Age | Commit message (Collapse) | Author | Files | Lines |
|
The hypervisor assigns VAS (Virtual Accelerator Switchboard)
windows depends on cores configured in LPAR. The kernel uses
OF reconfig notifier to reconfig VAS windows for DLPAR CPU event.
In the case of shared CPU mode partition, the hypervisor assigns
VAS windows depends on CPU entitled capacity, not based on vcpus.
When the user changes CPU entitled capacity for the partition,
drmgr uses /proc/ppc64/lparcfg interface to notify the kernel.
This patch adds the following changes to update VAS resources
for shared mode:
- Call vas reconfig windows from lparcfg_write()
- Ignore reconfig changes in the VAS notifier
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
[mpe: Rework error handling, report any errors as EIO]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/efa9c16e4a78dda4567a16f13dabfd73cb4674a2.camel@linux.ibm.com
|
|
irq_default_primary_handler() can be used only with IRQF_ONESHOT
flag, but the flag disables IRQ before executing the thread handler
and enables it after the interrupt is handled. But this IRQ disable
sets the VAS IRQ OFF state in the hypervisor. In case if NX faults
during this window, the hypervisor will not deliver the fault
interrupt to the partition and the user space may wait continuously
for the CSB update. So use VAS specific IRQ handler instead of
calling the default primary handler.
Increment pending_faults counter in IRQ handler and the bottom
thread handler will process all faults based on this counter.
In case if the another interrupt is received while the thread is
running, it will be processed using this counter. The synchronization
of top and bottom handlers will be done with IRQTF_RUNTHREAD flag
and will re-enter to bottom half if this flag is set.
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
Reviewed-by: Frederic Barrat <fbarrat@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/aaad8813b4762a6753cfcd0b605a7574a5192ec7.camel@linux.ibm.com
|
|
The recently moved dtl code must be compiled-in if
CONFIG_VIRT_CPU_ACCOUNTING_NATIVE=y even if CONFIG_DTL=n.
Fixes: 6ba5aa541aaa0 ("powerpc/pseries: Move dtl scanning and steal time accounting to pseries platform")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221013073131.1485742-1-npiggin@gmail.com
|
|
Add firmware version details to the hardware description, which is
printed at boot and in case of an oops.
Use /hypervisor if we find it, though currently it only exists if we're
running under qemu.
Look for "ibm,powervm-partition" which is specified in PAPR+ v2.11 and
tells us we're running under PowerVM.
Failing that look for "ibm,fw-net-version" which is seen on PowerVM
going back to at least Power6.
eg: Hardware name: ... of:IBM,FW860.42 (SV860_138) hv:phyp
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220930082709.55830-6-mpe@ellerman.id.au
|
|
Generally the hypervisor decides to allocate a window on different
VAS instances. But if user space wishes to allocate on the current VAS
instance where the process is executing, the kernel has to pass
associativity domain IDs to allocate VAS window HCALL.
To determine the associativity domain IDs for the current CPU,
smp_processor_id() is passed to node associativity HCALL which may
return H_P2 (-55) error during DLPAR CPU event. This is because Linux
CPU numbers (smp_processor_id()) are not the same as the hypervisor's
view of CPU numbers.
Fix the issue by passing hard_smp_processor_id() with
VPHN_FLAG_VCPU flag (PAPR 14.11.6.1 H_HOME_NODE_ASSOCIATIVITY).
Fixes: b22f2d88e435 ("powerpc/pseries/vas: Integrate API with open/close windows")
Reviewed-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
[mpe: Update change log to mention Linux vs HV CPU numbers]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/55380253ea0c11341824cd4c0fc6bbcfc5752689.camel@linux.ibm.com
|
|
Return the value vas_register_coproc_api() directly instead of storing it
in another redundant variable.
Reported-by: Zeal Robot <zealci@zte.com.cn>
Signed-off-by: ye xingchen <ye.xingchen@zte.com.cn>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220825072657.229168-1-ye.xingchen@zte.com.cn
|
|
The /proc/powerpc/ofdt interface allows the root user to freely alter
the in-kernel device tree, enabling arbitrary physical address writes
via drivers that could bind to malicious device nodes, thus making it
possible to disable lockdown.
