| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
During an eeh event when the cxl card is fenced and card sysfs attr
perst_reloads_same_image is set following warning message is seen in the
kernel logs:
Adapter context unlocked with 0 active contexts
------------[ cut here ]------------
WARNING: CPU: 12 PID: 627 at
../drivers/misc/cxl/main.c:325 cxl_adapter_context_unlock+0x60/0x80 [cxl]
Even though this warning is harmless, it clutters the kernel log
during an eeh event. This warning is triggered as the EEH callback
cxl_pci_error_detected doesn't obtain a context-lock before forcibly
detaching all active context and when context-lock is released during
call to cxl_configure_adapter from cxl_pci_slot_reset, a warning in
cxl_adapter_context_unlock is triggered.
To fix this warning, we acquire the adapter context-lock via
cxl_adapter_context_lock() in the eeh callback
cxl_pci_error_detected() once all the virtual AFU PHBs are notified
and their contexts detached. The context-lock is released in
cxl_pci_slot_reset() after the adapter is successfully reconfigured
and before the we call the slot_reset callback on slice attached
device-drivers.
Fixes: 70b565bbdb91 ("cxl: Prevent adapter reset if an active context exists")
Cc: [email protected] # v4.9+
Reported-by: Andrew Donnellan <[email protected]>
Signed-off-by: Vaibhav Jain <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Reviewed-by: Matthew R. Ochs <[email protected]>
Tested-by: Uma Krishnan <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
Add support for future IBM Coherent Accelerator (CXL) devices
with an IDs of 0x0623 and 0x0628.
Signed-off-by: Matthew R. Ochs <[email protected]>
Signed-off-by: Uma Krishnan <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
The new Coherent Accelerator Interface Architecture, level 2, for the
IBM POWER9 brings new content and features:
- POWER9 Service Layer
- Registers
- Radix mode
- Process element entry
- Dedicated-Shared Process Programming Model
- Translation Fault Handling
- CAPP
- Memory Context ID
If a valid mm_struct is found the memory context id is used for each
transaction associated with the process handle. The PSL uses the
context ID to find the corresponding process element.
Signed-off-by: Christophe Lombard <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
[mpe: Fixup comment formatting, unsplit long strings]
Signed-off-by: Michael Ellerman <[email protected]>
|
|
Point out the specific Coherent Accelerator Interface Architecture,
level 1, registers.
Code and functions specific to PSL8 (CAIA1) must be framed.
Signed-off-by: Christophe Lombard <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
[mpe: Don't split long strings, it makes them hard to grep for]
Signed-off-by: Michael Ellerman <[email protected]>
|
|
Rename a few functions, changing the '_psl' suffix to '_psl8', to make
clear that the implementation is psl8 specific.
Those functions will have an equivalent implementation for the psl9 in
a later patch.
Signed-off-by: Christophe Lombard <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
The service layer API (in cxl.h) lists some low-level functions whose
implementation is different on PSL8, PSL9 and XSL:
- Init implementation for the adapter and the afu.
- Invalidate TLB/SLB.
- Attach process for dedicated/directed models.
- Handle psl interrupts.
- Debug registers for the adapter and the afu.
- Traces.
Each environment implements its own functions, and the common code uses
them through function pointers, defined in cxl_service_layer_ops.
Signed-off-by: Christophe Lombard <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
The mm_struct corresponding to the current task is acquired each time
an interrupt is raised. So to simplify the code, we only get the
mm_struct when attaching an AFU context to the process.
The mm_count reference is increased to ensure that the mm_struct can't
be freed. The mm_struct will be released when the context is detached.
A reference on mm_users is not kept to avoid a circular dependency if
the process mmaps its cxl mmio and forget to unmap before exiting.
The field glpid (pid of the group leader associated with the pid), of
the structure cxl_context, is removed because it's no longer useful.
Signed-off-by: Christophe Lombard <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
The two previously fields pid and tid, located in the structure
cxl_irq_info, are only used in the guest environment. To avoid confusion,
it's not necessary to fill the fields in the bare-metal environment.
