linux.git/arch/powerpc/platforms/pseries, branch v5.4.30

powerpc/pseries/lparcfg: Fix display of Maximum Memory

2020-02-24T07:36:57+00:00

[ Upstream commit f1dbc1c5c70d0d4c60b5d467ba941fba167c12f6 ]

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

Signed-off-by: Michael Bringmann 
[mpe: Only n_lmbs needs casting to unsigned long]
Signed-off-by: Michael Ellerman 
Link: https://lore.kernel.org/r/5577aef8-1d5a-ca95-ff0a-9c7b5977e5bf@linux.ibm.com
Signed-off-by: Sasha Levin

powerpc/pseries: Allow not having ibm, hypertas-functions::hcall-multi-tce for DDW

2020-02-14T21:34:16+00:00

commit 7559d3d295f3365ea7ac0c0274c05e633fe4f594 upstream.

By default a pseries guest supports a H_PUT_TCE hypercall which maps
a single IOMMU page in a DMA window. Additionally the hypervisor may
support H_PUT_TCE_INDIRECT/H_STUFF_TCE which update multiple TCEs at once;
this is advertised via the device tree /rtas/ibm,hypertas-functions
property which Linux converts to FW_FEATURE_MULTITCE.

FW_FEATURE_MULTITCE is checked when dma_iommu_ops is used; however
the code managing the huge DMA window (DDW) ignores it and calls
H_PUT_TCE_INDIRECT even if it is explicitly disabled via
the "multitce=off" kernel command line parameter.

This adds FW_FEATURE_MULTITCE checking to the DDW code path.

This changes tce_build_pSeriesLP to take liobn and page size as
the huge window does not have iommu_table descriptor which usually
the place to store these numbers.

Fixes: 4e8b0cf46b25 ("powerpc/pseries: Add support for dynamic dma windows")
Signed-off-by: Alexey Kardashevskiy 
Reviewed-by: Thiago Jung Bauermann 
Tested-by: Thiago Jung Bauermann 
Signed-off-by: Michael Ellerman 
Link: https://lore.kernel.org/r/20191216041924.42318-3-aik@ozlabs.ru
Signed-off-by: Greg Kroah-Hartman

powerpc/pseries/vio: Fix iommu_table use-after-free refcount warning

2020-02-14T21:34:16+00:00

commit aff8c8242bc638ba57247ae1ec5f272ac3ed3b92 upstream.

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 
Reviewed-by: Alexey Kardashevskiy 
Signed-off-by: Michael Ellerman 
Link: https://lore.kernel.org/r/1579558202-26052-1-git-send-email-tyreld@linux.ibm.com
Signed-off-by: Greg Kroah-Hartman

powerpc/papr_scm: Fix leaking 'bus_desc.provider_name' in some paths

2020-02-14T21:34:16+00:00

commit 5649607a8d0b0e019a4db14aab3de1e16c3a2b4f upstream.

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 
Signed-off-by: Michael Ellerman 
Link: https://lore.kernel.org/r/20200122155140.120429-1-vaibhav@linux.ibm.com
Signed-off-by: Greg Kroah-Hartman

Revert "powerpc/pseries/iommu: Don't use dma_iommu_ops on secure guests"

2020-02-14T21:34:16+00:00

commit d862b44133b7a1d7de25288e09eabf4df415e971 upstream.

This reverts commit edea902c1c1efb855f77e041f9daf1abe7a9768a.

At the time the change allowed direct DMA ops for secure VMs; however
since then we switched on using SWIOTLB backed with IOMMU (direct mapping)
and to make this work, we need dma_iommu_ops which handles all cases
including TCE mapping I/O pages in the presence of an IOMMU.

Fixes: edea902c1c1e ("powerpc/pseries/iommu: Don't use dma_iommu_ops on secure guests")
Signed-off-by: Ram Pai 
[aik: added "revert" and "fixes:"]
Signed-off-by: Alexey Kardashevskiy 
Reviewed-by: Thiago Jung Bauermann 
Tested-by: Thiago Jung Bauermann 
Signed-off-by: Michael Ellerman 
Link: https://lore.kernel.org/r/20191216041924.42318-2-aik@ozlabs.ru
Signed-off-by: Greg Kroah-Hartman

powerpc/pseries: Advance pfn if section is not present in lmb_is_removable()

2020-02-11T12:35:17+00:00

commit fbee6ba2dca30d302efe6bddb3a886f5e964a257 upstream.