Historically this interface has been used on the pseries platform to
facilitate the runtime addition and removal of processor, memory, and
device resources (aka Dynamic Logical Partitioning or DLPAR). Years
ago, the processor and memory use cases were migrated to designs that
happen to be lockdown-friendly: device tree updates are communicated
directly to the kernel from firmware without passing through untrusted
user space. I/O device DLPAR via the "drmgr" command in powerpc-utils
remains the sole legitimate user of /proc/powerpc/ofdt, but it is
already broken in lockdown since it uses /dev/mem to allocate argument
buffers for the rtas syscall. So only illegitimate uses of the
interface should see a behavior change when running on a locked down
kernel.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Acked-by: Paul Moore <paul@paul-moore.com> (LSM)
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220926131643.146502-2-nathanl@linux.ibm.com
|
|
When the migration is initiated, the hypervisor changes VAS
mappings as part of pre-migration event. Then the OS gets the
migration event which closes all VAS windows before the migration
starts. NX generates continuous faults until windows are closed
and the user space can not differentiate these NX faults coming
from the actual migration. So to reduce this time window, close
VAS windows first in pseries_migrate_partition().
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
Reviewed-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/d8efade91dda831c9ed4abb226dab627da594c5f.camel@linux.ibm.com
|
|
The .toc section is not really intended for arbitrary data. Writable
data in particular prevents making the TOC read-only after relocation.
Move hcall_tracepoint_refcount into the .data section.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220926053823.2668799-1-npiggin@gmail.com
|
|
Merge our fixes branch to bring in a few things that new feature patches
rely on or conflict with.
|
|
As reported[1] by Nathan, the recently added plpks driver will crash if
it's built into the kernel and booted on a non-pseries machine, eg
powernv:
kernel BUG at arch/powerpc/kernel/syscall.c:39!
Oops: Exception in kernel mode, sig: 5 [#1]
LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA PowerNV
...
NIP system_call_exception+0x90/0x3d0
LR system_call_common+0xec/0x250
Call Trace:
0xc0000000035c3e10 (unreliable)
system_call_common+0xec/0x250
--- interrupt: c00 at plpar_hcall+0x38/0x60
NIP: c0000000000e4300 LR: c00000000202945c CTR: 0000000000000000
REGS: c0000000035c3e80 TRAP: 0c00 Not tainted (6.0.0-rc4)
MSR: 9000000002009033 <SF,HV,VEC,EE,ME,IR,DR,RI,LE> CR: 28000284 XER: 00000000
...
NIP plpar_hcall+0x38/0x60
LR pseries_plpks_init+0x64/0x23c
--- interrupt: c00
On powernv Linux is the hypervisor, so a hypercall just ends up going to
the syscall path, which BUGs if the syscall (hypercall) didn't come from
userspace.
The fix is simply to not probe the plpks driver on non-pseries machines.
[1] https://lore.kernel.org/linuxppc-dev/Yxe06fbq18Wv9y3W@dev-arch.thelio-3990X/
Fixes: 2454a7af0f2a ("powerpc/pseries: define driver for Platform KeyStore")
Reported-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Tested-by: Dan Horák <dan@danny.cz>
Reviewed-by: Dan Horák <dan@danny.cz>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20220907065038.1604504-1-mpe@ellerman.id.au
|
|
Delete the redundant word 'the'.
Signed-off-by: Jilin Yuan <yuanjilin@cdjrlc.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220831005109.38314-1-yuanjilin@cdjrlc.com
|
|
In pseries_cpuhp_cache_use_count() and pseries_cpuhp_detach_nodes(),
we need carefully hold the reference returned by
of_find_next_cache_node() and use it to call of_node_put() to keep
refcount balance.
Signed-off-by: Liang He <windhl@126.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220621111701.4082889-1-windhl@126.com
|
|
In ibmebus_match_path(), use of_node_put() to drop the reference
returned by of_find_node_by_path() before testing for equality of the
pointers.
Signed-off-by: Liang He <windhl@126.com>
[mpe: Rewrite change log]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220619074016.4068105-1-windhl@126.com
|
|
dtl is the PAPR Dispatch Trace Log, which is entirely a pseries feature.