Pid_tid is now renamed to 'reserved' to avoid undefined behavior on
bare-metal. The PSL Process and Thread Identification Register
(CXL_PSL_PID_TID_An) is only used when attaching a dedicated process
for PSL8 only. This register goes away in CAIA2.
Signed-off-by: Christophe Lombard <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
This bit is used to cause a flash image load for programmable
CAIA-compliant implementation. If this bit is set to ‘0’, a power
cycle of the adapter is required to load a programmable CAIA-com-
pliant implementation from flash.
This field will be used by the following patches.
Signed-off-by: Christophe Lombard <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
This patch fix some spelling typos found in printk.
[[email protected]: drop arch/arm64/kernel/hibernate.c that was already
in place]
Signed-off-by: Masanari Iida <[email protected]>
Acked-by: Randy Dunlap <[email protected]>
Signed-off-by: Jiri Kosina <[email protected]>
|
|
Fix a boundary condition where in some cases an eeh event with state ==
pci_channel_io_perm_failure wont be passed on to a driver attached to
the virtual PCI device associated with a slice. This will happen in case
the slice just before (n-1) doesn't have any vPHB bus associated with
it, that results in an early return from cxl_pci_error_detected()
callback.
With state == pci_channel_io_perm_failure, the adapter will be removed
irrespective of the return value of cxl_vphb_error_detected(). So we now
always return PCI_ERS_RESULT_DISCONNECTED for this case i.e even if
the AFU isn't using a vPHB (currently returns PCI_ERS_RESULT_NONE).
Fixes: e4f5fc001a6("cxl: Do not create vPHB if there are no AFU configuration records")
Signed-off-by: Vaibhav Jain <[email protected]>
Reviewed-by: Matthew R. Ochs <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
related APIs from <linux/sched.h> to <linux/sched/task.h>
But first update usage sites with the new header dependency.
Acked-by: Linus Torvalds <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
<linux/sched.h> into <linux/sched/signal.h>
Fix up affected files that include this signal functionality via sched.h.
Acked-by: Linus Torvalds <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
<linux/sched/mm.h>
We are going to split <linux/sched/mm.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.
Create a trivial placeholder <linux/sched/mm.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.
The APIs that are going to be moved first are:
mm_alloc()
__mmdrop()
mmdrop()
mmdrop_async_fn()
mmdrop_async()
mmget_not_zero()
mmput()
mmput_async()
get_task_mm()
mm_access()
mm_release()
Include the new header in the files that are going to need it.
Acked-by: Linus Torvalds <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
<linux/sched/clock.h>
We are going to split <linux/sched/clock.h> out of <linux/sched.h>, which
will have to be picked up from other headers and .c files.
Create a trivial placeholder <linux/sched/clock.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.
Include the new header in the files that are going to need it.
Acked-by: Linus Torvalds <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull more powerpc updates from Michael Ellerman:
"Highlights include:
- an update of the disassembly code used by xmon to the latest
versions in binutils. We've received permission from all the
authors of the relevant binutils changes to relicense their changes
to the relevant files from GPLv3 to GPLv2, for inclusion in Linux.
Thanks to Peter Bergner for doing the leg work to get permission
from everyone.
- addition of the "architected" Power9 CPU table entry, allowing us
to boot in Power9 architected mode under a hypervisor.
- updates to the Power9 PMU code.
- implementation of clear_bit_unlock_is_negative_byte() to optimise
unlock_page().
- Freescale updates from Scott: "Highlights include 8xx breakpoints
and perf, t1042rdb display support, and board updates."
