); if (!new) return -ENOMEM; - old = current_cred(); - - retval = -EPERM; - if (!ns_capable_setid(old->user_ns, CAP_SETGID)) { - if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && - !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid)) - goto error; - if (egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && - !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid)) - goto error; - if (sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && - !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid)) - goto error; - } if (rgid != (gid_t) -1) new->gid = krgid; -- cgit From ddc65971bb677aa9f6a4c21f76d3133e106f88eb Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Tue, 4 Apr 2023 21:31:48 +0900 Subject: prctl: add PR_GET_AUXV to copy auxv to userspace If a library wants to get information from auxv (for instance, AT_HWCAP/AT_HWCAP2), it has a few options, none of them perfectly reliable or ideal: - Be main or the pre-main startup code, and grub through the stack above main. Doesn't work for a library. - Call libc getauxval. Not ideal for libraries that are trying to be libc-independent and/or don't otherwise require anything from other libraries. - Open and read /proc/self/auxv. Doesn't work for libraries that may run in arbitrarily constrained environments that may not have /proc mounted (e.g. libraries that might be used by an init program or a container setup tool). - Assume you're on the main thread and still on the original stack, and try to walk the stack upwards, hoping to find auxv. Extremely bad idea. - Ask the caller to pass auxv in for you. Not ideal for a user-friendly library, and then your caller may have the same problem. Add a prctl that copies current->mm->saved_auxv to a userspace buffer. Link: https://lkml.kernel.org/r/d81864a7f7f43bca6afa2a09fc2e850e4050ab42.1680611394.git.josh@joshtriplett.org Signed-off-by: Josh Triplett Signed-off-by: Andrew Morton --- kernel/sys.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'kernel/sys.c') diff --git a/kernel/sys.c b/kernel/sys.c index 351de7916302..26c1399e0654 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2388,6 +2388,16 @@ static inline int prctl_get_mdwe(unsigned long arg2, unsigned long arg3, PR_MDWE_REFUSE_EXEC_GAIN : 0; } +static int prctl_get_auxv(void __user *addr, unsigned long len) +{ + struct mm_struct *mm = current->mm; + unsigned long size = min_t(unsigned long, sizeof(mm->saved_auxv), len); + + if (size && copy_to_user(addr, mm->saved_auxv, size)) + return -EFAULT; + return sizeof(mm->saved_auxv); +} + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2518,6 +2528,11 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, else return -EINVAL; break; + case PR_GET_AUXV: + if (arg4 || arg5) + return -EINVAL; + error = prctl_get_auxv((void __user *)arg2, arg3); + break; default: return -EINVAL; } -- cgit From d7597f59d1d33e9efbffa7060deb9ee5bd119e62 Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Mon, 17 Apr 2023 22:13:40 -0700 Subject: mm: add new api to enable ksm per process Patch series "mm: process/cgroup ksm support", v9. So far KSM can only be enabled by calling madvise for memory regions. To be able to use KSM for more workloads, KSM needs to have the ability to be enabled / disabled at the process / cgroup level. Use case 1: The madvise call is not available in the programming language. An example for this are programs with forked workloads using a garbage collected language without pointers. In such a language madvise cannot be made available. In addition the addresses of objects get moved around as they are garbage collected. KSM sharing needs to be enabled "from the outside" for these type of workloads. Use case 2: The same interpreter can also be used for workloads where KSM brings no benefit or even has overhead. We'd like to be able to enable KSM on a workload by workload basis. Use case 3: With the madvise call sharing opportunities are only enabled for the current process: it is a workload-local decision. A considerable number of sharing opportunities may exist across multiple workloads or jobs (if they are part of the same security domain). Only a higler level entity like a job scheduler or container can know for certain if its running one or more instances of a job. That job scheduler however doesn't have the necessary internal workload knowledge to make targeted madvise calls. Security concerns: In previous discussions security concerns have been brought up. The problem is that an individual workload does not have the knowledge about what else is running on a machine. Therefore it has to be very conservative in what memory areas can be shared or not. However, if the system is dedicated to running multiple jobs within the same security domain, its the job scheduler that has the knowledge that sharing can be safely enabled and is even desirable. Performance: Experiments with using UKSM have shown a capacity increase of around 20%. Here are the metrics from an instagram workload (taken from a machine with 64GB main memory): full_scans: 445 general_profit: 20158298048 max_page_sharing: 256 merge_across_nodes: 1 pages_shared: 129547 pages_sharing: 5119146 pages_to_scan: 4000 pages_unshared: 1760924 pages_volatile: 10761341 run: 1 sleep_millisecs: 20 stable_node_chains: 167 stable_node_chains_prune_millisecs: 2000 stable_node_dups: 2751 use_zero_pages: 0 zero_pages_sharing: 0 After the service is running for 30 minutes to an hour, 4 to 5 million shared pages are common for this workload when using KSM. Detailed changes: 1. New options for prctl system command This patch series adds two new options to the prctl system call. The first one allows to enable KSM at the process level and the second one to query the setting. The setting will be inherited by child processes. With the above setting, KSM can be enabled for the seed process of a cgroup and all processes in the cgroup will inherit the setting. 