The pseries platform alrady has a file dealing with the dtl, so move
scanning for stolen time accounting there from kernel/time.c.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220902085316.2071519-5-npiggin@gmail.com
|
|
CONFIG_VIRT_CPU_ACCOUNTING_GEN under pseries does not provide stolen
time accounting unless CONFIG_PARAVIRT_TIME_ACCOUNTING is enabled.
Implement this using the VPA accumulated wait counters.
Note this will not work on current KVM hosts because KVM does not
implement the VPA dispatch counters (yet). It could be implemented
with the dispatch trace log as it is for VIRT_CPU_ACCOUNTING_NATIVE,
but that is not necessary for the more limited accounting provided
by PARAVIRT_TIME_ACCOUNTING, and it is more expensive, complex, and
has downsides like potential log wrap.
From Shrikanth:
[...] it was tested on Power10 [PowerVM] Shared LPAR. system has two
LPAR. we will call first one LPAR1 and second one as LPAR2. Test was
carried out in SMT=1. Similar observation was seen in SMT=8 as well.
LPAR config header from each LPAR is below. LPAR1 is twice as big as
LPAR2. Since Both are sharing the same underlying hardware, work
stealing will happen when both the LPAR's are contending for the same
resource.
LPAR1:
type=Shared mode=Uncapped smt=Off lcpu=40 cpus=40 ent=20.00
LPAR2:
type=Shared mode=Uncapped smt=Off lcpu=20 cpus=40 ent=10.00
mpstat was used to check for the utilization. stress-ng has been used
as the workload. Few cases are tested. when the both LPAR are idle
there is no steal time. when LPAR1 starts running at 100% which
consumes all of the physical resource, steal time starts to get
accounted. With LPAR1 running at 100% and LPAR2 starts running, steal
time starts increasing. This is as expected. When the LPAR2 Load is
increased further, steal time increases further.
Case 1: 0% LPAR1; 0% LPAR2
%usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
0.00 0.00 0.05 0.00 0.00 0.00 0.00 0.00 0.00 99.95
Case 2: 100% LPAR1; 0% LPAR2
%usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
97.68 0.00 0.00 0.00 0.00 0.00 2.32 0.00 0.00 0.00
Case 3: 100% LPAR1; 50% LPAR2
%usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
86.34 0.00 0.10 0.00 0.00 0.03 13.54 0.00 0.00 0.00
Case 4: 100% LPAR1; 100% LPAR2
%usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
78.54 0.00 0.07 0.00 0.00 0.02 21.36 0.00 0.00 0.00
Case 5: 50% LPAR1; 100% LPAR2
%usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
49.37 0.00 0.00 0.00 0.00 0.00 1.17 0.00 0.00 49.47
Patch is accounting for the steal time and basic tests are holding
good.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Tested-by: Shrikanth Hegde <sshegde@linux.ibm.com>
[mpe: Add SPDX tag to new paravirt_api_clock.h]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220902085316.2071519-3-npiggin@gmail.com
|
|
Clang warns:
arch/powerpc/platforms/pseries/papr_scm.c:492:6: warning: variable 'rc' is used uninitialized whenever 'if' condition is true [-Wsometimes-uninitialized]
if (!p->stat_buffer_len)
^~~~~~~~~~~~~~~~~~~
arch/powerpc/platforms/pseries/papr_scm.c:523:64: note: uninitialized use occurs here
dev_info(&p->pdev->dev, "nvdimm pmu didn't register rc=%d\n", rc);
^~
include/linux/dev_printk.h:150:67: note: expanded from macro 'dev_info'
dev_printk_index_wrap(_dev_info, KERN_INFO, dev, dev_fmt(fmt), ##__VA_ARGS__)
^~~~~~~~~~~
include/linux/dev_printk.h:110:23: note: expanded from macro 'dev_printk_index_wrap'
_p_func(dev, fmt, ##__VA_ARGS__); \
^~~~~~~~~~~
arch/powerpc/platforms/pseries/papr_scm.c:492:2: note: remove the 'if' if its condition is always false
if (!p->stat_buffer_len)
^~~~~~~~~~~~~~~~~~~~~~~~
arch/powerpc/platforms/pseries/papr_scm.c:484:8: note: initialize the variable 'rc' to silence this warning
int rc, nodeid;
^
= 0
1 warning generated.