Thanks to:
Al Viro, Andrew Donnellan, Aneesh Kumar K.V, Balbir Singh, Douglas
Miller, Frédéric Weisbecker, Gavin Shan, Madhavan Srinivasan,
Michael Roth, Nathan Fontenot, Naveen N. Rao, Nicholas Piggin, Peter
Bergner, Paul E. McKenney, Rashmica Gupta, Russell Currey, Sahil
Mehta, Stewart Smith"
* tag 'powerpc-4.11-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (48 commits)
powerpc: Remove leftover cputime_to_nsecs call causing build error
powerpc/mm/hash: Always clear UPRT and Host Radix bits when setting up CPU
powerpc/optprobes: Fix TOC handling in optprobes trampoline
powerpc/pseries: Advertise Hot Plug Event support to firmware
cxl: fix nested locking hang during EEH hotplug
powerpc/xmon: Dump memory in CPU endian format
powerpc/pseries: Revert 'Auto-online hotplugged memory'
powerpc/powernv: Make PCI non-optional
powerpc/64: Implement clear_bit_unlock_is_negative_byte()
powerpc/powernv: Remove unused variable in pnv_pci_sriov_disable()
powerpc/kernel: Remove error message in pcibios_setup_phb_resources()
powerpc/mm: Fix typo in set_pte_at()
pci/hotplug/pnv-php: Disable MSI and PCI device properly
pci/hotplug/pnv-php: Disable surprise hotplug capability on conflicts
pci/hotplug/pnv-php: Remove WARN_ON() in pnv_php_put_slot()
powerpc: Add POWER9 architected mode to cputable
powerpc/perf: use is_kernel_addr macro in perf_get_misc_flags()
powerpc/perf: Avoid FAB_*_MATCH checks for power9
powerpc/perf: Add restrictions to PMC5 in power9 DD1
powerpc/perf: Use Instruction Counter value
...
|
|
->fault(), ->page_mkwrite(), and ->pfn_mkwrite() calls do not need to
take a vma and vmf parameter when the vma already resides in vmf.
Remove the vma parameter to simplify things.
[[email protected]: fix ARM build]
Link: http://lkml.kernel.org/r/[email protected]
Link: http://lkml.kernel.org/r/148521301778.19116.10840599906674778980.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Dave Jiang <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
Reviewed-by: Ross Zwisler <[email protected]>
Cc: Theodore Ts'o <[email protected]>
Cc: Darrick J. Wong <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: Jan Kara <[email protected]>
Cc: Dan Williams <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
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: [email protected] # v4.9+
Signed-off-by: Andrew Donnellan <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
Stub out the debugfs functions so that the build doesn't break when
CONFIG_DEBUG_FS=n.
Reported-by: Michael Ellerman <[email protected]>
Signed-off-by: Andrew Donnellan <[email protected]>
Acked-by: Ian Munsie <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
During EEH recovery, we deconfigure all AFUs whilst leaving the
corresponding vPHB and virtual PCI device in place.
If something attempts to interact with the AFU's PCI config space (e.g.
running lspci) after the AFU has been deconfigured and before it's
reconfigured, cxl_pcie_{read,write}_config() will read invalid values from
the deconfigured struct cxl_afu and proceed to Oops when they try to
dereference pointers that have been set to NULL during deconfiguration.
Add a rwsem to struct cxl_afu so we can prevent interaction with config
space while the AFU is deconfigured.
Reported-by: Pradipta Ghosh <[email protected]>
Suggested-by: Frederic Barrat <[email protected]>
Cc: [email protected] # v4.9+
Signed-off-by: Andrew Donnellan <[email protected]>
Signed-off-by: Vaibhav Jain <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
This change adds a force psl data cache flush during device shutdown
callback. This should reduce a possibility of psl holding a dirty
cache line while the CAPP is being reinitialized, which may result in
a UE [load/store] machine check error.
Signed-off-by: Vaibhav Jain <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
The kernel API does not use anything from this header file.
Signed-off-by: Greg Kurz <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
"Highlights include:
- Support for the kexec_file_load() syscall, which is a prereq for
secure and trusted boot.
- Prevent kernel execution of userspace on P9 Radix (similar to
SMEP/PXN).
- Sort the exception tables at build time, to save time at boot, and
store them as relative offsets to save space in the kernel image &
memory.
- Allow building the kernel with thin archives, which should allow us
to build an allyesconfig once some other fixes land.
- Build fixes to allow us to correctly rebuild when changing the
kernel endian from big to little or vice versa.
