From: "T.J. Mercier" tjmercier@google.com

When a buffer is exported to userspace, use memcg to attribute the buffer to the allocating cgroup until all buffer references are released.

Unlike the dmabuf sysfs stats implementation, this memcg accounting avoids contention over the kernfs_rwsem incurred when creating or removing nodes.

Signed-off-by: T.J. Mercier tjmercier@google.com Signed-off-by: Albert Esteve aesteve@redhat.com --- Documentation/admin-guide/cgroup-v2.rst | 4 ++++ drivers/dma-buf/dma-buf.c | 13 ++++++++++++ include/linux/dma-buf.h | 4 ++++ include/linux/memcontrol.h | 37 +++++++++++++++++++++++++++++++++ mm/memcontrol.c | 19 +++++++++++++++++ 5 files changed, 77 insertions(+)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 6efd0095ed995..8bdbc2e866430 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1635,6 +1635,10 @@ The following nested keys are defined. Amount of memory used for storing in-kernel data structures.

+ dmabuf (npn) + Amount of memory used for exported DMA buffers allocated by the cgroup. + Stays with the allocating cgroup regardless of how the buffer is shared. + workingset_refault_anon Number of refaults of previously evicted anonymous pages.

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 71f37544a5c61..ce02377f48908 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -14,6 +14,7 @@ #include <linux/fs.h> #include <linux/slab.h> #include <linux/dma-buf.h> +#include <linux/memcontrol.h> #include <linux/dma-fence.h> #include <linux/dma-fence-unwrap.h> #include <linux/anon_inodes.h> @@ -180,6 +181,9 @@ static void dma_buf_release(struct dentry *dentry) */ BUG_ON(dmabuf->cb_in.active || dmabuf->cb_out.active);

+ mem_cgroup_uncharge_dmabuf(dmabuf->memcg, PAGE_ALIGN(dmabuf->size) / PAGE_SIZE); + mem_cgroup_put(dmabuf->memcg); + dmabuf->ops->release(dmabuf);

if (dmabuf->resv == (struct dma_resv *)&dmabuf[1]) @@ -760,6 +764,13 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) dmabuf->resv = resv; }

+ dmabuf->memcg = get_mem_cgroup_from_mm(current->mm); + if (!mem_cgroup_charge_dmabuf(dmabuf->memcg, PAGE_ALIGN(dmabuf->size) / PAGE_SIZE, + GFP_KERNEL)) { + ret = -ENOMEM; + goto err_memcg; + } + file->private_data = dmabuf; file->f_path.dentry->d_fsdata = dmabuf; dmabuf->file = file; @@ -770,6 +781,8 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)

return dmabuf;

+err_memcg: + mem_cgroup_put(dmabuf->memcg); err_file: fput(file); err_module: diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index d1203da56fc5f..d9f1ccb51c60e 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -27,6 +27,7 @@ struct device; struct dma_buf; struct dma_buf_attachment; +struct mem_cgroup;

/** * struct dma_buf_ops - operations possible on struct dma_buf @@ -429,6 +430,9 @@ struct dma_buf {

__poll_t active; } cb_in, cb_out; + + /** @memcg: the cgroup to which this buffer is currently attributed */ + struct mem_cgroup *memcg; };

/** diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index dc3fa687759b4..10068a833ad9e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -39,6 +39,7 @@ enum memcg_stat_item { MEMCG_ZSWAP_B, MEMCG_ZSWAPPED, MEMCG_ZSWAP_INCOMP, + MEMCG_DMABUF, MEMCG_NR_STAT, };

@@ -649,6 +650,24 @@ int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp); int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry);

+/** + * mem_cgroup_charge_dmabuf - Charge dma-buf memory to a cgroup and update stat counter + * @memcg: memcg to charge + * @nr_pages: number of pages to charge + * @gfp_mask: reclaim mode + * + * Charges @nr_pages to @memcg. Returns %true if the charge fit within + * @memcg's configured limit, %false if it doesn't. + */ +bool __mem_cgroup_charge_dmabuf(struct mem_cgroup *memcg, unsigned int nr_pages, gfp_t gfp_mask); +static inline bool mem_cgroup_charge_dmabuf(struct mem_cgroup *memcg, unsigned int nr_pages, + gfp_t gfp_mask) +{ + if (mem_cgroup_disabled()) + return true; + return __mem_cgroup_charge_dmabuf(memcg, nr_pages, gfp_mask); +} + void __mem_cgroup_uncharge(struct folio *folio);