The call to papr_scm_pmu_check_events() was eliminated but a return code
was not added to the if statement. Add the same return code from
papr_scm_pmu_check_events() for this condition so there is no more
warning.
Fixes: 9b1ac04698a4 ("powerpc/papr_scm: Fix nvdimm event mappings")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://github.com/ClangBuiltLinux/linux/issues/1701
Link: https://lore.kernel.org/r/20220830151256.1473169-1-nathan@kernel.org
|
|
Follow the advice of the below link and prefer 'strscpy' in this
subsystem. Conversion is 1:1 because the return value is not used.
Generated by a coccinelle script.
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/CAHk-=wgfRnXz0W3D37d01q3JFkr_i_uTL=V6A6G1oUZcprmknw@mail.gmail.com/
Link: https://lore.kernel.org/r/20220818205946.6336-1-wsa+renesas@sang-engineering.com
|
|
Commit 4c08d4bbc089 ("powerpc/papr_scm: Add perf interface support")
added performance monitoring support for papr-scm nvdimm devices via
perf interface. Commit also added an array in papr_scm_priv
structure called "nvdimm_events_map", which got filled based on the
result of H_SCM_PERFORMANCE_STATS hcall.
Currently there is an assumption that the order of events in the
stats buffer, returned by the hypervisor is same. And order also
happens to matches with the events specified in nvdimm driver code.
But this assumption is not documented in Power Architecture
Platform Requirements (PAPR) document. Although the order
of events happens to be same on current generation od system, but
it might not be true in future generation systems. Fix the issue, by
adding a static mapping for nvdimm events to corresponding stat-id,
and removing the dynamic map from papr_scm_priv structure. Also
remove the function papr_scm_pmu_check_events from papr_scm.c file,
as we no longer need to copy stat-ids dynamically.
Fixes: 4c08d4bbc089 ("powerpc/papr_scm: Add perf interface support")
Reported-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Reviewed-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220804074852.55157-1-kjain@linux.ibm.com
|
|
Pull powerpc updates from Michael Ellerman:
- Add support for syscall stack randomization
- Add support for atomic operations to the 32 & 64-bit BPF JIT
- Full support for KASAN on 64-bit Book3E
- Add a watchdog driver for the new PowerVM hypervisor watchdog
- Add a number of new selftests for the Power10 PMU support
- Add a driver for the PowerVM Platform KeyStore
- Increase the NMI watchdog timeout during live partition migration, to
avoid timeouts due to increased memory access latency
- Add support for using the 'linux,pci-domain' device tree property for
PCI domain assignment
- Many other small features and fixes
Thanks to Alexey Kardashevskiy, Andy Shevchenko, Arnd Bergmann, Athira
Rajeev, Bagas Sanjaya, Christophe Leroy, Erhard Furtner, Fabiano Rosas,
Greg Kroah-Hartman, Greg Kurz, Haowen Bai, Hari Bathini, Jason A.
Donenfeld, Jason Wang, Jiang Jian, Joel Stanley, Juerg Haefliger, Kajol
Jain, Kees Cook, Laurent Dufour, Madhavan Srinivasan, Masahiro Yamada,
Maxime Bizon, Miaoqian Lin, Murilo Opsfelder Araújo, Nathan Lynch,
Naveen N. Rao, Nayna Jain, Nicholas Piggin, Ning Qiang, Pali Rohár,
Petr Mladek, Rashmica Gupta, Sachin Sant, Scott Cheloha, Segher
Boessenkool, Stephen Rothwell, Uwe Kleine-König, Wolfram Sang, Xiu
Jianfeng, and Zhouyi Zhou.
