[PATCH AUTOSEL 5.5 012/542] soc: fsl: qe: change return type of cpm_muram_alloc() to s32

[PATCH AUTOSEL 5.5 012/542] soc: fsl: qe: change return type of cpm_muram_alloc() to s32

[Sasha Levin]

From: Rasmus Villemoes <linux@rasmusvillemoes.dk>

[ Upstream commit 800cd6fb76f0ec7711deb72a86c924db1ae42648 ]

There are a number of problems with cpm_muram_alloc() and its
callers. Most callers assign the return value to some variable and
then use IS_ERR_VALUE to check for allocation failure. However, when
that variable is not sizeof(long), this leads to warnings - and it is
indeed broken to do e.g.

  u32 foo = cpm_muram_alloc();
  if (IS_ERR_VALUE(foo))

on a 64-bit platform, since the condition

  foo >= (unsigned long)-ENOMEM

is tautologically false. There are also callers that ignore the
possibility of error, and then there are those that check for error by
comparing the return value to 0...

One could fix that by changing all callers to store the return value
temporarily in an "unsigned long" and test that. However, use of
IS_ERR_VALUE() is error-prone and should be restricted to things which
are inherently long-sized (stuff in pt_regs etc.). Instead, let's aim
for changing to the standard kernel style

  int foo = cpm_muram_alloc();
  if (foo < 0)
    deal_with_it()
  some->where = foo;

Changing the return type from unsigned long to s32 (aka signed int)
doesn't change the value that gets stored into any of the callers'
variables except if the caller was storing the result in a u64 _and_
the allocation failed, so in itself this patch should be a no-op.

Another problem with cpm_muram_alloc() is that it can certainly
validly return 0 - and except if some cpm_muram_alloc_fixed() call
interferes, the very first cpm_muram_alloc() call will return just
that. But that shows that both ucc_slow_free() and ucc_fast_free() are
buggy, since they assume that a value of 0 means "that field was never
allocated". We'll later change cpm_muram_free() to accept (and ignore)
a negative offset, so callers can use a sentinel of -1 instead of 0
and just unconditionally call cpm_muram_free().

Reviewed-by: Timur Tabi <timur@kernel.org>
Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Li Yang <leoyang.li@nxp.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/soc/fsl/qe/qe_common.c | 29 ++++++++++++++++-------------
 include/soc/fsl/qe/qe.h        | 16 ++++++++--------
 2 files changed, 24 insertions(+), 21 deletions(-)

diff --git a/drivers/soc/fsl/qe/qe_common.c b/drivers/soc/fsl/qe/qe_common.c
index 83e85e61669f5..84c90105e588b 100644
--- a/drivers/soc/fsl/qe/qe_common.c
+++ b/drivers/soc/fsl/qe/qe_common.c
@@ -32,7 +32,7 @@ static phys_addr_t muram_pbase;
 
 struct muram_block {
 	struct list_head head;
-	unsigned long start;
+	s32 start;
 	int size;
 };
 
@@ -110,13 +110,14 @@ int cpm_muram_init(void)
  * @algo: algorithm for alloc.
  * @data: data for genalloc's algorithm.
  *
- * This function returns an offset into the muram area.
+ * This function returns a non-negative offset into the muram area, or
+ * a negative errno on failure.
  */
-static unsigned long cpm_muram_alloc_common(unsigned long size,
-		genpool_algo_t algo, void *data)
+static s32 cpm_muram_alloc_common(unsigned long size,
+				  genpool_algo_t algo, void *data)
 {
 	struct muram_block *entry;
-	unsigned long start;
+	s32 start;
 
 	if (!muram_pool && cpm_muram_init())
 		goto out2;
@@ -137,7 +138,7 @@ static unsigned long cpm_muram_alloc_common(unsigned long size,
 out1:
 	gen_pool_free(muram_pool, start, size);
 out2:
-	return (unsigned long)-ENOMEM;
+	return -ENOMEM;
 }
 
 /*
@@ -145,13 +146,14 @@ static unsigned long cpm_muram_alloc_common(unsigned long size,
  * @size: number of bytes to allocate
  * @align: requested alignment, in bytes
  *
- * This function returns an offset into the muram area.
+ * This function returns a non-negative offset into the muram area, or
+ * a negative errno on failure.
  * Use cpm_dpram_addr() to get the virtual address of the area.
  * Use cpm_muram_free() to free the allocation.
  */
-unsigned long cpm_muram_alloc(unsigned long size, unsigned long align)
+s32 cpm_muram_alloc(unsigned long size, unsigned long align)
 {
-	unsigned long start;
+	s32 start;
 	unsigned long flags;
 	struct genpool_data_align muram_pool_data;
 
@@ -168,7 +170,7 @@ EXPORT_SYMBOL(cpm_muram_alloc);
  * cpm_muram_free - free a chunk of multi-user ram
  * @offset: The beginning of the chunk as returned by cpm_muram_alloc().
  */
-int cpm_muram_free(unsigned long offset)
+int cpm_muram_free(s32 offset)
 {
 	unsigned long flags;
 	int size;
@@ -194,13 +196,14 @@ EXPORT_SYMBOL(cpm_muram_free);
  * cpm_muram_alloc_fixed - reserve a specific region of multi-user ram
  * @offset: offset of allocation start address
  * @size: number of bytes to allocate
- * This function returns an offset into the muram area
+ * This function returns @offset if the area was available, a negative
+ * errno otherwise.
  * Use cpm_dpram_addr() to get the virtual address of the area.
  * Use cpm_muram_free() to free the allocation.
  */
-unsigned long cpm_muram_alloc_fixed(unsigned long offset, unsigned long size)
+s32 cpm_muram_alloc_fixed(unsigned long offset, unsigned long size)
 {
-	unsigned long start;
+	s32 start;
 	unsigned long flags;
 	struct genpool_data_fixed muram_pool_data_fixed;
 
diff --git a/include/soc/fsl/qe/qe.h b/include/soc/fsl/qe/qe.h
index c1036d16ed03b..2d35d5db16231 100644
--- a/include/soc/fsl/qe/qe.h
+++ b/include/soc/fsl/qe/qe.h
@@ -98,26 +98,26 @@ static inline void qe_reset(void) {}
 int cpm_muram_init(void);
 
 #if defined(CONFIG_CPM) || defined(CONFIG_QUICC_ENGINE)
-unsigned long cpm_muram_alloc(unsigned long size, unsigned long align);
-int cpm_muram_free(unsigned long offset);
-unsigned long cpm_muram_alloc_fixed(unsigned long offset, unsigned long size);
+s32 cpm_muram_alloc(unsigned long size, unsigned long align);
+int cpm_muram_free(s32 offset);
+s32 cpm_muram_alloc_fixed(unsigned long offset, unsigned long size);
 void __iomem *cpm_muram_addr(unsigned long offset);
 unsigned long cpm_muram_offset(void __iomem *addr);
 dma_addr_t cpm_muram_dma(void __iomem *addr);
 #else
-static inline unsigned long cpm_muram_alloc(unsigned long size,
-					    unsigned long align)
+static inline s32 cpm_muram_alloc(unsigned long size,
+				  unsigned long align)
 {
 	return -ENOSYS;
 }
 
-static inline int cpm_muram_free(unsigned long offset)
+static inline int cpm_muram_free(s32 offset)
 {
 	return -ENOSYS;
 }
 
-static inline unsigned long cpm_muram_alloc_fixed(unsigned long offset,
-						  unsigned long size)
+static inline s32 cpm_muram_alloc_fixed(unsigned long offset,
+					unsigned long size)
 {
 	return -ENOSYS;
 }
-- 
2.20.1

[PATCH AUTOSEL 5.5 048/542] powerpc/powernv/iov: Ensure the pdn for VFs always contains a valid PE number

[Sasha Levin]

From: Oliver O'Halloran <oohall@gmail.com>

[ Upstream commit 3b5b9997b331e77ce967eba2c4bc80dc3134a7fe ]

On pseries there is a bug with adding hotplugged devices to an IOMMU
group. For a number of dumb reasons fixing that bug first requires
re-working how VFs are configured on PowerNV. For background, on
PowerNV we use the pcibios_sriov_enable() hook to do two things:

  1. Create a pci_dn structure for each of the VFs, and
  2. Configure the PHB's internal BARs so the MMIO range for each VF
     maps to a unique PE.