/** @@ -664,6 +683,14 @@ static inline void mem_cgroup_uncharge(struct folio *folio) __mem_cgroup_uncharge(folio); }

+void __mem_cgroup_uncharge_dmabuf(struct mem_cgroup *memcg, unsigned int nr_pages); +static inline void mem_cgroup_uncharge_dmabuf(struct mem_cgroup *memcg, unsigned int nr_pages) +{ + if (mem_cgroup_disabled()) + return; + __mem_cgroup_uncharge_dmabuf(memcg, nr_pages); +} + void __mem_cgroup_uncharge_folios(struct folio_batch *folios); static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { @@ -1142,10 +1169,20 @@ static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, return 0; }

+static inline bool mem_cgroup_charge_dmabuf(struct mem_cgroup *memcg, unsigned int nr_pages, + gfp_t gfp_mask) +{ + return true; +} + static inline void mem_cgroup_uncharge(struct folio *folio) { }

+static inline void mem_cgroup_uncharge_dmabuf(struct mem_cgroup *memcg, unsigned int nr_pages) +{ +} + static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c03d4787d4668..15cee13d3ccd6 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -433,6 +433,7 @@ static const unsigned int memcg_stat_items[] = { MEMCG_ZSWAP_B, MEMCG_ZSWAPPED, MEMCG_ZSWAP_INCOMP, + MEMCG_DMABUF, };

#define NR_MEMCG_NODE_STAT_ITEMS ARRAY_SIZE(memcg_node_stat_items) @@ -1580,6 +1581,7 @@ static const struct memory_stat memory_stats[] = { #ifdef CONFIG_HUGETLB_PAGE { "hugetlb", NR_HUGETLB }, #endif + { "dmabuf", MEMCG_DMABUF },

/* The memory events */ { "workingset_refault_anon", WORKINGSET_REFAULT_ANON }, @@ -5399,6 +5401,23 @@ void mem_cgroup_flush_workqueue(void) flush_workqueue(memcg_wq); }

+bool __mem_cgroup_charge_dmabuf(struct mem_cgroup *memcg, unsigned int nr_pages, gfp_t gfp_mask) +{ + if (try_charge(memcg, gfp_mask, nr_pages) == 0) { + mod_memcg_state(memcg, MEMCG_DMABUF, nr_pages); + return true; + } + + return false; +} + +void __mem_cgroup_uncharge_dmabuf(struct mem_cgroup *memcg, unsigned int nr_pages) +{ + mod_memcg_state(memcg, MEMCG_DMABUF, -nr_pages); + if (!mem_cgroup_is_root(memcg)) + refill_stock(memcg, nr_pages); +} + static int __init cgroup_memory(char *s) { char *token;

DMA_HEAP_IOCTL_ALLOC accepts a charge_pid_fd field that, when set, causes the allocation to be charged to an arbitrary process's cgroup rather than the caller's.

Without an access-control point, any process that holds a handle to a dma-heap device node can charge unlimited memory to any other process's cgroup, potentially exhausting that cgroup's limit and triggering OOM kills independent of the victim's own activity or privileges.

Add security_dma_heap_alloc(), called in dma_heap_ioctl_allocate() when charge_pid_fd refers to another process. The hook receives the credentials of the allocating process (from) and the credentials of the process whose cgroup will be charged (to), giving security modules a controlled enforcement point for cross-cgroup dma-buf attribution policy.

When CONFIG_SECURITY is not set the hook compiles to an inline returning 0, adding no overhead to the fast path.