* tag 'powerpc-6.0-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (191 commits)
powerpc/64e: Fix kexec build error
EDAC/ppc_4xx: Include required of_irq header directly
powerpc/pci: Fix PHB numbering when using opal-phbid
powerpc/64: Init jump labels before parse_early_param()
selftests/powerpc: Avoid GCC 12 uninitialised variable warning
powerpc/cell/axon_msi: Fix refcount leak in setup_msi_msg_address
powerpc/xive: Fix refcount leak in xive_get_max_prio
powerpc/spufs: Fix refcount leak in spufs_init_isolated_loader
powerpc/perf: Include caps feature for power10 DD1 version
powerpc: add support for syscall stack randomization
powerpc: Move system_call_exception() to syscall.c
powerpc/powernv: rename remaining rng powernv_ functions to pnv_
powerpc/powernv/kvm: Use darn for H_RANDOM on Power9
powerpc/powernv: Avoid crashing if rng is NULL
selftests/powerpc: Fix matrix multiply assist test
powerpc/signal: Update comment for clarity
powerpc: make facility_unavailable_exception 64s
powerpc/platforms/83xx/suspend: Remove write-only global variable
powerpc/platforms/83xx/suspend: Prevent unloading the driver
powerpc/platforms/83xx/suspend: Reorder to get rid of a forward declaration
...
|
|
Pull folio updates from Matthew Wilcox:
- Fix an accounting bug that made NR_FILE_DIRTY grow without limit
when running xfstests
- Convert more of mpage to use folios
- Remove add_to_page_cache() and add_to_page_cache_locked()
- Convert find_get_pages_range() to filemap_get_folios()
- Improvements to the read_cache_page() family of functions
- Remove a few unnecessary checks of PageError
- Some straightforward filesystem conversions to use folios
- Split PageMovable users out from address_space_operations into
their own movable_operations
- Convert aops->migratepage to aops->migrate_folio
- Remove nobh support (Christoph Hellwig)
* tag 'folio-6.0' of git://git.infradead.org/users/willy/pagecache: (78 commits)
fs: remove the NULL get_block case in mpage_writepages
fs: don't call ->writepage from __mpage_writepage
fs: remove the nobh helpers
jfs: stop using the nobh helper
ext2: remove nobh support
ntfs3: refactor ntfs_writepages
mm/folio-compat: Remove migration compatibility functions
fs: Remove aops->migratepage()
secretmem: Convert to migrate_folio
hugetlb: Convert to migrate_folio
aio: Convert to migrate_folio
f2fs: Convert to filemap_migrate_folio()
ubifs: Convert to filemap_migrate_folio()
btrfs: Convert btrfs_migratepage to migrate_folio
mm/migrate: Add filemap_migrate_folio()
mm/migrate: Convert migrate_page() to migrate_folio()
nfs: Convert to migrate_folio
btrfs: Convert btree_migratepage to migrate_folio
mm/migrate: Convert expected_page_refs() to folio_expected_refs()
mm/migrate: Convert buffer_migrate_page() to buffer_migrate_folio()
...
|
|
These drivers are rather uncomfortably hammered into the
address_space_operations hole. They aren't filesystems and don't behave
like filesystems. They just need their own movable_operations structure,
which we can point to directly from page->mapping.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
|
|
The double `the' in line 807 is duplicated, remove one.
Signed-off-by: Jason Wang <wangborong@cdjrlc.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220718075553.70897-1-wangborong@cdjrlc.com
|
|
PowerVM provides an isolated Platform Keystore(PKS) storage allocation
for each LPAR with individually managed access controls to store
sensitive information securely. It provides a new set of hypervisor
calls for Linux kernel to access PKS storage.
Define POWER LPAR Platform KeyStore(PLPKS) driver using H_CALL interface
to access PKS storage.
Signed-off-by: Nayna Jain <nayna@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220723113048.521744-2-nayna@linux.ibm.com
|
|
The pseries platform uses 32bit default DMA window (always 4K pages) and
optional 64bit DMA window available via DDW ("Dynamic DMA Windows"),
64K or 2M pages. For ages the default one was not removed and a huge
window was created in addition. Things changed with SRIOV-enabled
PowerVM which creates a default-and-bigger DMA window in 64bit space
(still using 4K pages) for IOV VFs so certain OSes do not need to use
the DDW API in order to utilize all available TCE budget.