Roughly speaking a PE is the hardware counterpart to a Linux IOMMU
group since all the devices in a PE share the same IOMMU table. A PE
also defines the set of devices that should be isolated in response to
a PCI error (i.e. bad DMA, UR/CA, AER events, etc). When isolated all
MMIO and DMA traffic to and from devicein the PE is blocked by the
root complex until the PE is recovered by the OS.

The requirement to block MMIO causes a giant headache because the P8
PHB generally uses a fixed mapping between MMIO addresses and PEs. As
a result we need to delay configuring the IOMMU groups for device
until after MMIO resources are assigned. For physical devices (i.e.
non-VFs) the PE assignment is done in pcibios_setup_bridge() which is
called immediately after the MMIO resources for downstream
devices (and the bridge's windows) are assigned. For VFs the setup is
more complicated because:

  a) pcibios_setup_bridge() is not called again when VFs are activated, and
  b) The pci_dev for VFs are created by generic code which runs after
     pcibios_sriov_enable() is called.

The work around for this is a two step process:

  1. A fixup in pcibios_add_device() is used to initialised the cached
     pe_number in pci_dn, then
  2. A bus notifier then adds the device to the IOMMU group for the PE
     specified in pci_dn->pe_number.

A side effect fixing the pseries bug mentioned in the first paragraph
is moving the fixup out of pcibios_add_device() and into
pcibios_bus_add_device(), which is called much later. This results in
step 2. failing because pci_dn->pe_number won't be initialised when
the bus notifier is run.

We can fix this by removing the need for the fixup. The PE for a VF is
known before the VF is even scanned so we can initialise
pci_dn->pe_number pcibios_sriov_enable() instead. Unfortunately,
moving the initialisation causes two problems:

  1. We trip the WARN_ON() in the current fixup code, and
  2. The EEH core clears pdn->pe_number when recovering a VF and
     relies on the fixup to correctly re-set it.

The only justification for either of these is a comment in
eeh_rmv_device() suggesting that pdn->pe_number *must* be set to
IODA_INVALID_PE in order for the VF to be scanned. However, this
comment appears to have no basis in reality. Both bugs can be fixed by
just deleting the code.

Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191028085424.12006-1-oohall@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kernel/eeh_driver.c          |  6 ------
 arch/powerpc/platforms/powernv/pci-ioda.c | 19 +++++++++++++++----
 arch/powerpc/platforms/powernv/pci.c      |  4 ----
 3 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 3dd1a422fc29d..a1eaffe868de4 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -525,12 +525,6 @@ static void eeh_rmv_device(struct eeh_dev *edev, void *userdata)
 
 		pci_iov_remove_virtfn(edev->physfn, pdn->vf_index);
 		edev->pdev = NULL;
-
-		/*
-		 * We have to set the VF PE number to invalid one, which is
-		 * required to plug the VF successfully.
-		 */
-		pdn->pe_number = IODA_INVALID_PE;
 #endif
 		if (rmv_data)
 			list_add(&edev->rmv_entry, &rmv_data->removed_vf_list);
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index da1068a9c2637..4374836b033b4 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1558,6 +1558,10 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 
 	/* Reserve PE for each VF */
 	for (vf_index = 0; vf_index < num_vfs; vf_index++) {
+		int vf_devfn = pci_iov_virtfn_devfn(pdev, vf_index);
+		int vf_bus = pci_iov_virtfn_bus(pdev, vf_index);
+		struct pci_dn *vf_pdn;
+
 		if (pdn->m64_single_mode)
 			pe_num = pdn->pe_num_map[vf_index];
 		else
@@ -1570,13 +1574,11 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 		pe->pbus = NULL;
 		pe->parent_dev = pdev;
 		pe->mve_number = -1;
-		pe->rid = (pci_iov_virtfn_bus(pdev, vf_index) << 8) |
-			   pci_iov_virtfn_devfn(pdev, vf_index);
+		pe->rid = (vf_bus << 8) | vf_devfn;
 
 		pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%x\n",
 			hose->global_number, pdev->bus->number,
-			PCI_SLOT(pci_iov_virtfn_devfn(pdev, vf_index)),
-			PCI_FUNC(pci_iov_virtfn_devfn(pdev, vf_index)), pe_num);
+			PCI_SLOT(vf_devfn), PCI_FUNC(vf_devfn), pe_num);
 
 		if (pnv_ioda_configure_pe(phb, pe)) {
 			/* XXX What do we do here ? */
@@ -1590,6 +1592,15 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 		list_add_tail(&pe->list, &phb->ioda.pe_list);
 		mutex_unlock(&phb->ioda.pe_list_mutex);
 
+		/* associate this pe to it's pdn */
+		list_for_each_entry(vf_pdn, &pdn->parent->child_list, list) {
+			if (vf_pdn->busno == vf_bus &&
+			    vf_pdn->devfn == vf_devfn) {
+				vf_pdn->pe_number = pe_num;
+				break;
+			}
+		}
+
 		pnv_pci_ioda2_setup_dma_pe(phb, pe);
 #ifdef CONFIG_IOMMU_API
 		iommu_register_group(&pe->table_group,
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index c0bea75ac27bf..e8e58a2cccddf 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -816,16 +816,12 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 	struct pnv_phb *phb = hose->private_data;
 #ifdef CONFIG_PCI_IOV
 	struct pnv_ioda_pe *pe;
-	struct pci_dn *pdn;
 
 	/* Fix the VF pdn PE number */
 	if (pdev->is_virtfn) {
-		pdn = pci_get_pdn(pdev);
-		WARN_ON(pdn->pe_number != IODA_INVALID_PE);
 		list_for_each_entry(pe, &phb->ioda.pe_list, list) {
 			if (pe->rid == ((pdev->bus->number << 8) |
 			    (pdev->devfn & 0xff))) {
-				pdn->pe_number = pe->pe_number;
 				pe->pdev = pdev;
 				break;
 			}
-- 
2.20.1

[PATCH AUTOSEL 5.5 096/542] powerpc/powernv/ioda: Fix ref count for devices with their own PE

[Sasha Levin]

From: Frederic Barrat <fbarrat@linux.ibm.com>

[ Upstream commit 05dd7da76986937fb288b4213b1fa10dbe0d1b33 ]

The pci_dn structure used to store a pointer to the struct pci_dev, so
taking a reference on the device was required. However, the pci_dev
pointer was later removed from the pci_dn structure, but the reference
was kept for the npu device.
See commit 902bdc57451c ("powerpc/powernv/idoa: Remove unnecessary
pcidev from pci_dn").

