cxl: fix nested locking hang during EEH hotplug

Commit 14a3ae34bfd0 ("cxl: Prevent read/write to AFU config space while AFU
not configured") introduced a rwsem to fix an invalid memory access that
occurred when someone attempts to access the config space of an AFU on a
vPHB whilst the AFU is deconfigured, such as during EEH recovery.

It turns out that it's possible to run into a nested locking issue when EEH
recovery fails and a full device hotplug is required.
cxl_pci_error_detected() deconfigures the AFU, taking a writer lock on
configured_rwsem. When EEH recovery fails, the EEH code calls
pci_hp_remove_devices() to remove the device, which in turn calls
cxl_remove() -> cxl_pci_remove_afu() -> pci_deconfigure_afu(), which tries
to grab the writer lock that's already held.

Standard rwsem semantics don't express what we really want to do here and
don't allow for nested locking. Fix this by replacing the rwsem with an
atomic_t which we can control more finely. Allow the AFU to be locked
multiple times so long as there are no readers.

Fixes: 14a3ae34bfd0 ("cxl: Prevent read/write to AFU config space while AFU not configured")
Cc: stable@vger.kernel.org # v4.9+
Signed-off-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Acked-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 14 insertions, 4 deletions

diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c
index 639a343b7836..512a4897dbf6 100644
--- a/drivers/misc/cxl/vphb.c
+++ b/drivers/misc/cxl/vphb.c
@@ -83,6 +83,16 @@ static inline struct cxl_afu *pci_bus_to_afu(struct pci_bus *bus)
 	return phb ? phb->private_data : NULL;
 }
 
+static void cxl_afu_configured_put(struct cxl_afu *afu)
+{
+	atomic_dec_if_positive(&afu->configured_state);
+}
+
+static bool cxl_afu_configured_get(struct cxl_afu *afu)
+{
+	return atomic_inc_unless_negative(&afu->configured_state);
+}
+
 static inline int cxl_pcie_config_info(struct pci_bus *bus, unsigned int devfn,
 				       struct cxl_afu *afu, int *_record)
 {
@@ -107,7 +117,7 @@ static int cxl_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
 
 	afu = pci_bus_to_afu(bus);
 	/* Grab a reader lock on afu. */
-	if (afu == NULL || !down_read_trylock(&afu->configured_rwsem))
+	if (afu == NULL || !cxl_afu_configured_get(afu))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	rc = cxl_pcie_config_info(bus, devfn, afu, &record);
@@ -132,7 +142,7 @@ static int cxl_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
 	}
 
 out:
-	up_read(&afu->configured_rwsem);
+	cxl_afu_configured_put(afu);
 	return rc ? PCIBIOS_DEVICE_NOT_FOUND : PCIBIOS_SUCCESSFUL;
 }
 
@@ -144,7 +154,7 @@ static int cxl_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
 
 	afu = pci_bus_to_afu(bus);
 	/* Grab a reader lock on afu. */
-	if (afu == NULL || !down_read_trylock(&afu->configured_rwsem))
+	if (afu == NULL || !cxl_afu_configured_get(afu))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	rc = cxl_pcie_config_info(bus, devfn, afu, &record);
@@ -166,7 +176,7 @@ static int cxl_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
 	}
 
 out:
-	up_read(&afu->configured_rwsem);
+	cxl_afu_configured_put(afu);
 	return rc ? PCIBIOS_SET_FAILED : PCIBIOS_SUCCESSFUL;
 }