Signed-off-by: Albert Esteve aesteve@redhat.com --- drivers/dma-buf/dma-heap.c | 12 +++++++++++- include/linux/lsm_hook_defs.h | 1 + include/linux/security.h | 7 +++++++ security/security.c | 16 ++++++++++++++++ 4 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index ff6e259afcdc0..e8ffb1031955e 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -18,6 +18,7 @@ #include <linux/list.h> #include <linux/nospec.h> #include <linux/pidfd.h> +#include <linux/security.h> #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/xarray.h> @@ -122,12 +123,13 @@ static int dma_heap_open(struct inode *inode, struct file *file)

static long dma_heap_ioctl_allocate(struct file *file, void *data) { + const struct cred *tcred; struct dma_heap_allocation_data *heap_allocation = data; struct dma_heap *heap = file->private_data; struct mem_cgroup *memcg = NULL; struct task_struct *task; unsigned int pidfd_flags; - int fd; + int fd, ret;

if (heap_allocation->fd) return -EINVAL; @@ -143,6 +145,14 @@ static long dma_heap_ioctl_allocate(struct file *file, void *data) if (IS_ERR(task)) return PTR_ERR(task);

+ tcred = get_task_cred(task); + ret = security_dma_heap_alloc(current_cred(), tcred); + put_cred(tcred); + if (ret) { + put_task_struct(task); + return ret; + } + memcg = get_mem_cgroup_from_mm(task->mm); put_task_struct(task); } diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 2b8dfb35caed3..6a91656f97e1e 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -43,6 +43,7 @@ LSM_HOOK(int, 0, capset, struct cred *new, const struct cred *old, const kernel_cap_t *permitted) LSM_HOOK(int, 0, capable, const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) +LSM_HOOK(int, 0, dma_heap_alloc, const struct cred *from, const struct cred *to) LSM_HOOK(int, 0, quotactl, int cmds, int type, int id, const struct super_block *sb) LSM_HOOK(int, 0, quota_on, struct dentry *dentry) LSM_HOOK(int, 0, syslog, int type) diff --git a/include/linux/security.h b/include/linux/security.h index 41d7367cf4036..f1dad1eabe754 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -350,6 +350,7 @@ int security_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts); +int security_dma_heap_alloc(const struct cred *from, const struct cred *to); int security_quotactl(int cmds, int type, int id, const struct super_block *sb); int security_quota_on(struct dentry *dentry); int security_syslog(int type); @@ -701,6 +702,12 @@ static inline int security_capable(const struct cred *cred, return cap_capable(cred, ns, cap, opts); }

+static inline int security_dma_heap_alloc(const struct cred *from, + const struct cred *to) +{ + return 0; +} + static inline int security_quotactl(int cmds, int type, int id, const struct super_block *sb) { diff --git a/security/security.c b/security/security.c index 4e999f0236516..4adacef73c507 100644 --- a/security/security.c +++ b/security/security.c @@ -660,6 +660,22 @@ int security_capable(const struct cred *cred, return call_int_hook(capable, cred, ns, cap, opts); }

+/** + * security_dma_heap_alloc() - Check if cross-cgroup dma-heap charging is allowed + * @from: credentials of the allocating process + * @to: credentials of the process to charge + * + * Check whether the process with credentials @from is allowed to allocate + * dma-heap memory and charge it to the cgroup of the process with credentials + * @to. + * + * Return: Returns 0 if permission is granted. + */ +int security_dma_heap_alloc(const struct cred *from, const struct cred *to) +{ + return call_int_hook(dma_heap_alloc, from, to); +} + /** * security_quotactl() - Check if a quotactl() syscall is allowed for this fs * @cmds: commands

Add tests for the new charge_pid_fd field in struct dma_heap_allocation_data.

When the charge_pid_fd feature is absent (unpatched kernel), the probe in pidfd_alloc_supported() detects this and the tests are skipped gracefully.

Add vmtest.sh similar to other subsystem suites, to orchestrate building the selftests (optionally with a freshly compiled kernel) inside a virtme-ng VM, so the tests can be run without modifying the host system. Add a config fragment with required Kconfig symbols.