- Plumbing so that we can avoid doing a full mm TLB flush on P9
Radix.
- Initial stack protector support (-fstack-protector).
- Support for dumping the radix (aka. Linux) and hash page tables via
debugfs.
- Fix an oops in cxl coredump generation when cxl_get_fd() is used.
- Freescale updates from Scott: "Highlights include 8xx hugepage
support, qbman fixes/cleanup, device tree updates, and some misc
cleanup."
- Many and varied fixes and minor enhancements as always.
Thanks to:
Alexey Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V, Anshuman
Khandual, Anton Blanchard, Balbir Singh, Bartlomiej Zolnierkiewicz,
Christophe Jaillet, Christophe Leroy, Denis Kirjanov, Elimar
Riesebieter, Frederic Barrat, Gautham R. Shenoy, Geliang Tang, Geoff
Levand, Jack Miller, Johan Hovold, Lars-Peter Clausen, Libin,
Madhavan Srinivasan, Michael Neuling, Nathan Fontenot, Naveen N.
Rao, Nicholas Piggin, Pan Xinhui, Peter Senna Tschudin, Rashmica
Gupta, Rui Teng, Russell Currey, Scott Wood, Simon Guo, Suraj
Jitindar Singh, Thiago Jung Bauermann, Tobias Klauser, Vaibhav Jain"
[ And thanks to Michael, who took time off from a new baby to get this
pull request done. - Linus ]
* tag 'powerpc-4.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (174 commits)
powerpc/fsl/dts: add FMan node for t1042d4rdb
powerpc/fsl/dts: add sg_2500_aqr105_phy4 alias on t1024rdb
powerpc/fsl/dts: add QMan and BMan nodes on t1024
powerpc/fsl/dts: add QMan and BMan nodes on t1023
soc/fsl/qman: test: use DEFINE_SPINLOCK()
powerpc/fsl-lbc: use DEFINE_SPINLOCK()
powerpc/8xx: Implement support of hugepages
powerpc: get hugetlbpage handling more generic
powerpc: port 64 bits pgtable_cache to 32 bits
powerpc/boot: Request no dynamic linker for boot wrapper
soc/fsl/bman: Use resource_size instead of computation
soc/fsl/qe: use builtin_platform_driver
powerpc/fsl_pmc: use builtin_platform_driver
powerpc/83xx/suspend: use builtin_platform_driver
powerpc/ftrace: Fix the comments for ftrace_modify_code
powerpc/perf: macros for power9 format encoding
powerpc/perf: power9 raw event format encoding
powerpc/perf: update attribute_group data structure
powerpc/perf: factor out the event format field
powerpc/mm/iommu, vfio/spapr: Put pages on VFIO container shutdown
...
|
|
Every single user of vmf->virtual_address typed that entry to unsigned
long before doing anything with it so the type of virtual_address does
not really provide us any additional safety. Just use masked
vmf->address which already has the appropriate type.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Jan Kara <[email protected]>
Acked-by: Kirill A. Shutemov <[email protected]>
Cc: Dan Williams <[email protected]>
Cc: Ross Zwisler <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Drop duplicate header sched.h from native.c.
Signed-off-by: Geliang Tang <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
Fix the following coccinelle warnings:
drivers/misc/cxl/debugfs.c:46:0-23: WARNING: fops_io_x64 should be
defined with DEFINE_DEBUGFS_ATTRIBUTE
drivers/misc/cxl/guest.c:890:5-26: WARNING: Comparison to bool
drivers/misc/cxl/irq.c:107:3-23: WARNING: Assignment of bool to 0/1
drivers/misc/cxl/native.c:57:2-3: Unneeded semicolon
drivers/misc/cxl/native.c:170:2-3: Unneeded semicolon
Signed-off-by: Andrew Donnellan <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Reviewed-by: Matthew R. Ochs <[email protected]>
Acked-by: Ian Munsie <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
If a process dumps core while owning a cxl file descriptor obtained
from an AFU driver (e.g. cxlflash) through the cxl_get_fd() API, the
following error occurs:
[ 868.027591] Unable to handle kernel paging request for data at address ...
