5.12.11-rc1 review

From: Dai Ngo <[email protected]>

commit f8849e206ef52b584cd9227255f4724f0cc900bb upstream.

Currently if __nfs4_proc_set_acl fails with NFS4ERR_BADOWNER it re-enables the idmapper by clearing NFS_CAP_UIDGID_NOMAP before retrying again. The NFS_CAP_UIDGID_NOMAP remains cleared even if the retry fails. This causes problem for subsequent setattr requests for v4 server that does not have idmapping configured.

This patch modifies nfs4_proc_set_acl to detect NFS4ERR_BADOWNER and NFS4ERR_BADNAME and skips the retry, since the kernel isn't involved in encoding the ACEs, and return -EINVAL.

Steps to reproduce the problem:

 # mount -o vers=4.1,sec=sys server:/export/test /tmp/mnt
 # touch /tmp/mnt/file1
 # chown 99 /tmp/mnt/file1
 # nfs4_setfacl -a A::[email protected]:wrtncy /tmp/mnt/file1
 Failed setxattr operation: Invalid argument
 # chown 99 /tmp/mnt/file1
 chown: changing ownership of ‘/tmp/mnt/file1’: Invalid argument
 # umount /tmp/mnt
 # mount -o vers=4.1,sec=sys server:/export/test /tmp/mnt
 # chown 99 /tmp/mnt/file1
 #

v2: detect NFS4ERR_BADOWNER and NFS4ERR_BADNAME and skip retry
in nfs4_proc_set_acl.

---
 fs/nfs/nfs4proc.c |    8 ++++++++
 1 file changed, 8 insertions(+)

@@ -5944,6 +5944,14 @@ static int nfs4_proc_set_acl(struct inod
 	do {
 		err = __nfs4_proc_set_acl(inode, buf, buflen);
 		trace_nfs4_set_acl(inode, err);
+		if (err == -NFS4ERR_BADOWNER || err == -NFS4ERR_BADNAME) {
+			/*
+			 * no need to retry since the kernel
+			 * isn't involved in encoding the ACEs.
+			 */
+			err = -EINVAL;
+			break;
+		}
 		err = nfs4_handle_exception(NFS_SERVER(inode), err,
 				&exception);
 	} while (exception.retry);

From: Ming Lei <[email protected]>

commit 66a834d092930cf41d809c0e989b13cd6f9ca006 upstream.

After device is initialized via device_initialize(), or its name is set via dev_set_name(), the device has to be freed via put_device(). Otherwise device name will be leaked because it is allocated dynamically in dev_set_name().

Fix the leak by replacing kfree() with put_device(). Since scsi_host_dev_release() properly handles IDA and kthread removal, remove special-casing these from the error handling as well.

---
 drivers/scsi/hosts.c |   23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

@@ -392,8 +392,10 @@ struct Scsi_Host *scsi_host_alloc(struct
 	mutex_init(&shost->scan_mutex);
 
 	index = ida_simple_get(&host_index_ida, 0, 0, GFP_KERNEL);
-	if (index < 0)
-		goto fail_kfree;
+	if (index < 0) {
+		kfree(shost);
+		return NULL;
+	}
 	shost->host_no = index;
 
 	shost->dma_channel = 0xff;

@@ -486,7 +488,7 @@ struct Scsi_Host *scsi_host_alloc(struct
 		shost_printk(KERN_WARNING, shost,
 			"error handler thread failed to spawn, error = %ld\n",
 			PTR_ERR(shost->ehandler));
-		goto fail_index_remove;
+		goto fail;
 	}
 
 	shost->tmf_work_q = alloc_workqueue("scsi_tmf_%d",

@@ -495,17 +497,18 @@ struct Scsi_Host *scsi_host_alloc(struct
 	if (!shost->tmf_work_q) {
 		shost_printk(KERN_WARNING, shost,
 			     "failed to create tmf workq\n");
-		goto fail_kthread;
+		goto fail;
 	}
 	scsi_proc_hostdir_add(shost->hostt);
 	return shost;
+ fail:
+	/*
+	 * Host state is still SHOST_CREATED and that is enough to release
+	 * ->shost_gendev. scsi_host_dev_release() will free
+	 * dev_name(&shost->shost_dev).
+	 */
+	put_device(&shost->shost_gendev);
 
- fail_kthread:
-	kthread_stop(shost->ehandler);
- fail_index_remove:
-	ida_simple_remove(&host_index_ida, shost->host_no);
- fail_kfree:
-	kfree(shost);
 	return NULL;
 }
 EXPORT_SYMBOL(scsi_host_alloc);

From: Ming Lei <[email protected]>

commit 3719f4ff047e20062b8314c23ec3cab84d74c908 upstream.