Also add test_memcg_dmabuf() to the existing test_memcontrol suite to verify end-to-end cross-cgroup accounting: a parent process opens a pidfd for a child in a separate cgroup, allocates a dma-buf via DMA_HEAP_IOCTL_ALLOC with that pidfd, and asserts that memory.stat dmabuf in the child's cgroup reflects the allocation. If the dmabuf key is missing (unpatched kernel) or /dev/dma_heap/system is absent, the test is skipped.

Assisted-by: Claude:claude-sonnet-4-6 Cursor Signed-off-by: Albert Esteve aesteve@redhat.com --- tools/testing/selftests/cgroup/Makefile | 2 +- tools/testing/selftests/cgroup/test_memcontrol.c | 143 +++++++++++++- tools/testing/selftests/dmabuf-heaps/config | 1 + tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c | 126 ++++++++++++- tools/testing/selftests/dmabuf-heaps/vmtest.sh | 205 +++++++++++++++++++++ 5 files changed, 473 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile index e01584c2189ac..9edfc9f1de5c4 100644 --- a/tools/testing/selftests/cgroup/Makefile +++ b/tools/testing/selftests/cgroup/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -Wall -pthread +CFLAGS += -Wall -pthread $(KHDR_INCLUDES)

all: ${HELPER_PROGS}

diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index b43da9bc20c49..b6a228407530f 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -19,9 +19,17 @@ #include <errno.h> #include <sys/mman.h>

+#include <linux/dma-heap.h> +#include <signal.h> +#include <sys/ioctl.h> + +#include "../pidfd/pidfd.h" #include "kselftest.h" #include "cgroup_util.h"

+#define DMA_HEAP_SYSTEM "/dev/dma_heap/system" +#define ONE_MEG (1024 * 1024) + #define MEMCG_SOCKSTAT_WAIT_RETRIES 30

static bool has_localevents; @@ -1762,6 +1770,125 @@ static int test_memcg_inotify_delete_dir(const char *root) return ret; }

+static int memcg_dmabuf_child(const char *cgroup, void *arg) +{ + pause(); + return 0; +} + +/* + * This test allocates a dma-buf via DMA_HEAP_IOCTL_ALLOC with a pidfd + * pointing to a child process in a separate cgroup, then checks that + * memory.stat[dmabuf] in the child's cgroup rises by the allocation size + * and returns to zero after the buffer fd is closed. + */ +static int test_memcg_dmabuf(const char *root) +{ + char *parent = NULL, *child_cg = NULL; + int ret = KSFT_FAIL; + int heap_fd = -1, dmabuf_fd = -1, pidfd = -1; + pid_t child_pid; + int child_status; + long dmabuf_stat; + struct dma_heap_allocation_data alloc = { + .len = ONE_MEG, + .fd_flags = O_RDWR | O_CLOEXEC, + }; + + if (access(DMA_HEAP_SYSTEM, R_OK | W_OK)) { + ret = KSFT_SKIP; + goto cleanup; + } + + parent = cg_name(root, "dmabuf_memcg_test"); + if (!parent) + goto cleanup; + + if (cg_create(parent)) + goto cleanup_parent; + + if (cg_write(parent, "cgroup.subtree_control", "+memory")) + goto cleanup_parent; + + child_cg = cg_name(parent, "child"); + if (!child_cg) + goto cleanup_parent; + + if (cg_create(child_cg)) + goto cleanup_parent; + + child_pid = cg_run_nowait(child_cg, memcg_dmabuf_child, NULL); + if (child_pid < 0) + goto cleanup_child; + + if (cg_wait_for_proc_count(child_cg, 1)) + goto cleanup_kill; + + pidfd = sys_pidfd_open(child_pid, 0); + if (pidfd < 0) { + ret = KSFT_SKIP; + goto cleanup_kill; + } + + heap_fd = open(DMA_HEAP_SYSTEM, O_RDWR); + if (heap_fd < 0) { + ret = KSFT_SKIP; + goto cleanup_pidfd; + } + + alloc.charge_pid_fd = (__u32)pidfd; + if (ioctl(heap_fd, DMA_HEAP_IOCTL_ALLOC, &alloc) < 0) + goto cleanup_heap; + dmabuf_fd = (int)alloc.fd; + + dmabuf_stat = cg_read_key_long(child_cg, "memory.stat", "dmabuf "); + if (dmabuf_stat == -1) { + ret = KSFT_SKIP; + goto cleanup_dmabuf; + } + if (dmabuf_stat != ONE_MEG) + dmabuf_stat = cg_read_key_long_poll(child_cg, "memory.stat", + "dmabuf ", ONE_MEG, + 15, 200000); + if (dmabuf_stat != ONE_MEG) { + fprintf(stderr, "Expected dmabuf stat %d, got %ld\n", + ONE_MEG, dmabuf_stat); + goto cleanup_dmabuf; + } + + close(dmabuf_fd); + dmabuf_fd = -1; + + dmabuf_stat = cg_read_key_long_poll(child_cg, "memory.stat", + "dmabuf ", 0, 15, 200000); + if (dmabuf_stat != 0) { + fprintf(stderr, "Expected dmabuf stat 0 after close, got %ld\n", + dmabuf_stat); + goto cleanup_heap; + } + + ret = KSFT_PASS; + +cleanup_dmabuf: + if (dmabuf_fd >= 0) + close(dmabuf_fd); +cleanup_heap: + close(heap_fd); +cleanup_pidfd: + close(pidfd); +cleanup_kill: + kill(child_pid, SIGTERM); + waitpid(child_pid, &child_status, 0); +cleanup_child: + cg_destroy(child_cg); + free(child_cg); +cleanup_parent: + cg_destroy(parent); + free(parent); +cleanup: + return ret; +} + #define T(x) { x, #x } struct memcg_test { int (*fn)(const char *root); @@ -1783,16 +1910,26 @@ struct memcg_test { T(test_memcg_oom_group_score_events), T(test_memcg_inotify_delete_file), T(test_memcg_inotify_delete_dir), + T(test_memcg_dmabuf), }; #undef T