Linux on the other hand removes the default window and creates a bigger
one (with more TCEs or/and a bigger page size - 64K/2M) in a bid to map
the entire RAM, and if the new window size is smaller than that - it
still uses this new bigger window. The result is that the default window
is removed but the "ibm,dma-window" property is not.
When kdump is invoked, the existing code tries reusing the existing 64bit
DMA window which location and parameters are stored in the device tree but
this fails as the new property does not make it to the kdump device tree
blob. So the code falls back to the default window which does not exist
anymore although the device tree says that it does. The result of that
is that PCI devices become unusable and cannot be used for kdumping.
This preserves the DMA64 and DIRECT64 properties in the device tree blob
for the crash kernel. Since the crash kernel setup is done after device
drivers are loaded and probed, the proper DMA config is stored at least
for boot time devices.
Because DDW window is optional and the code configures the default window
first, the existing code creates an IOMMU table descriptor for
the non-existing default DMA window. It is harmless for kdump as it does
not touch the actual window (only reads what is mapped and marks those IO
pages as used) but it is bad for kexec which clears it thinking it is
a smaller default window rather than a bigger DDW window.
This removes the "ibm,dma-window" property from the device tree after
a bigger window is created and the crash kernel setup picks it up.
Fixes: 381ceda88c4c ("powerpc/pseries/iommu: Make use of DDW for indirect mapping")
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Acked-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220629060614.1680476-1-aik@ozlabs.ru
|
|
During an LPM, while the memory transfer is in progress on the arrival
side, some latencies are generated when accessing not yet transferred
pages on the arrival side. Thus, the NMI watchdog may be triggered too
frequently, which increases the risk to hit an NMI interrupt in a bad
place in the kernel, leading to a kernel panic.
Disabling the Hard Lockup Watchdog until the memory transfer could be a
too strong work around, some users would want this timeout to be
eventually triggered if the system is hanging even during an LPM.
Introduce a new sysctl variable nmi_watchdog_factor. It allows to apply
a factor to the NMI watchdog timeout during an LPM. Just before the CPUs
are stopped for the switchover sequence, the NMI watchdog timer is set
to watchdog_thresh + factor%
A value of 0 has no effect. The default value is 200, meaning that the
NMI watchdog is set to 30s during LPM (based on a 10s watchdog_thresh
value). Once the memory transfer is achieved, the factor is reset to 0.
Setting this value to a high number is like disabling the NMI watchdog
during an LPM.
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220713154729.80789-5-ldufour@linux.ibm.com
|
|
In pseries_migration_partition(), loop until the memory transfer is
complete. This way the calling drmgr process will not exit earlier,
allowing callbacks to be run only once the migration is fully completed.
If reading the VASI state is done after the hypervisor has completed the
migration, the HCALL is returning H_PARAMETER. We can safely assume that
the memory transfer is achieved if this happens.
This will also allow to manage the NMI watchdog state in the next commits.
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Reviewed-by: Nathan Lynch <nathanl@linux.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220713154729.80789-2-ldufour@linux.ibm.com
|
|
Since commit 87c78b612f4f ("powerpc: Fix all occurences of "the the"")
fixed "the the", there's now a steady stream of patches fixing other
duplicate words.
Just fix them all at once, to save the overhead of dealing with
individual patches for each case.
This leaves a few cases of "that that", which in some contexts is
correct.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220718095158.326606-1-mpe@ellerman.id.au
|
|
PAPR v2.12 defines a new hypercall, H_WATCHDOG. The hypercall permits
guest control of one or more virtual watchdog timers.
These timers do not conform to PowerPC device conventions. They are
not affixed to any extant bus, nor do they have full representation in
the device tree.
As a workaround we represent them as platform devices.
This patch registers a single platform device, "pseries-wdt", with the
platform bus if the FW_FEATURE_WATCHDOG flag is set.
A driver for this device, "pseries-wdt", will be introduced in a
subsequent patch.
Signed-off-by: Scott Cheloha <cheloha@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220713202335.1217647-4-cheloha@linux.ibm.com
|
|
PAPR v2.12 specifies a new optional function set, "hcall-watchdog",
for the /rtas/ibm,hypertas-functions property. The presence of this
function set indicates support for the H_WATCHDOG hypercall.