[ 868.027778] Faulting instruction address: 0xc00000000035edb0
cpu 0x8c: Vector: 300 (Data Access) at [c000003c688275e0]
pc: c00000000035edb0: elf_core_dump+0xd60/0x1300
lr: c00000000035ed80: elf_core_dump+0xd30/0x1300
sp: c000003c68827860
msr: 9000000100009033
dar: c
dsisr: 40000000
current = 0xc000003c68780000
paca = 0xc000000001b73200 softe: 0 irq_happened: 0x01
pid = 46725, comm = hxesurelock
enter ? for help
[c000003c68827a60] c00000000036948c do_coredump+0xcec/0x11e0
[c000003c68827c20] c0000000000ce9e0 get_signal+0x540/0x7b0
[c000003c68827d10] c000000000017354 do_signal+0x54/0x2b0
[c000003c68827e00] c00000000001777c do_notify_resume+0xbc/0xd0
[c000003c68827e30] c000000000009838 ret_from_except_lite+0x64/0x68
--- Exception: 300 (Data Access) at 00003fff98ad2918
The root cause is that the address_space structure for the file
doesn't define a 'host' member.
When cxl allocates a file descriptor, it's using the anonymous inode
to back the file, but allocates a private address_space for each
context. The private address_space allows to track memory allocation
for each context. cxl doesn't define the 'host' member of the address
space, i.e. the inode. We don't want to define it as the anonymous
inode, since there's no longer a 1-to-1 relation between address_space
and inode.
To fix it, instead of using the anonymous inode, we introduce a simple
pseudo filesystem so that cxl can allocate its own inodes. So we now
have one inode for each file and address_space. The pseudo filesystem
is only mounted on the first allocation of a file descriptor by
cxl_get_fd().
Tested with cxlflash.
Signed-off-by: Frederic Barrat <[email protected]>
Reviewed-by: Matthew R. Ochs <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
If an afu interrupt is in flight when an eeh error is triggered the
control still reaches the function native_irq_multiplexed and the
PE-Handle read from the CXL_PSL_PEHandle_An register is 0xffff. The
function then erroneously assumes that the interrupt belonged to a
detached context and generates a warning with full stack dump in the
kernel log complaining:
"Unable to demultiplex CXL PSL IRQ for PE 65535 DSISR ffffffff DAR
ffffffff. (Possible AFU HW issue - was a term/remove acked with
outstanding transactions"
To fix this the patch adds new code to the function
native_irq_multiplexed function to compares the read value of register
CXL_PSL_PEHandle_An to ~0ULL. If true then logs a warning message
saying that the interrupt is being ignored and returns IRQ_HANDLED from
the irq handler.
Reviewed-by: Andrew Donnellan <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Acked-by: Ian Munsie <[email protected]>
Signed-off-by: Vaibhav Jain <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
'cxl_dev_context_init()' returns an error pointer in case of error, not
NULL. So test it with IS_ERR.
Signed-off-by: Christophe JAILLET <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Acked-by: Ian Munsie <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
'cxl_dev_context_init()' returns an error pointer in case of error, not
NULL. So test it with IS_ERR.
Signed-off-by: Christophe JAILLET <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Acked-by: Ian Munsie <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
'cxl_context_alloc()' does not return an error pointer. It is just a
shortcut for a call to 'kzalloc' with 'sizeof(struct cxl_context)' as the
size parameter.
So its return value should be compared with NULL.
While fixing it, simplify a bit the code.
Signed-off-by: Christophe JAILLET <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Acked-by: Ian Munsie <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
In some error paths in functions cxl_start_context and
afu_ioctl_start_work pid references to the current & group-leader tasks
can leak after they are taken. This patch fixes these error paths to
release these pid references before exiting the error path.