int main(int argc, char **argv) { char root[PATH_MAX]; - int i, proc_status; + int i, proc_status, plan; + const char *filter = NULL; + + if (argc > 1) + filter = argv[1]; + + plan = 0; + for (i = 0; i < ARRAY_SIZE(tests); i++) + if (!filter || !strcmp(tests[i].name, filter)) + plan++;

ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); + ksft_set_plan(plan); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n");

@@ -1818,6 +1955,8 @@ int main(int argc, char **argv) has_localevents = proc_status;

for (i = 0; i < ARRAY_SIZE(tests); i++) { + if (filter && strcmp(tests[i].name, filter)) + continue; switch (tests[i].fn(root)) { case KSFT_PASS: ksft_test_result_pass("%s\n", tests[i].name); diff --git a/tools/testing/selftests/dmabuf-heaps/config b/tools/testing/selftests/dmabuf-heaps/config index be091f1cdfa04..94c8f33b71a28 100644 --- a/tools/testing/selftests/dmabuf-heaps/config +++ b/tools/testing/selftests/dmabuf-heaps/config @@ -1,3 +1,4 @@ +CONFIG_MEMCG=y CONFIG_DMABUF_HEAPS=y CONFIG_DMABUF_HEAPS_SYSTEM=y CONFIG_DRM_VGEM=y diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c index fc9694fc4e89e..904332b17698a 100644 --- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c +++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c @@ -3,6 +3,7 @@ #include <dirent.h> #include <errno.h> #include <fcntl.h> +#include <signal.h> #include <stdio.h> #include <stdlib.h> #include <stdint.h> @@ -10,11 +11,14 @@ #include <unistd.h> #include <sys/ioctl.h> #include <sys/mman.h> +#include <sys/syscall.h> #include <sys/types.h> +#include <sys/wait.h>

#include <linux/dma-buf.h> #include <linux/dma-heap.h> #include <drm/drm.h> +#include "../pidfd/pidfd.h" #include "kselftest.h"