When scsi_add_host_with_dma() returns failure, the caller will call scsi_host_put(shost) to release everything allocated for this host instance. Consequently we can't also free allocated stuff in scsi_add_host_with_dma(), otherwise we will end up with a double free.

Strictly speaking, host resource allocations should have been done in scsi_host_alloc(). However, the allocations may need information which is not yet provided by the driver when that function is called. So leave the allocations where they are but rely on host device's release handler to free resources.

---
 drivers/scsi/hosts.c |   14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

@@ -278,23 +278,22 @@ int scsi_add_host_with_dma(struct Scsi_H
 
 		if (!shost->work_q) {
 			error = -EINVAL;
-			goto out_free_shost_data;
+			goto out_del_dev;
 		}
 	}
 
 	error = scsi_sysfs_add_host(shost);
 	if (error)
-		goto out_destroy_host;
+		goto out_del_dev;
 
 	scsi_proc_host_add(shost);
 	scsi_autopm_put_host(shost);
 	return error;
 
- out_destroy_host:
-	if (shost->work_q)
-		destroy_workqueue(shost->work_q);
- out_free_shost_data:
-	kfree(shost->shost_data);
+	/*
+	 * Any host allocation in this function will be freed in
+	 * scsi_host_dev_release().
+	 */
  out_del_dev:
 	device_del(&shost->shost_dev);
  out_del_gendev:

@@ -304,7 +303,6 @@ int scsi_add_host_with_dma(struct Scsi_H
 	pm_runtime_disable(&shost->shost_gendev);
 	pm_runtime_set_suspended(&shost->shost_gendev);
 	pm_runtime_put_noidle(&shost->shost_gendev);
-	scsi_mq_destroy_tags(shost);
  fail:
 	return error;
 }

From: Ming Lei <[email protected]>

commit 11714026c02d613c30a149c3f4c4a15047744529 upstream.

scsi_host_dev_release() only frees dev_name when host state is SHOST_CREATED. After host state has changed to SHOST_RUNNING, scsi_host_dev_release() no longer cleans up.

Fix this by doing a put_device(&shost->shost_dev) in the failure path when host state is SHOST_RUNNING. Move get_device(&shost->shost_gendev) before device_add(&shost->shost_dev) so that scsi_host_cls_release() can do a put on this reference.

---
 drivers/scsi/hosts.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

@@ -254,12 +254,11 @@ int scsi_add_host_with_dma(struct Scsi_H
 
 	device_enable_async_suspend(&shost->shost_dev);
 
+	get_device(&shost->shost_gendev);
 	error = device_add(&shost->shost_dev);
 	if (error)
 		goto out_del_gendev;
 
-	get_device(&shost->shost_gendev);
-
 	if (shost->transportt->host_size) {
 		shost->shost_data = kzalloc(shost->transportt->host_size,
 					 GFP_KERNEL);

@@ -297,6 +296,11 @@ int scsi_add_host_with_dma(struct Scsi_H
  out_del_dev:
 	device_del(&shost->shost_dev);
  out_del_gendev:
+	/*
+	 * Host state is SHOST_RUNNING so we have to explicitly release
+	 * ->shost_dev.
+	 */
+	put_device(&shost->shost_dev);
 	device_del(&shost->shost_gendev);
  out_disable_runtime_pm:
 	device_disable_async_suspend(&shost->shost_gendev);

From: Ming Lei <[email protected]>

commit 1e0d4e6225996f05271de1ebcb1a7c9381af0b27 upstream.

get_device(shost->shost_gendev.parent) is called after host state has switched to SHOST_RUNNING. scsi_host_dev_release() shouldn't release the parent device if host state is still SHOST_CREATED.

---
 drivers/scsi/hosts.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -347,7 +347,7 @@ static void scsi_host_dev_release(struct
 
 	ida_simple_remove(&host_index_ida, shost->host_no);
 
-	if (parent)
+	if (shost->shost_state != SHOST_CREATED)
 		put_device(parent);
 	kfree(shost);
 }

5.12.11-rc1 Successfully Compiled and booted on my Raspberry PI 4b (8g) (bcm2711)

All tests passing for Tegra ...

Test results for stable-v5.12:

    12 builds:	12 pass, 0 fail
    28 boots:	28 pass, 0 fail
    104 tests:	104 pass, 0 fail

Linux version: 5.12.11-rc1-g38004b22b0ae
Boards tested: tegra124-jetson-tk1, tegra186-p2771-0000,

                tegra194-p2972-0000, tegra194-p3509-0000+p3668-0000,
                tegra20-ventana, tegra210-p2371-2180,
                tegra210-p3450-0000, tegra30-cardhu-a04

Jon

Compiled and booted on my test system. No dmesg regressions.

thanks,
-- Shuah

On ARCH_BRCMSTB using 32-bit and 64-bit kernels:

Florian

Tested rc1 against the Fedora build system (aarch64, armv7, ppc64le, s390x, x86_64), and boot tested x86_64. No regressions noted.