Fixes: 7b8ad495d592 ("cxl: Fix DSI misses when the context owning task exits")
Cc: [email protected] # v4.5+
Reviewed-by: Andrew Donnellan <[email protected]>
Reported-by: Frederic Barrat <[email protected]>
Signed-off-by: Vaibhav Jain <[email protected]>
Acked-by: Frederic Barrat <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
This patch prevents resetting the cxl adapter via sysfs in presence of
one or more active cxl_context on it. This protects against an
unrecoverable error caused by PSL owning a dirty cache line even after
reset and host tries to touch the same cache line. In case a force reset
of the card is required irrespective of any active contexts, the int
value -1 can be stored in the 'reset' sysfs attribute of the card.
The patch introduces a new atomic_t member named contexts_num inside
struct cxl that holds the number of active context attached to the card
, which is checked against '0' before proceeding with the reset. To
prevent against a race condition where a context is activated just after
reset check is performed, the contexts_num is atomically set to '-1'
after reset-check to indicate that no more contexts can be activated on
the card anymore.
Before activating a context we atomically test if contexts_num is
non-negative and if so, increment its value by one. In case the value of
contexts_num is negative then it indicates that the card is about to be
reset and context activation is error-ed out at that point.
Fixes: 62fa19d4b4fd ("cxl: Add ability to reset the card")
Cc: [email protected] # v4.0+
Acked-by: Frederic Barrat <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Signed-off-by: Vaibhav Jain <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
Rewrite the cxl_guest_init_afu() loop in cxl_of_probe() to use
for_each_child_of_node() rather than a hand-coded for loop.
Remove the useless of_node_put(afu_np) call after the loop, where it's
guaranteed that afu_np == NULL.
Reported-by: SF Markus Elfring <[email protected]>
Reported-by: Julia Lawall <[email protected]>
Signed-off-by: Andrew Donnellan <[email protected]>
Reviewed-by: Frederic Barrat <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
If the capi link is going down while the PSL owns a dirty cache line,
any access from the host for that data could lead to an Uncorrectable
Error.
So when resetting the capi adapter through sysfs, make sure the PSL
cache is flushed. It won't help if there are any active Process
Elements on the card, as the cache would likely get new dirty cache
lines immediately, but if resetting an idle adapter, it should avoid
any bad surprises from data left over from terminated Process Elements.
Signed-off-by: Frederic Barrat <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Acked-by: Ian Munsie <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
When set_sl_ops() is called, the adapter data structure is not fully
initialized yet. Therefore the device name is not showing up in the
trace. Fix is simply to get the device name from the pci_dev
structure.
Fixes: 6d382616ac22 ("cxl: Abstract the differences between the PSL and XSL")
Signed-off-by: Frederic Barrat <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
When cxl removes a vPHB, it's possible that the pci_controller may be freed
before all references to the devices on the vPHB have been released. This
in turn causes an invalid memory access when the devices are eventually
released, as pcibios_release_device() attempts to call the phb's
release_device hook.
In cxl_pci_vphb_remove(), remove the existing call to
pcibios_free_controller(). Instead, use
pcibios_free_controller_deferred() to free the pci_controller after all
devices have been released. Export pci_set_host_bridge_release() so we can
do this.
Cc: [email protected]
Signed-off-by: Andrew Donnellan <[email protected]>
Reviewed-by: Matthew R. Ochs <[email protected]>
Acked-by: Ian Munsie <[email protected]>
Signed-off-by: Benjamin Herrenschmidt <[email protected]>
|
|
Switch the setting of psl_fir_cntl from debug to production
environment recommended value. It mostly affects the PSL behavior when
an error is raised in psl_fir1/2.
Tested with cxlflash.
Signed-off-by: Frederic Barrat <[email protected]>
Reviewed-by: Uma Krishnan <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
Make native_irq_wait() static and use NULL rather than 0 to initialise
phb->cfg_data in cxl_pci_vphb_add() to remove sparse warnings.
Signed-off-by: Andrew Donnellan <[email protected]>
Reviewed-by: Matthew R. Ochs <[email protected]>
Acked-by: Ian Munsie <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
Commit f67a6722d650 ("cxl: Workaround PE=0 hardware limitation in
Mellanox CX4") added a "min_pe" field to struct cxl_service_layer_ops,
to allow us to work around a Mellanox CX-4 hardware limitation.