In lmb_is_removable(), if a section is not present, it should continue
to test the rest of the sections in the block. But the current code
fails to do so.

Fixes: 51925fb3c5c9 ("powerpc/pseries: Implement memory hotplug remove in the kernel")
Cc: stable@vger.kernel.org # v4.1+
Signed-off-by: Pingfan Liu 
Signed-off-by: Michael Ellerman 
Link: https://lore.kernel.org/r/1578632042-12415-1-git-send-email-kernelfans@gmail.com
Signed-off-by: Greg Kroah-Hartman

powerpc/vcpu: Assume dedicated processors as non-preempt

2020-01-12T11:21:29+00:00

commit 14c73bd344da60abaf7da3ea2e7733ddda35bbac upstream.

With commit 247f2f6f3c70 ("sched/core: Don't schedule threads on
pre-empted vCPUs"), the scheduler avoids preempted vCPUs to schedule
tasks on wakeup. This leads to wrong choice of CPU, which in-turn
leads to larger wakeup latencies. Eventually, it leads to performance
regression in latency sensitive benchmarks like soltp, schbench etc.

On Powerpc, vcpu_is_preempted() only looks at yield_count. If the
yield_count is odd, the vCPU is assumed to be preempted. However
yield_count is increased whenever the LPAR enters CEDE state (idle).
So any CPU that has entered CEDE state is assumed to be preempted.

Even if vCPU of dedicated LPAR is preempted/donated, it should have
right of first-use since they are supposed to own the vCPU.

On a Power9 System with 32 cores:
  # lscpu
  Architecture:        ppc64le
  Byte Order:          Little Endian
  CPU(s):              128
  On-line CPU(s) list: 0-127
  Thread(s) per core:  8
  Core(s) per socket:  1
  Socket(s):           16
  NUMA node(s):        2
  Model:               2.2 (pvr 004e 0202)
  Model name:          POWER9 (architected), altivec supported
  Hypervisor vendor:   pHyp
  Virtualization type: para
  L1d cache:           32K
  L1i cache:           32K
  L2 cache:            512K
  L3 cache:            10240K
  NUMA node0 CPU(s):   0-63
  NUMA node1 CPU(s):   64-127

  # perf stat -a -r 5 ./schbench
  v5.4                               v5.4 + patch
  Latency percentiles (usec)         Latency percentiles (usec)
        50.0000th: 45                      50.0th: 45
        75.0000th: 62                      75.0th: 63
        90.0000th: 71                      90.0th: 74
        95.0000th: 77                      95.0th: 78
        *99.0000th: 91                     *99.0th: 82
        99.5000th: 707                     99.5th: 83
        99.9000th: 6920                    99.9th: 86
        min=0, max=10048                   min=0, max=96
  Latency percentiles (usec)         Latency percentiles (usec)
        50.0000th: 45                      50.0th: 46
        75.0000th: 61                      75.0th: 64
        90.0000th: 72                      90.0th: 75
        95.0000th: 79                      95.0th: 79
        *99.0000th: 691                    *99.0th: 83
        99.5000th: 3972                    99.5th: 85
        99.9000th: 8368                    99.9th: 91
        min=0, max=16606                   min=0, max=117
  Latency percentiles (usec)         Latency percentiles (usec)
        50.0000th: 45                      50.0th: 46
        75.0000th: 61                      75.0th: 64
        90.0000th: 71                      90.0th: 75
        95.0000th: 77                      95.0th: 79
        *99.0000th: 106                    *99.0th: 83
        99.5000th: 2364                    99.5th: 84
        99.9000th: 7480                    99.9th: 90
        min=0, max=10001                   min=0, max=95
  Latency percentiles (usec)         Latency percentiles (usec)
        50.0000th: 45                      50.0th: 47
        75.0000th: 62                      75.0th: 65
        90.0000th: 72                      90.0th: 75
        95.0000th: 78                      95.0th: 79
        *99.0000th: 93                     *99.0th: 84
        99.5000th: 108                     99.5th: 85
        99.9000th: 6792                    99.9th: 90
        min=0, max=17681                   min=0, max=117
  Latency percentiles (usec)         Latency percentiles (usec)
        50.0000th: 46                      50.0th: 45
        75.0000th: 62                      75.0th: 64
        90.0000th: 73                      90.0th: 75
        95.0000th: 79                      95.0th: 79
        *99.0000th: 113                    *99.0th: 82
        99.5000th: 2724                    99.5th: 83
        99.9000th: 6184                    99.9th: 93
        min=0, max=9887                    min=0, max=111