Check for this function set and, if present, set the new
FW_FEATURE_WATCHDOG flag.
Signed-off-by: Scott Cheloha <cheloha@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220713202335.1217647-3-cheloha@linux.ibm.com
|
|
When RDRAND was introduced, there was much discussion on whether it
should be trusted and how the kernel should handle that. Initially, two
mechanisms cropped up, CONFIG_ARCH_RANDOM, a compile time switch, and
"nordrand", a boot-time switch.
Later the thinking evolved. With a properly designed RNG, using RDRAND
values alone won't harm anything, even if the outputs are malicious.
Rather, the issue is whether those values are being *trusted* to be good
or not. And so a new set of options were introduced as the real
ones that people use -- CONFIG_RANDOM_TRUST_CPU and "random.trust_cpu".
With these options, RDRAND is used, but it's not always credited. So in
the worst case, it does nothing, and in the best case, maybe it helps.
Along the way, CONFIG_ARCH_RANDOM's meaning got sort of pulled into the
center and became something certain platforms force-select.
The old options don't really help with much, and it's a bit odd to have
special handling for these instructions when the kernel can deal fine
with the existence or untrusted existence or broken existence or
non-existence of that CPU capability.
Simplify the situation by removing CONFIG_ARCH_RANDOM and using the
ordinary asm-generic fallback pattern instead, keeping the two options
that are actually used. For now it leaves "nordrand" for now, as the
removal of that will take a different route.
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Borislav Petkov <bp@suse.de>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
|
|
Merge our fixes branch. In particular this brings in commit
986481618023 ("powerpc/book3e: Fix PUD allocation size in
map_kernel_page()") which fixes a build failure in next, because commit
2db2008e6363 ("powerpc/64e: Rewrite p4d_populate() as a static inline
function") depends on it.
|
|
PowerVM has a stricter policy about allocating TCEs for LPARs and
often there is not enough TCEs for 1:1 mapping, this adds the supported
numbers into dev_info() to help analyzing bugreports.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220601040117.1467710-1-aik@ozlabs.ru
|
|
There is no need to read the H_BLOCK_REMOVE characteristics when running in
Radix mode because this hcall is never called.
Furthermore since the commit 387e220a2e5e ("powerpc/64s: Move hash MMU
support code under CONFIG_PPC_64S_HASH_MMU") define
pseries_lpar_read_hblkrm_characteristics as un empty function if
CONFIG_PPC_64S_HASH_MMU is not set, the #ifdef block can be removed.
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220523164353.26441-1-ldufour@linux.ibm.com
|
|
Eliminate direct accesses to the driver_data field.
Signed-off-by: Haowen Bai <baihaowen@meizu.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1653988790-19999-1-git-send-email-baihaowen@meizu.com
|
|
Trying to remove asm/ppc_asm.h from all places that don't need it
leads to several failures linked to firmware_has_feature().
To fix it, include asm/firmware.h in all files using
firmware_has_feature()
All users found with:
git grep -L "firmware\.h" ` git grep -l "firmware_has_feature("`
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/11956ec181a034b51a881ac9c059eea72c679a73.1651828453.git.christophe.leroy@csgroup.eu
|
|
asm/machdep.h doesn't need asm/setup.h
Remove it.
Add it directly in files that needs it.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/3b1dfb19a2c3265fb4abc2bfc7b6eae9261a998b.1654966508.git.christophe.leroy@csgroup.eu
|
|
The platform's RNG must be available before random_init() in order to be
useful for initial seeding, which in turn means that it needs to be
called from setup_arch(), rather than from an init call. Fortunately,
each platform already has a setup_arch function pointer, which means
it's easy to wire this up. This commit also removes some noisy log
messages that don't add much.