#define DEVPATH "/dev/dma_heap" @@ -320,6 +324,8 @@ static int dmabuf_heap_alloc_newer(int fd, size_t len, unsigned int flags, __u32 fd; __u32 fd_flags; __u64 heap_flags; + __u32 charge_pid_fd; + __u32 __padding; __u64 garbage1; __u64 garbage2; __u64 garbage3; @@ -328,6 +334,8 @@ static int dmabuf_heap_alloc_newer(int fd, size_t len, unsigned int flags, .fd = 0, .fd_flags = O_RDWR | O_CLOEXEC, .heap_flags = flags, + .charge_pid_fd = 0, + .__padding = 0, .garbage1 = 0xffffffff, .garbage2 = 0x88888888, .garbage3 = 0x11111111, @@ -390,6 +398,120 @@ static void test_alloc_errors(char *heap_name) close(heap_fd); }

+static int dmabuf_heap_alloc_pidfd(int fd, size_t len, unsigned int heap_flags, + unsigned int charge_pid_fd, int *dmabuf_fd) +{ + struct dma_heap_allocation_data data = { + .len = len, + .fd = 0, + .fd_flags = O_RDWR | O_CLOEXEC, + .heap_flags = heap_flags, + .charge_pid_fd = charge_pid_fd, + }; + int ret; + + if (!dmabuf_fd) + return -EINVAL; + + ret = ioctl(fd, DMA_HEAP_IOCTL_ALLOC, &data); + if (ret < 0) + return ret; + *dmabuf_fd = (int)data.fd; + return ret; +} + +/* + * Probe whether the kernel honours charge_pid_fd in DMA_HEAP_IOCTL_ALLOC. + */ +static bool pidfd_alloc_supported(int heap_fd) +{ + int devnull_fd, dmabuf_fd = -1, ret; + + devnull_fd = open("/dev/null", O_RDONLY); + if (devnull_fd < 0) + return false; + + ret = dmabuf_heap_alloc_pidfd(heap_fd, ONE_MEG, 0, devnull_fd, &dmabuf_fd); + if (dmabuf_fd >= 0) { + close(dmabuf_fd); + dmabuf_fd = -1; + } + close(devnull_fd); + return ret < 0; +} + +/* + * Test: allocate charging the calling process's own cgroup via a self pidfd. + */ +static void test_alloc_pidfd_self(char *heap_name) +{ + int heap_fd = -1, pidfd = -1, dmabuf_fd = -1, ret; + + heap_fd = dmabuf_heap_open(heap_name); + + if (!pidfd_alloc_supported(heap_fd)) { + ksft_test_result_skip("charge_pid_fd not supported by this kernel\n"); + goto out; + } + + pidfd = sys_pidfd_open(getpid(), 0); + if (pidfd < 0) { + ksft_test_result_skip("pidfd_open not available\n"); + goto out; + } + + ret = dmabuf_heap_alloc_pidfd(heap_fd, ONE_MEG, 0, pidfd, &dmabuf_fd); + ksft_test_result(!ret, "Allocation with self pidfd %d\n", ret); + if (dmabuf_fd >= 0) + close(dmabuf_fd); + close(pidfd); +out: + close(heap_fd); +} + +/* + * Test: allocate charging a child process's cgroup via a child pidfd. + */ +static void test_alloc_pidfd_child(char *heap_name) +{ + int heap_fd = -1, pidfd = -1, dmabuf_fd = -1; + pid_t child_pid; + int status, ret; + + heap_fd = dmabuf_heap_open(heap_name); + + if (!pidfd_alloc_supported(heap_fd)) { + ksft_test_result_skip("charge_pid_fd not supported by this kernel\n"); + goto out; + } + + child_pid = fork(); + if (child_pid == 0) { + pause(); + _exit(0); + } + if (child_pid < 0) + ksft_exit_fail_msg("fork failed: %s\n", strerror(errno)); + + pidfd = sys_pidfd_open(child_pid, 0); + if (pidfd < 0) { + kill(child_pid, SIGTERM); + waitpid(child_pid, &status, 0); + ksft_test_result_skip("pidfd_open for child failed\n"); + goto out; + } + + ret = dmabuf_heap_alloc_pidfd(heap_fd, ONE_MEG, 0, pidfd, &dmabuf_fd); + ksft_test_result(!ret, "Allocation with child pidfd %d\n", ret); + if (dmabuf_fd >= 0) + close(dmabuf_fd); + close(pidfd); + kill(child_pid, SIGTERM); + waitpid(child_pid, &status, 0); +out: + close(heap_fd); +} + static int numer_of_heaps(void) { DIR *d = opendir(DEVPATH); @@ -420,7 +542,7 @@ int main(void) return KSFT_SKIP; }