We don't need to take a reference on the device when assigning the PE
as the struct pnv_ioda_pe is cleaned up at the same time as
the (physical) device is released. Doing so prevents the device from
being released, which is a problem for opencapi devices, since we want
to be able to remove them through PCI hotplug.

Now the ugly part: nvlink npu devices are not meant to be
released. Because of the above, we've always leaked a reference and
simply removing it now is dangerous and would likely require more
work. There's currently no release device callback for nvlink devices
for example. So to be safe, this patch leaks a reference on the npu
device, but only for nvlink and not opencapi.

Signed-off-by: Frederic Barrat <fbarrat@linux.ibm.com>
Reviewed-by: Andrew Donnellan <ajd@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191121134918.7155-2-fbarrat@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/platforms/powernv/pci-ioda.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 4374836b033b4..67b836f102402 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1062,14 +1062,13 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 		return NULL;
 	}
 
-	/* NOTE: We get only one ref to the pci_dev for the pdn, not for the
-	 * pointer in the PE data structure, both should be destroyed at the
-	 * same time. However, this needs to be looked at more closely again
-	 * once we actually start removing things (Hotplug, SR-IOV, ...)
+	/* NOTE: We don't get a reference for the pointer in the PE
+	 * data structure, both the device and PE structures should be
+	 * destroyed at the same time. However, removing nvlink
+	 * devices will need some work.
 	 *
 	 * At some point we want to remove the PDN completely anyways
 	 */
-	pci_dev_get(dev);
 	pdn->pe_number = pe->pe_number;
 	pe->flags = PNV_IODA_PE_DEV;
 	pe->pdev = dev;
@@ -1084,7 +1083,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 		pnv_ioda_free_pe(pe);
 		pdn->pe_number = IODA_INVALID_PE;
 		pe->pdev = NULL;
-		pci_dev_put(dev);
 		return NULL;
 	}
 
@@ -1205,6 +1203,14 @@ static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
 	struct pci_controller *hose = pci_bus_to_host(npu_pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
 
+	/*
+	 * Intentionally leak a reference on the npu device (for
+	 * nvlink only; this is not an opencapi path) to make sure it
+	 * never goes away, as it's been the case all along and some
+	 * work is needed otherwise.
+	 */
+	pci_dev_get(npu_pdev);
+
 	/*
 	 * Due to a hardware errata PE#0 on the NPU is reserved for
 	 * error handling. This means we only have three PEs remaining
@@ -1228,7 +1234,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
 			 */
 			dev_info(&npu_pdev->dev,
 				"Associating to existing PE %x\n", pe_num);
-			pci_dev_get(npu_pdev);
 			npu_pdn = pci_get_pdn(npu_pdev);
 			rid = npu_pdev->bus->number << 8 | npu_pdn->devfn;
 			npu_pdn->pe_number = pe_num;
-- 
2.20.1

Re: [PATCH AUTOSEL 5.5 096/542] powerpc/powernv/ioda: Fix ref count for devices with their own PE

[Frederic Barrat]

Le 14/02/2020 à 16:41, Sasha Levin a écrit :
> From: Frederic Barrat <fbarrat@linux.ibm.com>
> 
> [ Upstream commit 05dd7da76986937fb288b4213b1fa10dbe0d1b33 ]


Hi,

Upstream commit 05dd7da76986937fb288b4213b1fa10dbe0d1b33 doesn't really 
need to go to stable (any of 4.19, 5.4 and 5.5). While it's probably 
safe, the patch replaces a refcount leak by another one, which makes 
sense as part of the full series merged in 5.6-rc1, but isn't terribly 
useful standalone on the current stable branches.

   Fred



> The pci_dn structure used to store a pointer to the struct pci_dev, so
> taking a reference on the device was required. However, the pci_dev
> pointer was later removed from the pci_dn structure, but the reference
> was kept for the npu device.
> See commit 902bdc57451c ("powerpc/powernv/idoa: Remove unnecessary
> pcidev from pci_dn").
> 
> We don't need to take a reference on the device when assigning the PE
> as the struct pnv_ioda_pe is cleaned up at the same time as
> the (physical) device is released. Doing so prevents the device from
> being released, which is a problem for opencapi devices, since we want
> to be able to remove them through PCI hotplug.
> 
> Now the ugly part: nvlink npu devices are not meant to be
> released. Because of the above, we've always leaked a reference and
> simply removing it now is dangerous and would likely require more
> work. There's currently no release device callback for nvlink devices
> for example. So to be safe, this patch leaks a reference on the npu
> device, but only for nvlink and not opencapi.
> 
> Signed-off-by: Frederic Barrat <fbarrat@linux.ibm.com>
> Reviewed-by: Andrew Donnellan <ajd@linux.ibm.com>
> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
> Link: https://lore.kernel.org/r/20191121134918.7155-2-fbarrat@linux.ibm.com
> Signed-off-by: Sasha Levin <sashal@kernel.org>
> ---
>   arch/powerpc/platforms/powernv/pci-ioda.c | 19 ++++++++++++-------
>   1 file changed, 12 insertions(+), 7 deletions(-)
> 
> diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
> index 4374836b033b4..67b836f102402 100644
> --- a/arch/powerpc/platforms/powernv/pci-ioda.c
> +++ b/arch/powerpc/platforms/powernv/pci-ioda.c
> @@ -1062,14 +1062,13 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
>   		return NULL;
>   	}
>   
> -	/* NOTE: We get only one ref to the pci_dev for the pdn, not for the
> -	 * pointer in the PE data structure, both should be destroyed at the
> -	 * same time. However, this needs to be looked at more closely again
> -	 * once we actually start removing things (Hotplug, SR-IOV, ...)
> +	/* NOTE: We don't get a reference for the pointer in the PE
> +	 * data structure, both the device and PE structures should be
> +	 * destroyed at the same time. However, removing nvlink
> +	 * devices will need some work.
>   	 *
>   	 * At some point we want to remove the PDN completely anyways
>   	 */
> -	pci_dev_get(dev);
>   	pdn->pe_number = pe->pe_number;
>   	pe->flags = PNV_IODA_PE_DEV;
>   	pe->pdev = dev;
> @@ -1084,7 +1083,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
>   		pnv_ioda_free_pe(pe);
>   		pdn->pe_number = IODA_INVALID_PE;
>   		pe->pdev = NULL;
> -		pci_dev_put(dev);
>   		return NULL;
>   	}
>   
> @@ -1205,6 +1203,14 @@ static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
>   	struct pci_controller *hose = pci_bus_to_host(npu_pdev->bus);
>   	struct pnv_phb *phb = hose->private_data;
>   
> +	/*
> +	 * Intentionally leak a reference on the npu device (for
> +	 * nvlink only; this is not an opencapi path) to make sure it
> +	 * never goes away, as it's been the case all along and some
> +	 * work is needed otherwise.
> +	 */
> +	pci_dev_get(npu_pdev);
> +
>   	/*
>   	 * Due to a hardware errata PE#0 on the NPU is reserved for
>   	 * error handling. This means we only have three PEs remaining
> @@ -1228,7 +1234,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
>   			 */
>   			dev_info(&npu_pdev->dev,
>   				"Associating to existing PE %x\n", pe_num);
> -			pci_dev_get(npu_pdev);
>   			npu_pdn = pci_get_pdn(npu_pdev);
>   			rid = npu_pdev->bus->number << 8 | npu_pdn->devfn;
>   			npu_pdn->pe_number = pe_num;
> 

