IB/hfi1: Fix fault injection init/exit issues

There are config dependent code paths that expose panics in unload
paths both in this file and in debugfs_remove_recursive() because
CONFIG_FAULT_INJECTION and CONFIG_FAULT_INJECTION_DEBUG_FS can be
set independently.

Having CONFIG_FAULT_INJECTION set and CONFIG_FAULT_INJECTION_DEBUG_FS
reset causes fault_create_debugfs_attr() to return an error.

The debugfs.c routines tolerate failures, but the module unload panics
dereferencing a NULL in the two exit routines.  If that is fixed, the
dir passed to debugfs_remove_recursive comes from a memory location
that was freed and potentially reused causing a segfault or corrupting
memory.

Here is an example of the NULL deref panic:

[66866.286829] BUG: unable to handle kernel NULL pointer dereference at 0000000000000088
[66866.295602] IP: hfi1_dbg_ibdev_exit+0x2a/0x80 [hfi1]
[66866.301138] PGD 858496067 P4D 858496067 PUD 8433a7067 PMD 0
[66866.307452] Oops: 0000 [#1] SMP
[66866.310953] Modules linked in: hfi1(-) rdmavt rdma_ucm ib_ucm ib_uverbs ib_umad rdma_cm iw_cm ib_cm ib_core rpcsec_gss_krb5 nfsv4 dns_resolver nfsv3 nfs fscache sb_edac x86_pkg_temp_thermal intel_powerclamp vfat fat coretemp kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel iTCO_wdt iTCO_vendor_support crypto_simd mei_me glue_helper cryptd mxm_wmi ipmi_si pcspkr lpc_ich sg mei ioatdma ipmi_devintf i2c_i801 mfd_core shpchp ipmi_msghandler wmi acpi_power_meter acpi_cpufreq nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables ext4 mbcache jbd2 sd_mod mgag200 drm_kms_helper syscopyarea sysfillrect sysimgblt igb fb_sys_fops ttm ahci ptp crc32c_intel libahci pps_core drm dca libata i2c_algo_bit i2c_core [last unloaded: opa_vnic]
[66866.385551] CPU: 8 PID: 7470 Comm: rmmod Not tainted 4.14.0-mam-tid-rdma #2
[66866.393317] Hardware name: Intel Corporation S2600WT2/S2600WT2, BIOS SE5C610.86B.01.01.0018.C4.072020161249 07/20/2016
[66866.405252] task: ffff88084f28c380 task.stack: ffffc90008454000
[66866.411866] RIP: 0010:hfi1_dbg_ibdev_exit+0x2a/0x80 [hfi1]
[66866.417984] RSP: 0018:ffffc90008457da0 EFLAGS: 00010202
[66866.423812] RAX: 0000000000000000 RBX: ffff880857de0000 RCX: 0000000180040001
[66866.431773] RDX: 0000000180040002 RSI: ffffea0021088200 RDI: 0000000040000000
[66866.439734] RBP: ffffc90008457da8 R08: ffff88084220e000 R09: 0000000180040001
[66866.447696] R10: 000000004220e001 R11: ffff88084220e000 R12: ffff88085a31c000
[66866.455657] R13: ffffffffa07c9820 R14: ffffffffa07c9890 R15: ffff881059d78100
[66866.463618] FS:  00007f6876047740(0000) GS:ffff88085f800000(0000) knlGS:0000000000000000
[66866.472644] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[66866.479053] CR2: 0000000000000088 CR3: 0000000856357006 CR4: 00000000001606e0
[66866.487013] Call Trace:
[66866.489747]  remove_one+0x1f/0x220 [hfi1]
[66866.494221]  pci_device_remove+0x39/0xc0
[66866.498596]  device_release_driver_internal+0x141/0x210
[66866.504424]  driver_detach+0x3f/0x80
[66866.508409]  bus_remove_driver+0x55/0xd0
[66866.512784]  driver_unregister+0x2c/0x50
[66866.517164]  pci_unregister_driver+0x2a/0xa0
[66866.521934]  hfi1_mod_cleanup+0x10/0xaa2 [hfi1]
[66866.526988]  SyS_delete_module+0x171/0x250
[66866.531558]  do_syscall_64+0x67/0x1b0
[66866.535644]  entry_SYSCALL64_slow_path+0x25/0x25
[66866.540792] RIP: 0033:0x7f6875525c27
[66866.544777] RSP: 002b:00007ffd48528e78 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0
[66866.553224] RAX: ffffffffffffffda RBX: 0000000001cc01d0 RCX: 00007f6875525c27
[66866.561185] RDX: 00007f6875596000 RSI: 0000000000000800 RDI: 0000000001cc0238
[66866.569146] RBP: 0000000000000000 R08: 00007f68757e9060 R09: 00007f6875596000
[66866.577120] R10: 00007ffd48528c00 R11: 0000000000000206 R12: 00007ffd48529db4
[66866.585080] R13: 0000000000000000 R14: 0000000001cc01d0 R15: 0000000001cc0010
[66866.593040] Code: 90 0f 1f 44 00 00 48 83 3d a3 8b 03 00 00 55 48 89 e5 53 48 89 fb 74 4e 48 8d bf 18 0c 00 00 e8 9d f2 ff ff 48 8b 83 20 0c 00 00 <48> 8b b8 88 00 00 00 e8 2a 21 b3 e0 48 8b bb 20 0c 00 00 e8 0e
[66866.614127] RIP: hfi1_dbg_ibdev_exit+0x2a/0x80 [hfi1] RSP: ffffc90008457da0
[66866.621885] CR2: 0000000000000088
[66866.625618] ---[ end trace c4817425783fb092 ]---