Results from Linaro’s test farm.
No regressions on arm64, arm, x86_64, and i386.

## Build
* kernel: 5.12.11-rc1
* git: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
* git branch: linux-5.12.y
* git commit: 38004b22b0ae0ed236de37f13b323c9d89311f9e
* git describe: v5.12.10-174-g38004b22b0ae
* test details:
https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-5.12.y/build/v5.12.10-174-g38004b22b0ae

## No regressions (compared to v5.12.10)

## No fixes (compared to v5.12.10)

## Test result summary
total: 83712, pass: 69169, fail: 1865, skip: 11956, xfail: 722,

## Build Summary
* arc: 10 total, 10 passed, 0 failed
* arm: 193 total, 193 passed, 0 failed
* arm64: 27 total, 27 passed, 0 failed
* dragonboard-410c: 1 total, 1 passed, 0 failed
* hi6220-hikey: 1 total, 1 passed, 0 failed
* i386: 26 total, 26 passed, 0 failed
* juno-r2: 1 total, 1 passed, 0 failed
* mips: 45 total, 45 passed, 0 failed
* parisc: 9 total, 9 passed, 0 failed
* powerpc: 27 total, 27 passed, 0 failed
* riscv: 21 total, 21 passed, 0 failed
* s390: 18 total, 18 passed, 0 failed
* sh: 18 total, 18 passed, 0 failed
* sparc: 9 total, 9 passed, 0 failed
* x15: 1 total, 0 passed, 1 failed
* x86: 1 total, 1 passed, 0 failed
* x86_64: 27 total, 27 passed, 0 failed

## Test suites summary
* fwts
* igt-gpu-tools
* install-android-platform-tools-r2600
* kselftest-
* kselftest-android
* kselftest-bpf
* kselftest-breakpoints
* kselftest-capabilities
* kselftest-cgroup
* kselftest-clone3
* kselftest-core
* kselftest-cpu-hotplug
* kselftest-cpufreq
* kselftest-drivers
* kselftest-efivarfs
* kselftest-filesystems
* kselftest-firmware
* kselftest-fpu
* kselftest-futex
* kselftest-gpio
* kselftest-intel_pstate
* kselftest-ipc
* kselftest-ir
* kselftest-kcmp
* kselftest-kexec
* kselftest-kvm
* kselftest-lib
* kselftest-livepatch
* kselftest-lkdtm
* kselftest-membarrier
* kselftest-memfd
* kselftest-memory-hotplug
* kselftest-mincore
* kselftest-mount
* kselftest-mqueue
* kselftest-net
* kselftest-netfilter
* kselftest-nsfs
* kselftest-openat2
* kselftest-pid_namespace
* kselftest-pidfd
* kselftest-proc
* kselftest-pstore
* kselftest-ptrace
* kselftest-rseq
* kselftest-rtc
* kselftest-seccomp
* kselftest-sigaltstack
* kselftest-size
* kselftest-splice
* kselftest-static_keys
* kselftest-sync
* kselftest-sysctl
* kselftest-tc-testing
* kselftest-timens
* kselftest-timers
* kselftest-tmpfs
* kselftest-tpm2
* kselftest-user
* kselftest-vm
* kselftest-vsyscall-mode-native-
* kselftest-vsyscall-mode-none-
* kselftest-x86
* kselftest-zram
* kunit
* kvm-unit-tests
* libhugetlbfs
* linux-log-parser
* ltp-cap_bounds-tests
* ltp-commands-tests
* ltp-containers-tests
* ltp-controllers-tests
* ltp-cpuhotplug-tests
* ltp-crypto-tests
* ltp-cve-tests
* ltp-dio-tests
* ltp-fcntl-locktests-tests
* ltp-filecaps-tests
* ltp-fs-tests
* ltp-fs_bind-tests
* ltp-fs_perms_simple-tests
* ltp-fsx-tests
* ltp-hugetlb-tests
* ltp-io-tests
* ltp-ipc-tests
* ltp-math-tests
* ltp-mm-tests
* ltp-nptl-tests
* ltp-open-posix-tests
* ltp-pty-tests
* ltp-sched-tests
* ltp-securebits-tests
* ltp-syscalls-tests
* ltp-tracing-tests
* network-basic-tests
* packetdrill
* perf
* prep-inline
* rcutorture
* ssuite
* v4l2-compliance

--
Linaro LKFT
https://lkft.linaro.org

Build results:

	total: 151 pass: 151 fail: 0
Qemu test results:
	total: 462 pass: 462 fail: 0

Guenter