Re: [PATCH AUTOSEL 5.5 096/542] powerpc/powernv/ioda: Fix ref count for devices with their own PE

[Sasha Levin]

On Mon, Feb 17, 2020 at 09:49:41AM +0100, Frederic Barrat wrote:
>
>
>Le 14/02/2020 à 16:41, Sasha Levin a écrit :
>>From: Frederic Barrat <fbarrat@linux.ibm.com>
>>
>>[ Upstream commit 05dd7da76986937fb288b4213b1fa10dbe0d1b33 ]
>
>
>Hi,
>
>Upstream commit 05dd7da76986937fb288b4213b1fa10dbe0d1b33 doesn't 
>really need to go to stable (any of 4.19, 5.4 and 5.5). While it's 
>probably safe, the patch replaces a refcount leak by another one, 
>which makes sense as part of the full series merged in 5.6-rc1, but 
>isn't terribly useful standalone on the current stable branches.

I'll drop it, thank you.

-- 
Thanks,
Sasha

[PATCH AUTOSEL 5.5 097/542] powerpc/iov: Move VF pdev fixup into pcibios_fixup_iov()

[Sasha Levin]

From: Oliver O'Halloran <oohall@gmail.com>

[ Upstream commit 965c94f309be58fbcc6c8d3e4f123376c5970d79 ]

An ioda_pe for each VF is allocated in pnv_pci_sriov_enable() before
the pci_dev for the VF is created. We need to set the pe->pdev pointer
at some point after the pci_dev is created. Currently we do that in:

pcibios_bus_add_device()
	pnv_pci_dma_dev_setup() (via phb->ops.dma_dev_setup)
		/* fixup is done here */
		pnv_pci_ioda_dma_dev_setup() (via pnv_phb->dma_dev_setup)

The fixup needs to be done before setting up DMA for for the VF's PE,
but there's no real reason to delay it until this point. Move the
fixup into pnv_pci_ioda_fixup_iov() so the ordering is:

	pcibios_add_device()
		pnv_pci_ioda_fixup_iov() (via ppc_md.pcibios_fixup_sriov)

	pcibios_bus_add_device()
		...

This isn't strictly required, but it's a slightly more logical place
to do the fixup and it simplifies pnv_pci_dma_dev_setup().

Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200110070207.439-4-oohall@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/platforms/powernv/pci-ioda.c | 29 +++++++++++++++++++----
 arch/powerpc/platforms/powernv/pci.c      | 14 -----------
 2 files changed, 25 insertions(+), 18 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 67b836f102402..b4afabe20744a 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2905,9 +2905,6 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
 	struct pci_dn *pdn;
 	int mul, total_vfs;
 
-	if (!pdev->is_physfn || pci_dev_is_added(pdev))
-		return;
-
 	pdn = pci_get_pdn(pdev);
 	pdn->vfs_expanded = 0;
 	pdn->m64_single_mode = false;
@@ -2982,6 +2979,30 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
 		res->end = res->start - 1;
 	}
 }
+
+static void pnv_pci_ioda_fixup_iov(struct pci_dev *pdev)
+{
+	if (WARN_ON(pci_dev_is_added(pdev)))
+		return;
+
+	if (pdev->is_virtfn) {
+		struct pnv_ioda_pe *pe = pnv_ioda_get_pe(pdev);
+
+		/*
+		 * VF PEs are single-device PEs so their pdev pointer needs to
+		 * be set. The pdev doesn't exist when the PE is allocated (in
+		 * (pcibios_sriov_enable()) so we fix it up here.
+		 */
+		pe->pdev = pdev;
+		WARN_ON(!(pe->flags & PNV_IODA_PE_VF));
+	} else if (pdev->is_physfn) {
+		/*
+		 * For PFs adjust their allocated IOV resources to match what
+		 * the PHB can support using it's M64 BAR table.
+		 */
+		pnv_pci_ioda_fixup_iov_resources(pdev);
+	}
+}
 #endif /* CONFIG_PCI_IOV */
 
 static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe,
@@ -3878,7 +3899,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	ppc_md.pcibios_default_alignment = pnv_pci_default_alignment;
 
 #ifdef CONFIG_PCI_IOV
-	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources;
+	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov;
 	ppc_md.pcibios_iov_resource_alignment = pnv_pci_iov_resource_alignment;
 	ppc_md.pcibios_sriov_enable = pnv_pcibios_sriov_enable;
 	ppc_md.pcibios_sriov_disable = pnv_pcibios_sriov_disable;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index e8e58a2cccddf..8307e1f4086cb 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -814,20 +814,6 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
-#ifdef CONFIG_PCI_IOV
-	struct pnv_ioda_pe *pe;
-
-	/* Fix the VF pdn PE number */
-	if (pdev->is_virtfn) {
-		list_for_each_entry(pe, &phb->ioda.pe_list, list) {
-			if (pe->rid == ((pdev->bus->number << 8) |
-			    (pdev->devfn & 0xff))) {
-				pe->pdev = pdev;
-				break;
-			}
-		}
-	}
-#endif /* CONFIG_PCI_IOV */
 
 	if (phb && phb->dma_dev_setup)
 		phb->dma_dev_setup(phb, pdev);
-- 
2.20.1

[PATCH AUTOSEL 5.5 103/542] powerpc/papr_scm: Fix leaking 'bus_desc.provider_name' in some paths

[Sasha Levin]

From: Vaibhav Jain <vaibhav@linux.ibm.com>

[ Upstream commit 5649607a8d0b0e019a4db14aab3de1e16c3a2b4f ]

String 'bus_desc.provider_name' allocated inside
papr_scm_nvdimm_init() will leaks in case call to
nvdimm_bus_register() fails or when papr_scm_remove() is called.

This minor patch ensures that 'bus_desc.provider_name' is freed in
error path for nvdimm_bus_register() as well as in papr_scm_remove().

Fixes: b5beae5e224f ("powerpc/pseries: Add driver for PAPR SCM regions")
Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200122155140.120429-1-vaibhav@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/platforms/pseries/papr_scm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index c2ef320ba1bf2..eb420655ed0b9 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -322,6 +322,7 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 	p->bus = nvdimm_bus_register(NULL, &p->bus_desc);
 	if (!p->bus) {
 		dev_err(dev, "Error creating nvdimm bus %pOF\n", p->dn);
+		kfree(p->bus_desc.provider_name);
 		return -ENXIO;
 	}
 
@@ -477,6 +478,7 @@ static int papr_scm_remove(struct platform_device *pdev)
 
 	nvdimm_bus_unregister(p->bus);
 	drc_pmem_unbind(p);
+	kfree(p->bus_desc.provider_name);
 	kfree(p);
 
 	return 0;
-- 
2.20.1

[PATCH AUTOSEL 5.5 104/542] powerpc/pseries/vio: Fix iommu_table use-after-free refcount warning

[Sasha Levin]

From: Tyrel Datwyler <tyreld@linux.vnet.ibm.com>

[ Upstream commit aff8c8242bc638ba57247ae1ec5f272ac3ed3b92 ]

Commit e5afdf9dd515 ("powerpc/vfio_spapr_tce: Add reference counting to
iommu_table") missed an iommu_table allocation in the pseries vio code.
The iommu_table is allocated with kzalloc and as a result the associated
kref gets a value of zero. This has the side effect that during a DLPAR
remove of the associated virtual IOA the iommu_tce_table_put() triggers
a use-after-free underflow warning.