   Performance counter stats for 'system wide' (5 runs):

  context-switches    43,373  ( +-  0.40% )   44,597 ( +-  0.55% )
  cpu-migrations       1,211  ( +-  5.04% )      220 ( +-  6.23% )
  page-faults         15,983  ( +-  5.21% )   15,360 ( +-  3.38% )

Waiman Long suggested using static_keys.

Fixes: 247f2f6f3c70 ("sched/core: Don't schedule threads on pre-empted vCPUs")
Cc: stable@vger.kernel.org # v4.18+
Reported-by: Parth Shah 
Reported-by: Ihor Pasichnyk 
Tested-by: Juri Lelli 
Acked-by: Waiman Long 
Reviewed-by: Gautham R. Shenoy 
Signed-off-by: Srikar Dronamraju 
Acked-by: Phil Auld 
Reviewed-by: Vaidyanathan Srinivasan 
Tested-by: Parth Shah 
[mpe: Move the key and setting of the key to pseries/setup.c]
Signed-off-by: Michael Ellerman 
Link: https://lore.kernel.org/r/20191213035036.6913-1-mpe@ellerman.id.au
Signed-off-by: Greg Kroah-Hartman

Revert "powerpc/vcpu: Assume dedicated processors as non-preempt"

2020-01-04T18:18:33+00:00

This reverts commit 8332dbe5157a0056d8ab409957dfa89930066d87 which is
commit 14c73bd344da60abaf7da3ea2e7733ddda35bbac upstream.

It breaks the build.

Cc: Guenter Roeck 
Cc: Parth Shah 
Cc: Ihor Pasichnyk 
Cc: Juri Lelli 
Cc: Waiman Long 
Cc: Gautham R. Shenoy 
Cc: Srikar Dronamraju 
Cc: Phil Auld 
Cc: Vaidyanathan Srinivasan 
Cc: Parth Shah 
Cc: Michael Ellerman 
Signed-off-by: Greg Kroah-Hartman

powerpc/pseries/cmm: Implement release() function for sysfs device

2020-01-04T18:17:51+00:00

[ Upstream commit 7d8212747435c534c8d564fbef4541a463c976ff ]

When unloading the module, one gets
  ------------[ cut here ]------------
  Device 'cmm0' does not have a release() function, it is broken and must be fixed. See Documentation/kobject.txt.
  WARNING: CPU: 0 PID: 19308 at drivers/base/core.c:1244 .device_release+0xcc/0xf0
  ...

We only have one static fake device. There is nothing to do when
releasing the device (via cmm_exit()).

Signed-off-by: David Hildenbrand 
Signed-off-by: Michael Ellerman 
Link: https://lore.kernel.org/r/20191031142933.10779-2-david@redhat.com
Signed-off-by: Sasha Levin

powerpc/papr_scm: Fix an off-by-one check in papr_scm_meta_{get, set}

2020-01-04T18:16:33+00:00

[ Upstream commit 612ee81b9461475b5a5612c2e8d71559dd3c7920 ]

A validation check to prevent out of bounds read/write inside
functions papr_scm_meta_{get,set}() is off-by-one that prevent reads
and writes to the last byte of the label area.

This bug manifests as a failure to probe a dimm when libnvdimm is
unable to read the entire config-area as advertised by
ND_CMD_GET_CONFIG_SIZE. This usually happens when there are large
number of namespaces created in the region backed by the dimm and the
label-index spans max possible config-area. An error of the form below
usually reported in the kernel logs:

[  255.293912] nvdimm: probe of nmem0 failed with error -22

The patch fixes these validation checks there by letting libnvdimm
access the entire config-area.

Fixes: 53e80bd042773('powerpc/nvdimm: Add support for multibyte read/write for metadata')
Signed-off-by: Vaibhav Jain 
Reviewed-by: Aneesh Kumar K.V 
Signed-off-by: Michael Ellerman 
Link: https://lore.kernel.org/r/20190927062002.3169-1-vaibhav@linux.ibm.com
Signed-off-by: Sasha Levin