Fix by insuring that upon failure from fault_create_debugfs_attr() the
parent pointer for the routines is always set to NULL and guards added
in the exit routines to insure that debugfs_remove_recursive() is not
called when when the parent pointer is NULL.

Fixes: 0181ce3 ("IB/hfi1: Add receive fault injection feature")
Cc: <[email protected]> # 4.14.x
Reviewed-by: Michael J. Ruhl <[email protected]>
Signed-off-by: Mike Marciniszyn <[email protected]>
Signed-off-by: Dennis Dalessandro <[email protected]>
Signed-off-by: Doug Ledford <[email protected]>

Author: Mike Marciniszyn

drivers/infiniband/hw/hfi1/debugfs.c

@@ -1227,7 +1227,8 @@ DEBUGFS_FILE_OPS(fault_stats);
 
 static void fault_exit_opcode_debugfs(struct hfi1_ibdev *ibd)
 {
-	debugfs_remove_recursive(ibd->fault_opcode->dir);
+	if (ibd->fault_opcode)
+		debugfs_remove_recursive(ibd->fault_opcode->dir);
 	kfree(ibd->fault_opcode);
 	ibd->fault_opcode = NULL;
 }
@@ -1255,6 +1256,7 @@ static int fault_init_opcode_debugfs(struct hfi1_ibdev *ibd)
 					  &ibd->fault_opcode->attr);
 	if (IS_ERR(ibd->fault_opcode->dir)) {
 		kfree(ibd->fault_opcode);
+		ibd->fault_opcode = NULL;
 		return -ENOENT;
 	}
 
@@ -1278,7 +1280,8 @@ static int fault_init_opcode_debugfs(struct hfi1_ibdev *ibd)
 
 static void fault_exit_packet_debugfs(struct hfi1_ibdev *ibd)
 {
-	debugfs_remove_recursive(ibd->fault_packet->dir);
+	if (ibd->fault_packet)
+		debugfs_remove_recursive(ibd->fault_packet->dir);
 	kfree(ibd->fault_packet);
 	ibd->fault_packet = NULL;
 }
@@ -1304,6 +1307,7 @@ static int fault_init_packet_debugfs(struct hfi1_ibdev *ibd)
 					  &ibd->fault_opcode->attr);
 	if (IS_ERR(ibd->fault_packet->dir)) {
 		kfree(ibd->fault_packet);
+		ibd->fault_packet = NULL;
 		return -ENOENT;
 	}