Call Trace:
[c0000002879e39f0] [c00000000071ecb4] refcount_warn_saturate+0x184/0x190
(unreliable)
[c0000002879e3a50] [c0000000000500ac] iommu_tce_table_put+0x9c/0xb0
[c0000002879e3a70] [c0000000000f54e4] vio_dev_release+0x34/0x70
[c0000002879e3aa0] [c00000000087cfa4] device_release+0x54/0xf0
[c0000002879e3b10] [c000000000d64c84] kobject_cleanup+0xa4/0x240
[c0000002879e3b90] [c00000000087d358] put_device+0x28/0x40
[c0000002879e3bb0] [c0000000007a328c] dlpar_remove_slot+0x15c/0x250
[c0000002879e3c50] [c0000000007a348c] remove_slot_store+0xac/0xf0
[c0000002879e3cd0] [c000000000d64220] kobj_attr_store+0x30/0x60
[c0000002879e3cf0] [c0000000004ff13c] sysfs_kf_write+0x6c/0xa0
[c0000002879e3d10] [c0000000004fde4c] kernfs_fop_write+0x18c/0x260
[c0000002879e3d60] [c000000000410f3c] __vfs_write+0x3c/0x70
[c0000002879e3d80] [c000000000415408] vfs_write+0xc8/0x250
[c0000002879e3dd0] [c0000000004157dc] ksys_write+0x7c/0x120
[c0000002879e3e20] [c00000000000b278] system_call+0x5c/0x68

Further, since the refcount was always zero the iommu_tce_table_put()
fails to call the iommu_table release function resulting in a leak.

Fix this issue be initilizing the iommu_table kref immediately after
allocation.

Fixes: e5afdf9dd515 ("powerpc/vfio_spapr_tce: Add reference counting to iommu_table")
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1579558202-26052-1-git-send-email-tyreld@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/platforms/pseries/vio.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 79e2287991dbb..f682b7babc09c 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1176,6 +1176,8 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
 	if (tbl == NULL)
 		return NULL;
 
+	kref_init(&tbl->it_kref);
+
 	of_parse_dma_window(dev->dev.of_node, dma_window,
 			    &tbl->it_index, &offset, &size);
 
-- 
2.20.1

[PATCH AUTOSEL 5.5 177/542] net/wan/fsl_ucc_hdlc: reject muram offsets above 64K

[Sasha Levin]

From: Rasmus Villemoes <linux@rasmusvillemoes.dk>

[ Upstream commit 148587a59f6b85831695e0497d9dd1af5f0495af ]

Qiang Zhao points out that these offsets get written to 16-bit
registers, and there are some QE platforms with more than 64K
muram. So it is possible that qe_muram_alloc() gives us an allocation
that can't actually be used by the hardware, so detect and reject
that.

Reported-by: Qiang Zhao <qiang.zhao@nxp.com>
Reviewed-by: Timur Tabi <timur@kernel.org>
Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Li Yang <leoyang.li@nxp.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wan/fsl_ucc_hdlc.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index aef7de225783f..4ad0a0c33d853 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -245,6 +245,11 @@ static int uhdlc_init(struct ucc_hdlc_private *priv)
 		ret = -ENOMEM;
 		goto free_riptr;
 	}
+	if (riptr != (u16)riptr || tiptr != (u16)tiptr) {
+		dev_err(priv->dev, "MURAM allocation out of addressable range\n");
+		ret = -ENOMEM;
+		goto free_tiptr;
+	}
 
 	/* Set RIPTR, TIPTR */
 	iowrite16be(riptr, &priv->ucc_pram->riptr);
-- 
2.20.1

[PATCH AUTOSEL 5.5 266/542] net/wan/fsl_ucc_hdlc: remove set but not used variables 'ut_info' and 'ret'

[Sasha Levin]

From: Chen Zhou <chenzhou10@huawei.com>

[ Upstream commit 270fe2ceda66b6964d4c6f261d7f562a02c1c786 ]

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/wan/fsl_ucc_hdlc.c: In function ucc_hdlc_irq_handler:
drivers/net/wan/fsl_ucc_hdlc.c:643:23:
	warning: variable ut_info set but not used [-Wunused-but-set-variable]
drivers/net/wan/fsl_ucc_hdlc.c: In function uhdlc_suspend:
drivers/net/wan/fsl_ucc_hdlc.c:880:23:
	warning: variable ut_info set but not used [-Wunused-but-set-variable]
drivers/net/wan/fsl_ucc_hdlc.c: In function uhdlc_resume:
drivers/net/wan/fsl_ucc_hdlc.c:925:6:
	warning: variable ret set but not used [-Wunused-but-set-variable]

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Chen Zhou <chenzhou10@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wan/fsl_ucc_hdlc.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index 4ad0a0c33d853..607cb1edff964 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -640,11 +640,9 @@ static irqreturn_t ucc_hdlc_irq_handler(int irq, void *dev_id)
 	struct ucc_hdlc_private *priv = (struct ucc_hdlc_private *)dev_id;
 	struct net_device *dev = priv->ndev;
 	struct ucc_fast_private *uccf;
-	struct ucc_tdm_info *ut_info;
 	u32 ucce;
 	u32 uccm;
 
-	ut_info = priv->ut_info;
 	uccf = priv->uccf;
 
 	ucce = ioread32be(uccf->p_ucce);
@@ -877,7 +875,6 @@ static void resume_clk_config(struct ucc_hdlc_private *priv)
 static int uhdlc_suspend(struct device *dev)
 {
 	struct ucc_hdlc_private *priv = dev_get_drvdata(dev);
-	struct ucc_tdm_info *ut_info;
 	struct ucc_fast __iomem *uf_regs;
 
 	if (!priv)
@@ -889,7 +886,6 @@ static int uhdlc_suspend(struct device *dev)
 	netif_device_detach(priv->ndev);
 	napi_disable(&priv->napi);
 
-	ut_info = priv->ut_info;
 	uf_regs = priv->uf_regs;
 
 	/* backup gumr guemr*/
@@ -922,7 +918,7 @@ static int uhdlc_resume(struct device *dev)
 	struct ucc_fast __iomem *uf_regs;
 	struct ucc_fast_private *uccf;
 	struct ucc_fast_info *uf_info;
-	int ret, i;
+	int i;
 	u32 cecr_subblock;
 	u16 bd_status;
 
@@ -967,16 +963,16 @@ static int uhdlc_resume(struct device *dev)
 
 	/* Write to QE CECR, UCCx channel to Stop Transmission */
 	cecr_subblock = ucc_fast_get_qe_cr_subblock(uf_info->ucc_num);
-	ret = qe_issue_cmd(QE_STOP_TX, cecr_subblock,
-			   (u8)QE_CR_PROTOCOL_UNSPECIFIED, 0);
+	qe_issue_cmd(QE_STOP_TX, cecr_subblock,
+		     (u8)QE_CR_PROTOCOL_UNSPECIFIED, 0);
 