When allocating the PE number in cxl_context_init(), we read from
ctx->afu->adapter->native->sl_ops->min_pe to get the minimum PE number.
Unsurprisingly, in a PowerVM guest ctx->afu->adapter->native is NULL,
and guests don't have a cxl_service_layer_ops struct anywhere.
Move min_pe from struct cxl_service_layer_ops to struct cxl so it's
accessible in both native and PowerVM environments. For the Mellanox
CX-4, set the min_pe value in set_sl_ops().
Fixes: f67a6722d650 ("cxl: Workaround PE=0 hardware limitation in Mellanox CX4")
Reported-by: Frederic Barrat <[email protected]>
Signed-off-by: Andrew Donnellan <[email protected]>
Acked-by: Ian Munsie <[email protected]>
Reviewed-by: Frederic Barrat <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
If kzalloc() fails when allocating adapter->guest in
cxl_guest_init_adapter(), we call free_adapter() before erroring out.
free_adapter() in turn attempts to dereference adapter->guest, which in
this case is NULL.
In free_adapter(), skip the adapter->guest cleanup if adapter->guest is
NULL.
Fixes: 14baf4d9c739 ("cxl: Add guest-specific code")
Reported-by: Dan Carpenter <[email protected]>
Signed-off-by: Andrew Donnellan <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
Remove the CXL_KERNEL_API and CXL_EEH Kconfig options, as they were only
needed to coordinate the merging of the cxlflash driver. Also remove the
stub implementation of cxl_perst_reloads_same_image() in cxlflash which is
only used if CXL_EEH isn't defined (i.e. never).
Suggested-by: Ian Munsie <[email protected]>
Signed-off-by: Andrew Donnellan <[email protected]>
Acked-by: Ian Munsie <[email protected]>
Acked-by: Matthew R. Ochs <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
Add a new API, cxl_check_and_switch_mode() to allow for switching of
bi-modal CAPI cards, such as the Mellanox CX-4 network card.
When a driver requests to switch a card to CAPI mode, use PCI hotplug
infrastructure to remove all PCI devices underneath the slot. We then write
an updated mode control register to the CAPI VSEC, hot reset the card, and
reprobe the card.
As the card may present a different set of PCI devices after the mode
switch, use the infrastructure provided by the pnv_php driver and the OPAL
PCI slot management facilities to ensure that:
* the old devices are removed from both the OPAL and Linux device trees
* the new devices are probed by OPAL and added to the OPAL device tree
* the new devices are added to the Linux device tree and probed through
the regular PCI device probe path
As such, introduce a new option, CONFIG_CXL_BIMODAL, with a dependency on
the pnv_php driver.
Refactor existing code that touches the mode control register in the
regular single mode case into a new function, setup_cxl_protocol_area().
Co-authored-by: Ian Munsie <[email protected]>
Cc: Gavin Shan <[email protected]>
Signed-off-by: Andrew Donnellan <[email protected]>
Signed-off-by: Ian Munsie <[email protected]>
Reviewed-by: Gavin Shan <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
The CX4 card cannot cope with a context with PE=0 due to a hardware
limitation, resulting in:
[ 34.166577] command failed, status limits exceeded(0x8), syndrome 0x5a7939
[ 34.166580] mlx5_core 0000:01:00.1: Failed allocating uar, aborting
Since the kernel API allocates a default context very early during
device init that will almost certainly get Process Element ID 0 there is
no easy way for us to extend the API to allow the Mellanox to inform us
of this limitation ahead of time.
Instead, work around the issue by extending the XSL structure to include
a minimum PE to allocate. Although the bug is not in the XSL, it is the
easiest place to work around this limitation given that the CX4 is
currently the only card that uses an XSL.