- ksft_set_plan(11 * numer_of_heaps()); + ksft_set_plan(13 * numer_of_heaps());

while ((dir = readdir(d))) { if (!strncmp(dir->d_name, ".", 2)) @@ -435,6 +557,8 @@ int main(void) test_alloc_zeroed(dir->d_name, ONE_MEG); test_alloc_compat(dir->d_name); test_alloc_errors(dir->d_name); + test_alloc_pidfd_self(dir->d_name); + test_alloc_pidfd_child(dir->d_name); } closedir(d);

diff --git a/tools/testing/selftests/dmabuf-heaps/vmtest.sh b/tools/testing/selftests/dmabuf-heaps/vmtest.sh new file mode 100755 index 0000000000000..6f1a878384127 --- /dev/null +++ b/tools/testing/selftests/dmabuf-heaps/vmtest.sh @@ -0,0 +1,205 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2026 Red Hat +# +# Dependencies: +# * virtme-ng +# * qemu (used by virtme-ng) + +readonly SCRIPT_DIR="$(cd -P -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)" +readonly KERNEL_CHECKOUT=$(realpath "${SCRIPT_DIR}"/../../../../) +readonly CGROUP_DIR="${KERNEL_CHECKOUT}/tools/testing/selftests/cgroup" + +source "${SCRIPT_DIR}"/../kselftest/ktap_helpers.sh + +readonly DMABUF_HEAP_TEST="${SCRIPT_DIR}"/dmabuf-heap +readonly MEMCONTROL_TEST="${CGROUP_DIR}"/test_memcontrol +readonly TMP_DIR=$(mktemp -d /tmp/dmabuf-vmtest.XXXXXXXX) + +VERBOSE=false +BUILD=false +BUILD_HOST="" +BUILD_HOST_PODMAN_CONTAINER_NAME="" + +usage() { + echo + echo "$0 [OPTIONS]" + echo + echo "Options" + echo " -b: build the kernel from the current source tree and use it for the VM" + echo " -H: hostname for remote build host (used with -b)" + echo " -p: podman container name for remote build host (used with -b)" + echo " Example: -H beefyserver -p vng" + + echo " -v: enable verbose vng/qemu output" + echo + + exit 1 +} + +die() { + echo "$*" >&2 + exit "${KSFT_FAIL}" +} + +cleanup() { + rm -rf "${TMP_DIR}" +} + +check_deps() { + for dep in vng make; do + if [[ ! -x $(command -v "${dep}") ]]; then + echo -e "skip: dependency ${dep} not found!\n" + exit "${KSFT_SKIP}" + fi + done + + if [[ ! -x "${DMABUF_HEAP_TEST}" ]]; then + printf "skip: %s not found!" "${DMABUF_HEAP_TEST}" + printf " Please build the kselftest dmabuf-heaps target (or use -b).\n" + exit "${KSFT_SKIP}" + fi + + if [[ ! -x "${MEMCONTROL_TEST}" ]]; then + printf "skip: %s not found!" "${MEMCONTROL_TEST}" + printf " Please build the kselftest cgroup target (or use -b).\n" + exit "${KSFT_SKIP}" + fi +} + +check_vng() { + local tested_versions=("1.36" "1.37") + local version + local ok=0 + + version="$(vng --version)" + for tv in "${tested_versions[@]}"; do + if [[ "${version}" == *"${tv}"* ]]; then + ok=1 + break + fi + done + + if [[ "${ok}" -eq 0 ]]; then + printf "warning: vng version '%s' has not been tested and may " "${version}" >&2 + printf "not function properly.