 	/* Set UPSMR normal mode */
 	iowrite32be(0, &uf_regs->upsmr);
 
 	/* init parameter base */
 	cecr_subblock = ucc_fast_get_qe_cr_subblock(uf_info->ucc_num);
-	ret = qe_issue_cmd(QE_ASSIGN_PAGE_TO_DEVICE, cecr_subblock,
-			   QE_CR_PROTOCOL_UNSPECIFIED, priv->ucc_pram_offset);
+	qe_issue_cmd(QE_ASSIGN_PAGE_TO_DEVICE, cecr_subblock,
+		     QE_CR_PROTOCOL_UNSPECIFIED, priv->ucc_pram_offset);
 
 	priv->ucc_pram = (struct ucc_hdlc_param __iomem *)
 				qe_muram_addr(priv->ucc_pram_offset);
-- 
2.20.1

[PATCH AUTOSEL 5.5 302/542] soc: fsl: qe: remove set but not used variable 'mm_gc'

[Sasha Levin]

From: YueHaibing <yuehaibing@huawei.com>

[ Upstream commit 6e62bd36e9ad85a22d92b1adce6a0336ea549733 ]

drivers/soc/fsl/qe/gpio.c: In function qe_pin_request:
drivers/soc/fsl/qe/gpio.c:163:26: warning: variable mm_gc set but not used [-Wunused-but-set-variable]

commit 1e714e54b5ca ("powerpc: qe_lib-gpio: use gpiochip data pointer")
left behind this unused variable.

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Chen Zhou <chenzhou10@huawei.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Li Yang <leoyang.li@nxp.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/soc/fsl/qe/gpio.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/soc/fsl/qe/gpio.c b/drivers/soc/fsl/qe/gpio.c
index f0c29ed8f0ff1..807df73728fc7 100644
--- a/drivers/soc/fsl/qe/gpio.c
+++ b/drivers/soc/fsl/qe/gpio.c
@@ -160,7 +160,6 @@ struct qe_pin *qe_pin_request(struct device_node *np, int index)
 {
 	struct qe_pin *qe_pin;
 	struct gpio_chip *gc;
-	struct of_mm_gpio_chip *mm_gc;
 	struct qe_gpio_chip *qe_gc;
 	int err;
 	unsigned long flags;
@@ -186,7 +185,6 @@ struct qe_pin *qe_pin_request(struct device_node *np, int index)
 		goto err0;
 	}
 
-	mm_gc = to_of_mm_gpio_chip(gc);
 	qe_gc = gpiochip_get_data(gc);
 
 	spin_lock_irqsave(&qe_gc->lock, flags);
-- 
2.20.1

[PATCH AUTOSEL 5.5 395/542] KVM: PPC: Remove set but not used variable 'ra', 'rs', 'rt'

[Sasha Levin]

From: zhengbin <zhengbin13@huawei.com>

[ Upstream commit 4de0a8355463e068e443b48eb5ae32370155368b ]

Fixes gcc '-Wunused-but-set-variable' warning:

arch/powerpc/kvm/emulate_loadstore.c: In function kvmppc_emulate_loadstore:
arch/powerpc/kvm/emulate_loadstore.c:87:6: warning: variable ra set but not used [-Wunused-but-set-variable]
arch/powerpc/kvm/emulate_loadstore.c: In function kvmppc_emulate_loadstore:
arch/powerpc/kvm/emulate_loadstore.c:87:10: warning: variable rs set but not used [-Wunused-but-set-variable]
arch/powerpc/kvm/emulate_loadstore.c: In function kvmppc_emulate_loadstore:
arch/powerpc/kvm/emulate_loadstore.c:87:14: warning: variable rt set but not used [-Wunused-but-set-variable]

They are not used since commit 2b33cb585f94 ("KVM: PPC: Reimplement
LOAD_FP/STORE_FP instruction mmio emulation with analyse_instr() input")

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: zhengbin <zhengbin13@huawei.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kvm/emulate_loadstore.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c
index 2e496eb86e94a..1139bc56e0045 100644
--- a/arch/powerpc/kvm/emulate_loadstore.c
+++ b/arch/powerpc/kvm/emulate_loadstore.c
@@ -73,7 +73,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
 	u32 inst;
-	int ra, rs, rt;
 	enum emulation_result emulated = EMULATE_FAIL;
 	int advance = 1;
 	struct instruction_op op;
@@ -85,10 +84,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 	if (emulated != EMULATE_DONE)
 		return emulated;
 
-	ra = get_ra(inst);
-	rs = get_rs(inst);
-	rt = get_rt(inst);
-
 	vcpu->arch.mmio_vsx_copy_nums = 0;
 	vcpu->arch.mmio_vsx_offset = 0;
 	vcpu->arch.mmio_copy_type = KVMPPC_VSX_COPY_NONE;
-- 
2.20.1

[PATCH AUTOSEL 5.5 414/542] ide: remove set but not used variable 'hwif'

[Sasha Levin]

From: Wang Hai <wanghai38@huawei.com>

[ Upstream commit 98949a1946d70771789def0c9dbc239497f9f138 ]

Fix the following gcc warning:

drivers/ide/pmac.c: In function pmac_ide_setup_device:
drivers/ide/pmac.c:1027:14: warning: variable hwif set but not used
[-Wunused-but-set-variable]

Fixes: d58b0c39e32f ("powerpc/macio: Rework hotplug media bay support")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wang Hai <wanghai38@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/ide/pmac.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/ide/pmac.c b/drivers/ide/pmac.c
index b5647e34e74ee..ea0b064b5f56b 100644
--- a/drivers/ide/pmac.c
+++ b/drivers/ide/pmac.c
@@ -1019,7 +1019,6 @@ static int pmac_ide_setup_device(pmac_ide_hwif_t *pmif, struct ide_hw *hw)
 	struct device_node *np = pmif->node;
 	const int *bidp;
 	struct ide_host *host;
-	ide_hwif_t *hwif;
 	struct ide_hw *hws[] = { hw };
 	struct ide_port_info d = pmac_port_info;
 	int rc;
@@ -1075,7 +1074,7 @@ static int pmac_ide_setup_device(pmac_ide_hwif_t *pmif, struct ide_hw *hw)
 		rc = -ENOMEM;
 		goto bail;
 	}
-	hwif = pmif->hwif = host->ports[0];
+	pmif->hwif = host->ports[0];
 
 	if (on_media_bay(pmif)) {
 		/* Fixup bus ID for media bay */
-- 
2.20.1

[PATCH AUTOSEL 5.5 444/542] powerpc/ptdump: Fix W+X verification call in mark_rodata_ro()

[Sasha Levin]

From: Christophe Leroy <christophe.leroy@c-s.fr>

[ Upstream commit e26ad936dd89d79f66c2b567f700e0c2a7103070 ]

ptdump_check_wx() also have to be called when pages are mapped
by blocks.