Signed-off-by: Ian Munsie <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Reviewed-by: Frederic Barrat <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
The Mellanox CX4 in cxl mode uses a hybrid interrupt model, where
interrupts are routed from the networking hardware to the XSL using the
MSIX table, and from there will be transformed back into an MSIX
interrupt using the cxl style interrupts (i.e. using IVTE entries and
ranges to map a PE and AFU interrupt number to an MSIX address).
We want to hide the implementation details of cxl interrupts as much as
possible. To this end, we use a special version of the MSI setup &
teardown routines in the PHB while in cxl mode to allocate the cxl
interrupts and configure the IVTE entries in the process element.
This function does not configure the MSIX table - the CX4 card uses a
custom format in that table and it would not be appropriate to fill that
out in generic code. The rest of the functionality is similar to the
"Full MSI-X mode" described in the CAIA, and this could be easily
extended to support other adapters that use that mode in the future.
The interrupts will be associated with the default context. If the
maximum number of interrupts per context has been limited (e.g. by the
mlx5 driver), it will automatically allocate additional kernel contexts
to associate extra interrupts as required. These contexts will be
started using the same WED that was used to start the default context.
Signed-off-by: Ian Munsie <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
The Mellanox CX4 has a hardware limitation where only 4 bits of the
AFU interrupt number can be passed to the XSL when sending an interrupt,
limiting it to only 15 interrupts per context (AFU interrupt number 0 is
invalid).
In order to overcome this, we will allocate additional contexts linked
to the default context as extra address space for the extra interrupts -
this will be implemented in the next patch.
This patch adds the preliminary support to allow this, by way of adding
a linked list in the context structure that we use to keep track of the
contexts dedicated to interrupts, and an API to simultaneously iterate
over the related context structures, AFU interrupt numbers and hardware
interrupt numbers. The point of using a single API to iterate these is
to hide some of the details of the iteration from external code, and to
reduce the number of APIs that need to be exported via base.c to allow
built in code to call.
Signed-off-by: Ian Munsie <[email protected]>
Reviewed-by: Frederic Barrat <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
These APIs will be used by the Mellanox CX4 support. While they function
standalone to configure existing behaviour, their primary purpose is to
allow the Mellanox driver to inform the cxl driver of a hardware
limitation, which will be used in a future patch.
Signed-off-by: Ian Munsie <[email protected]>
Reviewed-by: Frederic Barrat <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
This hooks up support for using the kernel API with a real PHB. After
the AFU initialisation has completed it calls into the PHB code to pass
it the AFU that will be used by other peer physical functions on the
adapter.
The cxl_pci_to_afu API is extended to work with peer PCI devices,
retrieving the peer AFU from the PHB. This API may also now return an
error if it is called on a PCI device that is not associated with either
a cxl vPHB or a peer PCI device to an AFU, and this error is propagated
down.
Signed-off-by: Ian Munsie <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
The vPHB model of the cxl kernel API is a hierarchy where the AFU is
represented by the vPHB, and it's AFU configuration records are exposed
as functions under that vPHB. If there are no AFU configuration records
we will create a vPHB with nothing under it, which is a waste of
resources and will opt us into EEH handling despite not having anything
special to handle.
This also does not make sense for cards using the peer model of the cxl
kernel API, where the other functions of the device are exposed via
additional peer physical functions rather than AFU configuration
records. This model will also not work with the existing EEH handling in
the cxl driver, as that is designed around the vPHB model.
Skip creating the vPHB for AFUs without any AFU configuration records,
and opt out of EEH handling for them.
Signed-off-by: Ian Munsie <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|
|
The cxl kernel API has a concept of a default context associated with
each PCI device under the virtual PHB. The Mellanox CX4 will also use
the cxl kernel API, but it does not use a virtual PHB - rather, the AFU
appears as a physical function as a peer to the networking functions.
In order to allow the kernel API to work with those networking
functions, we will need to associate a default context with them as
well. To this end, refactor the corresponding code to do this in vphb.c
and export it so that it can be called from the PHB code.
Signed-off-by: Ian Munsie <[email protected]>
Reviewed-by: Frederic Barrat <[email protected]>
Reviewed-by: Andrew Donnellan <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
|