2. Changes to KSM processing When KSM is enabled at the process level, the KSM code will iterate over all the VMA's and enable KSM for the eligible VMA's. When forking a process that has KSM enabled, the setting will be inherited by the new child process. 3. Add general_profit metric The general_profit metric of KSM is specified in the documentation, but not calculated. This adds the general profit metric to /sys/kernel/debug/mm/ksm. 4. Add more metrics to ksm_stat This adds the process profit metric to /proc//ksm_stat. 5. Add more tests to ksm_tests and ksm_functional_tests This adds an option to specify the merge type to the ksm_tests. This allows to test madvise and prctl KSM. It also adds a two new tests to ksm_functional_tests: one to test the new prctl options and the other one is a fork test to verify that the KSM process setting is inherited by client processes. This patch (of 3): So far KSM can only be enabled by calling madvise for memory regions. To be able to use KSM for more workloads, KSM needs to have the ability to be enabled / disabled at the process / cgroup level. 1. New options for prctl system command This patch series adds two new options to the prctl system call. The first one allows to enable KSM at the process level and the second one to query the setting. The setting will be inherited by child processes. With the above setting, KSM can be enabled for the seed process of a cgroup and all processes in the cgroup will inherit the setting. 2. Changes to KSM processing When KSM is enabled at the process level, the KSM code will iterate over all the VMA's and enable KSM for the eligible VMA's. When forking a process that has KSM enabled, the setting will be inherited by the new child process. 1) Introduce new MMF_VM_MERGE_ANY flag This introduces the new flag MMF_VM_MERGE_ANY flag. When this flag is set, kernel samepage merging (ksm) gets enabled for all vma's of a process. 2) Setting VM_MERGEABLE on VMA creation When a VMA is created, if the MMF_VM_MERGE_ANY flag is set, the VM_MERGEABLE flag will be set for this VMA. 3) support disabling of ksm for a process This adds the ability to disable ksm for a process if ksm has been enabled for the process with prctl. 4) add new prctl option to get and set ksm for a process This adds two new options to the prctl system call - enable ksm for all vmas of a process (if the vmas support it). - query if ksm has been enabled for a process. 3. Disabling MMF_VM_MERGE_ANY for storage keys in s390 In the s390 architecture when storage keys are used, the MMF_VM_MERGE_ANY will be disabled. Link: https://lkml.kernel.org/r/20230418051342.1919757-1-shr@devkernel.io Link: https://lkml.kernel.org/r/20230418051342.1919757-2-shr@devkernel.io Signed-off-by: Stefan Roesch Acked-by: David Hildenbrand Cc: David Hildenbrand Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Cc: Bagas Sanjaya Signed-off-by: Andrew Morton --- kernel/sys.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'kernel/sys.c') diff --git a/kernel/sys.c b/kernel/sys.c index 26c1399e0654..72cdb16e2636 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -2687,6 +2688,32 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_SET_VMA: error = prctl_set_vma(arg2, arg3, arg4, arg5); break; +#ifdef CONFIG_KSM + case PR_SET_MEMORY_MERGE: + if (arg3 || arg4 || arg5) + return -EINVAL; + if (mmap_write_lock_killable(me->mm)) + return -EINTR; + + if (arg2) { + error = ksm_enable_merge_any(me->mm); + } else { + /* + * TODO: we might want disable KSM on all VMAs and + * trigger unsharing to completely disable KSM. + */ + clear_bit(MMF_VM_MERGE_ANY, &me->mm->flags); + error = 0; + } + mmap_write_unlock(me->mm); + break; + case PR_GET_MEMORY_MERGE: + if (arg2 || arg3 || arg4 || arg5) + return -EINVAL; + + error = !!test_bit(MMF_VM_MERGE_ANY, &me->mm->flags); + break; +#endif default: error = -EINVAL; break; -- cgit From 24139c07f413ef4b555482c758343d71392a19bc Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Sat, 22 Apr 2023 22:54:18 +0200 Subject: mm/ksm: unmerge and clear VM_MERGEABLE when setting PR_SET_MEMORY_MERGE=0 Patch series "mm/ksm: improve PR_SET_MEMORY_MERGE=0 handling and cleanup disabling KSM", v2. (1) Make PR_SET_MEMORY_MERGE=0 unmerge pages like setting MADV_UNMERGEABLE does, (2) add a selftest for it and (3) factor out disabling of KSM from s390/gmap code. This patch (of 3): Let's unmerge any KSM pages when setting PR_SET_MEMORY_MERGE=0, and clear the VM_MERGEABLE flag from all VMAs -- just like KSM would. Of course, only do that if we previously set PR_SET_MEMORY_MERGE=1. Link: https://lkml.kernel.org/r/20230422205420.30372-1-david@redhat.com Link: https://lkml.kernel.org/r/20230422205420.30372-2-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Stefan Roesch Cc: Christian Borntraeger Cc: Claudio Imbrenda Cc: Heiko Carstens Cc: Janosch Frank Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Cc: Shuah Khan Cc: Sven Schnelle Cc: Vasily Gorbik Signed-off-by: Andrew Morton --- kernel/sys.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'kernel/sys.c') diff --git a/kernel/sys.c b/kernel/sys.c index 72cdb16e2636..339fee3eff6a 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2695,16 +2695,10 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, if (mmap_write_lock_killable(me->mm)) return -EINTR; - if (arg2) { + if (arg2) error = ksm_enable_merge_any(me->mm); - } else { - /* - * TODO: we might want disable KSM on all VMAs and - * trigger unsharing to completely disable KSM. - */ - clear_bit(MMF_VM_MERGE_ANY, &me->mm->flags); - error = 0; - } + else + error = ksm_disable_merge_any(me->mm); mmap_write_unlock(me->mm); break; case PR_GET_MEMORY_MERGE: -- cgit