Fixes: 453d87f6a8ae ("powerpc/mm: Warn if W+X pages found on boot")
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/37517da8310f4457f28921a4edb88fb21d27b62a.1578989531.git.christophe.leroy@c-s.fr
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/mm/pgtable_32.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 73b84166d06a6..5fb90edd865e6 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -218,6 +218,7 @@ void mark_rodata_ro(void)
 
 	if (v_block_mapped((unsigned long)_sinittext)) {
 		mmu_mark_rodata_ro();
+		ptdump_check_wx();
 		return;
 	}
 
-- 
2.20.1

[PATCH AUTOSEL 5.5 445/542] powerpc/ptdump: Only enable PPC_CHECK_WX with STRICT_KERNEL_RWX

[Sasha Levin]

From: Christophe Leroy <christophe.leroy@c-s.fr>

[ Upstream commit f509247b08f2dcf7754d9ed85ad69a7972aa132b ]

ptdump_check_wx() is called from mark_rodata_ro() which only exists
when CONFIG_STRICT_KERNEL_RWX is selected.

Fixes: 453d87f6a8ae ("powerpc/mm: Warn if W+X pages found on boot")
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/922d4939c735c6b52b4137838bcc066fffd4fc33.1578989545.git.christophe.leroy@c-s.fr
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/Kconfig.debug | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 4e1d398474627..0b063830eea84 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -371,7 +371,7 @@ config PPC_PTDUMP
 
 config PPC_DEBUG_WX
 	bool "Warn on W+X mappings at boot"
-	depends on PPC_PTDUMP
+	depends on PPC_PTDUMP && STRICT_KERNEL_RWX
 	help
 	  Generate a warning if any W+X mappings are found at boot.
 
-- 
2.20.1

[PATCH AUTOSEL 5.5 446/542] powerpc/sriov: Remove VF eeh_dev state when disabling SR-IOV

[Sasha Levin]

From: Oliver O'Halloran <oohall@gmail.com>

[ Upstream commit 1fb4124ca9d456656a324f1ee29b7bf942f59ac8 ]

When disabling virtual functions on an SR-IOV adapter we currently do not
correctly remove the EEH state for the now-dead virtual functions. When
removing the pci_dn that was created for the VF when SR-IOV was enabled
we free the corresponding eeh_dev without removing it from the child device
list of the eeh_pe that contained it. This can result in crashes due to the
use-after-free.

Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Reviewed-by: Sam Bobroff <sbobroff@linux.ibm.com>
Tested-by: Sam Bobroff <sbobroff@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190821062655.19735-1-oohall@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kernel/pci_dn.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 9524009ca1ae4..d876eda926094 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -244,9 +244,22 @@ void remove_dev_pci_data(struct pci_dev *pdev)
 				continue;
 
 #ifdef CONFIG_EEH
-			/* Release EEH device for the VF */
+			/*
+			 * Release EEH state for this VF. The PCI core
+			 * has already torn down the pci_dev for this VF, but
+			 * we're responsible to removing the eeh_dev since it
+			 * has the same lifetime as the pci_dn that spawned it.
+			 */
 			edev = pdn_to_eeh_dev(pdn);
 			if (edev) {
+				/*
+				 * We allocate pci_dn's for the totalvfs count,
+				 * but only only the vfs that were activated
+				 * have a configured PE.
+				 */
+				if (edev->pe)
+					eeh_rmv_from_parent_pe(edev);
+
 				pdn->edev = NULL;
 				kfree(edev);
 			}
-- 
2.20.1

[PATCH AUTOSEL 5.5 457/542] PCI/AER: Initialize aer_fifo

[Sasha Levin]

From: Dongdong Liu <liudongdong3@huawei.com>

[ Upstream commit d95f20c4f07020ebc605f3b46af4b6db9eb5fc99 ]

Previously we did not call INIT_KFIFO() for aer_fifo.  This leads to
kfifo_put() sometimes returning 0 (queue full) when in fact it is not.

It is easy to reproduce the problem by using aer-inject:

  $ aer-inject -s :82:00.0 multiple-corr-nonfatal

The content of the multiple-corr-nonfatal file is as below:

  AER
  COR RCVR
  HL 0 1 2 3
  AER
  UNCOR POISON_TLP
  HL 4 5 6 7

Fixes: 27c1ce8bbed7 ("PCI/AER: Use kfifo for tracking events instead of reimplementing it")
Link: https://lore.kernel.org/r/1579767991-103898-1-git-send-email-liudongdong3@huawei.com
Signed-off-by: Dongdong Liu <liudongdong3@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/pci/pcie/aer.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 1ca86f2e01665..4a818b07a1afb 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1445,6 +1445,7 @@ static int aer_probe(struct pcie_device *dev)
 		return -ENOMEM;
 
 	rpc->rpd = port;
+	INIT_KFIFO(rpc->aer_fifo);
 	set_service_data(dev, rpc);
 
 	status = devm_request_threaded_irq(device, dev->irq, aer_irq, aer_isr,
-- 
2.20.1

[PATCH AUTOSEL 5.5 464/542] powerpc/pseries/lparcfg: Fix display of Maximum Memory

[Sasha Levin]

From: Michael Bringmann <mwb@linux.ibm.com>

[ Upstream commit f1dbc1c5c70d0d4c60b5d467ba941fba167c12f6 ]

Correct overflow problem in calculation and display of Maximum Memory
value to syscfg.

Signed-off-by: Michael Bringmann <mwb@linux.ibm.com>
[mpe: Only n_lmbs needs casting to unsigned long]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/5577aef8-1d5a-ca95-ff0a-9c7b5977e5bf@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/platforms/pseries/lparcfg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index e33e8bc4b69bd..38c306551f76b 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -435,10 +435,10 @@ static void maxmem_data(struct seq_file *m)
 {
 	unsigned long maxmem = 0;
 
-	maxmem += drmem_info->n_lmbs * drmem_info->lmb_size;
+	maxmem += (unsigned long)drmem_info->n_lmbs * drmem_info->lmb_size;
 	maxmem += hugetlb_total_pages() * PAGE_SIZE;
 
-	seq_printf(m, "MaxMem=%ld\n", maxmem);
+	seq_printf(m, "MaxMem=%lu\n", maxmem);
 }
 
 static int pseries_lparcfg_data(struct seq_file *m, void *v)
-- 
2.20.1

[PATCH AUTOSEL 5.5 465/542] selftests/eeh: Bump EEH wait time to 60s

[Sasha Levin]

From: Oliver O'Halloran <oohall@gmail.com>

[ Upstream commit 414f50434aa2463202a5b35e844f4125dd1a7101 ]

Some newer cards supported by aacraid can take up to 40s to recover
after an EEH event. This causes spurious failures in the basic EEH
self-test since the current maximim timeout is only 30s.

Fix the immediate issue by bumping the timeout to a default of 60s,
and allow the wait time to be specified via an environmental variable
(EEH_MAX_WAIT).