\n\tThe following versions have been tested: " >&2 + echo "${tested_versions[@]}" >&2 + fi +} + +build_selftests() { + make -C "${KERNEL_CHECKOUT}" headers_install \ + INSTALL_HDR_PATH="${TMP_DIR}/usr" -j"$(nproc)" + + local khdr="-isystem ${TMP_DIR}/usr/include" + + if ! make -C "${SCRIPT_DIR}" KHDR_INCLUDES="${khdr}" -j"$(nproc)"; then + die "failed to build dmabuf-heaps selftests" + fi + + if ! make -C "${CGROUP_DIR}" KHDR_INCLUDES="${khdr}" \ + "${MEMCONTROL_TEST}" -j"$(nproc)"; then + die "failed to build cgroup/test_memcontrol selftest" + fi +} + +handle_build() { + if ! ${BUILD}; then + return + fi + + if [[ ! -d "${KERNEL_CHECKOUT}" ]]; then + echo "-b requires vmtest.sh called from the kernel source tree" >&2 + exit 1 + fi + + pushd "${KERNEL_CHECKOUT}" &>/dev/null + + if ! vng --kconfig --config "${SCRIPT_DIR}/config"; then + die "failed to generate .config for kernel source tree (${KERNEL_CHECKOUT})" + fi + + local vng_args=("-v" "--config" "${SCRIPT_DIR}/config" "--build") + + if [[ -n "${BUILD_HOST}" ]]; then + vng_args+=("--build-host" "${BUILD_HOST}") + fi + + if [[ -n "${BUILD_HOST_PODMAN_CONTAINER_NAME}" ]]; then + vng_args+=("--build-host-exec-prefix" \ + "podman exec -ti ${BUILD_HOST_PODMAN_CONTAINER_NAME}") + fi + + if ! vng "${vng_args[@]}"; then + die "failed to build kernel from source tree (${KERNEL_CHECKOUT})" + fi + + build_selftests + + popd &>/dev/null +} + +make_runner() { + # virtme-ng shares the host filesystem, so TMP_DIR is accessible + # inside the VM at the same absolute path. + cat > "${TMP_DIR}/run_tests.sh" <<-EOF + #!/bin/sh + set -u + PASS=0; FAIL=0; SKIP=0; N=0 + + run() { + name="$1"; shift + N=$((N+1)) + "$@"; rc=$? + if [ $rc -eq 0 ]; then echo "ok $N $name"; PASS=$((PASS+1)) + elif [ $rc -eq 4 ]; then echo "ok $N $name # SKIP"; SKIP=$((SKIP+1)) + else echo "not ok $N $name"; FAIL=$((FAIL+1)) + fi + } + + run "dmabuf-heap charge_pid_fd ioctl" ${DMABUF_HEAP_TEST} + run "memcontrol dma-buf memcg" ${MEMCONTROL_TEST} test_memcg_dmabuf + echo "# PASS=$PASS SKIP=$SKIP FAIL=$FAIL" + [ $FAIL -eq 0 ] + EOF + chmod +x "${TMP_DIR}/run_tests.sh" +} + +run_vm() { + local verbose_opt="" + local kernel_opt="" + + ${VERBOSE} && verbose_opt="--verbose" + + # If we are running from within the kernel source tree, use the kernel + # source tree as the kernel to boot, otherwise use the running kernel. + if [[ "$(realpath "$(pwd)")" == "${KERNEL_CHECKOUT}"* ]]; then + kernel_opt="${KERNEL_CHECKOUT}" + fi + + vng --run ${kernel_opt} ${verbose_opt} --user root --memory 512M \ + --exec "${TMP_DIR}/run_tests.sh" +} + +while getopts :hvbH:p: o +do + case $o in + v) VERBOSE=true;; + b) BUILD=true;; + H) BUILD_HOST=$OPTARG;; + p) BUILD_HOST_PODMAN_CONTAINER_NAME=$OPTARG;; + h|*) usage;; + esac +done +shift $((OPTIND-1)) + +trap cleanup EXIT + +check_vng +handle_build +check_deps +make_runner + +echo "Booting VM and running tests..." +run_vm