Reported-by: Steve Best <sbest@redhat.com>
Suggested-by: Douglas Miller <dougmill@us.ibm.com>
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200122031125.25991-1-oohall@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/powerpc/eeh/eeh-functions.sh | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/powerpc/eeh/eeh-functions.sh b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh
index 26112ab5cdf42..f52ed92b53e74 100755
--- a/tools/testing/selftests/powerpc/eeh/eeh-functions.sh
+++ b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh
@@ -53,9 +53,13 @@ eeh_one_dev() {
 	# is a no-op.
 	echo $dev >/sys/kernel/debug/powerpc/eeh_dev_check
 
-	# Enforce a 30s timeout for recovery. Even the IPR, which is infamously
-	# slow to reset, should recover within 30s.
-	max_wait=30
+	# Default to a 60s timeout when waiting for a device to recover. This
+	# is an arbitrary default which can be overridden by setting the
+	# EEH_MAX_WAIT environmental variable when required.
+
+	# The current record holder for longest recovery time is:
+	#  "Adaptec Series 8 12G SAS/PCIe 3" at 39 seconds
+	max_wait=${EEH_MAX_WAIT:=60}
 
 	for i in `seq 0 ${max_wait}` ; do
 		if pe_ok $dev ; then
-- 
2.20.1

[PATCH AUTOSEL 5.5 483/542] powerpc/mm: Don't log user reads to 0xffffffff

[Sasha Levin]

From: Christophe Leroy <christophe.leroy@c-s.fr>

[ Upstream commit 0f9aee0cb9da7db7d96f63cfa2dc5e4f1bffeb87 ]

Running vdsotest leaves many times the following log:

  [   79.629901] vdsotest[396]: User access of kernel address (ffffffff) - exploit attempt? (uid: 0)

A pointer set to (-1) is likely a programming error similar to
a NULL pointer and is not worth logging as an exploit attempt.

Don't log user accesses to 0xffffffff.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/0728849e826ba16f1fbd6fa7f5c6cc87bd64e097.1577087627.git.christophe.leroy@c-s.fr
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/mm/fault.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 1baeb045f7f4b..e083a9f67f701 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -354,6 +354,9 @@ static void sanity_check_fault(bool is_write, bool is_user,
 	 * Userspace trying to access kernel address, we get PROTFAULT for that.
 	 */
 	if (is_user && address >= TASK_SIZE) {
+		if ((long)address == -1)
+			return;
+
 		pr_crit_ratelimited("%s[%d]: User access of kernel address (%lx) - exploit attempt? (uid: %d)\n",
 				   current->comm, current->pid, address,
 				   from_kuid(&init_user_ns, current_uid()));
-- 
2.20.1

[PATCH AUTOSEL 5.5 493/542] KVM: PPC: Book3S HV: Release lock on page-out failure path

[Sasha Levin]

From: Bharata B Rao <bharata@linux.ibm.com>

[ Upstream commit e032e3b55b6f487e48c163c5dca74086f147a169 ]

When migrate_vma_setup() fails in kvmppc_svm_page_out(),
release kvm->arch.uvmem_lock before returning.

Fixes: ca9f4942670 ("KVM: PPC: Book3S HV: Support for running secure guests")
Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
Reviewed-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kvm/book3s_hv_uvmem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 2de264fc31563..5914fbfa5e0a7 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -543,7 +543,7 @@ kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start,
 
 	ret = migrate_vma_setup(&mig);
 	if (ret)
-		return ret;
+		goto out;
 
 	spage = migrate_pfn_to_page(*mig.src);
 	if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE))
-- 
2.20.1

[PATCH AUTOSEL 5.5 502/542] powerpc: Do not consider weak unresolved symbol relocations as bad

[Sasha Levin]

From: Alexandre Ghiti <alex@ghiti.fr>

[ Upstream commit 43e76cd368fbb67e767da5363ffeaa3989993c8c ]

Commit 8580ac9404f6 ("bpf: Process in-kernel BTF") introduced two weak
symbols that may be unresolved at link time which result in an absolute
relocation to 0. relocs_check.sh emits the following warning:

"WARNING: 2 bad relocations
c000000001a41478 R_PPC64_ADDR64    _binary__btf_vmlinux_bin_start
c000000001a41480 R_PPC64_ADDR64    _binary__btf_vmlinux_bin_end"

whereas those relocations are legitimate even for a relocatable kernel
compiled with -pie option.

relocs_check.sh already excluded some weak unresolved symbols explicitly:
remove those hardcoded symbols and add some logic that parses the symbols
using nm, retrieves all the weak unresolved symbols and excludes those from
the list of the potential bad relocations.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200118170335.21440-1-alex@ghiti.fr
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/Makefile.postlink     |  4 ++--
 arch/powerpc/tools/relocs_check.sh | 20 ++++++++++++--------
 2 files changed, 14 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/Makefile.postlink b/arch/powerpc/Makefile.postlink
index 134f12f89b92b..2268396ff4bba 100644
--- a/arch/powerpc/Makefile.postlink
+++ b/arch/powerpc/Makefile.postlink
@@ -17,11 +17,11 @@ quiet_cmd_head_check = CHKHEAD $@
 quiet_cmd_relocs_check = CHKREL  $@
 ifdef CONFIG_PPC_BOOK3S_64
       cmd_relocs_check =						\
-	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@" ; \
+	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@" ; \
 	$(BASH) $(srctree)/arch/powerpc/tools/unrel_branch_check.sh "$(OBJDUMP)" "$@"
 else
       cmd_relocs_check =						\
-	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@"
+	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@"
 endif
 
 # `@true` prevents complaint when there is nothing to be done
diff --git a/arch/powerpc/tools/relocs_check.sh b/arch/powerpc/tools/relocs_check.sh
index 7b9fe0a567cf3..014e00e74d2b6 100755
--- a/arch/powerpc/tools/relocs_check.sh
+++ b/arch/powerpc/tools/relocs_check.sh
@@ -10,14 +10,21 @@
 # based on relocs_check.pl
 # Copyright © 2009 IBM Corporation
 
-if [ $# -lt 2 ]; then
-	echo "$0 [path to objdump] [path to vmlinux]" 1>&2
+if [ $# -lt 3 ]; then
+	echo "$0 [path to objdump] [path to nm] [path to vmlinux]" 1>&2
 	exit 1
 fi
 
-# Have Kbuild supply the path to objdump so we handle cross compilation.
+# Have Kbuild supply the path to objdump and nm so we handle cross compilation.
 objdump="$1"
-vmlinux="$2"
+nm="$2"
+vmlinux="$3"
+
+# Remove from the bad relocations those that match an undefined weak symbol
+# which will result in an absolute relocation to 0.
+# Weak unresolved symbols are of that form in nm output:
+# "                  w _binary__btf_vmlinux_bin_end"
+undef_weak_symbols=$($nm "$vmlinux" | awk '$1 ~ /w/ { print $2 }')
 
 bad_relocs=$(
 $objdump -R "$vmlinux" |
@@ -26,8 +33,6 @@ $objdump -R "$vmlinux" |
 	# These relocations are okay
 	# On PPC64:
 	#	R_PPC64_RELATIVE, R_PPC64_NONE
-	#	R_PPC64_ADDR64 mach_<name>
-	#	R_PPC64_ADDR64 __crc_<name>
 	# On PPC:
 	#	R_PPC_RELATIVE, R_PPC_ADDR16_HI,
 	#	R_PPC_ADDR16_HA,R_PPC_ADDR16_LO,
@@ -39,8 +44,7 @@ R_PPC_ADDR16_HI
 R_PPC_ADDR16_HA
 R_PPC_RELATIVE
 R_PPC_NONE' |
-	grep -E -v '\<R_PPC64_ADDR64[[:space:]]+mach_' |
-	grep -E -v '\<R_PPC64_ADDR64[[:space:]]+__crc_'
+	([ "$undef_weak_symbols" ] && grep -F -w -v "$undef_weak_symbols" || cat)
 )
 
 if [ -z "$bad_relocs" ]; then
-- 
2.20.1