Fixes: a489043f4626 ("powerpc/pseries: Implement arch_get_random_long() based on H_RANDOM")
Cc: stable@vger.kernel.org # v3.13+
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220611151015.548325-4-Jason@zx2c4.com
|
|
Sachin reported [1] that on a POWER-10 lpar he is seeing a kernel panic being
reported with vPMEM when papr_scm probe is being called. The panic is of the
form below and is observed only with following option disabled(profile) for the
said LPAR 'Enable Performance Information Collection' in the HMC:
Kernel attempted to write user page (1c) - exploit attempt? (uid: 0)
BUG: Kernel NULL pointer dereference on write at 0x0000001c
Faulting instruction address: 0xc008000001b90844
Oops: Kernel access of bad area, sig: 11 [#1]
<snip>
NIP [c008000001b90844] drc_pmem_query_stats+0x5c/0x270 [papr_scm]
LR [c008000001b92794] papr_scm_probe+0x2ac/0x6ec [papr_scm]
Call Trace:
0xc00000000941bca0 (unreliable)
papr_scm_probe+0x2ac/0x6ec [papr_scm]
platform_probe+0x98/0x150
really_probe+0xfc/0x510
__driver_probe_device+0x17c/0x230
<snip>
---[ end trace 0000000000000000 ]---
Kernel panic - not syncing: Fatal exception
On investigation looks like this panic was caused due to a 'stat_buffer' of
size==0 being provided to drc_pmem_query_stats() to fetch all performance
stats-ids of an NVDIMM. However drc_pmem_query_stats() shouldn't have been called
since the vPMEM NVDIMM doesn't support and performance stat-id's. This was caused
due to missing check for 'p->stat_buffer_len' at the beginning of
papr_scm_pmu_check_events() which indicates that the NVDIMM doesn't support
performance-stats.
Fix this by introducing the check for 'p->stat_buffer_len' at the beginning of
papr_scm_pmu_check_events().
[1] https://lore.kernel.org/all/6B3A522A-6A5F-4CC9-B268-0C63AA6E07D3@linux.ibm.com
Fixes: 0e0946e22f3665d2732 ("powerpc/papr_scm: Fix leaking nvdimm_events_map elements")
Reported-by: Sachin Sant <sachinp@linux.ibm.com>
Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Tested-by: Sachin Sant <sachinp@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220524112353.1718454-1-vaibhav@linux.ibm.com
|
|
Pull powerpc updates from Michael Ellerman:
- Convert to the generic mmap support (ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT)
- Add support for outline-only KASAN with 64-bit Radix MMU (P9 or later)
- Increase SIGSTKSZ and MINSIGSTKSZ and add support for AT_MINSIGSTKSZ
- Enable the DAWR (Data Address Watchpoint) on POWER9 DD2.3 or later
- Drop support for system call instruction emulation
- Many other small features and fixes
Thanks to Alexey Kardashevskiy, Alistair Popple, Andy Shevchenko, Bagas
Sanjaya, Bjorn Helgaas, Bo Liu, Chen Huang, Christophe Leroy, Colin Ian
King, Daniel Axtens, Dwaipayan Ray, Fabiano Rosas, Finn Thain, Frank
Rowand, Fuqian Huang, Guilherme G. Piccoli, Hangyu Hua, Haowen Bai,
Haren Myneni, Hari Bathini, He Ying, Jason Wang, Jiapeng Chong, Jing
Yangyang, Joel Stanley, Julia Lawall, Kajol Jain, Kevin Hao, Krzysztof
Kozlowski, Laurent Dufour, Lv Ruyi, Madhavan Srinivasan, Magali Lemes,
Miaoqian Lin, Minghao Chi, Nathan Chancellor, Naveen N. Rao, Nicholas
Piggin, Oliver O'Halloran, Oscar Salvador, Pali Rohár, Paul Mackerras,
Peng Wu, Qing Wang, Randy Dunlap, Reza Arbab, Russell Currey, Sohaib
Mohamed, Vaibhav Jain, Vasant Hegde, Wang Qing, Wang Wensheng, Xiang
wangx, Xiaomeng Tong, Xu Wang, Yang Guang, Yang Li, Ye Bin, YueHaibing,
Yu Kuai, Zheng Bin, Zou Wei, and Zucheng Zheng.
* tag 'powerpc-5.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (200 commits)
powerpc/64: Include cache.h directly in paca.h
powerpc/64s: Only set HAVE_ARCH_UNMAPPED_AREA when CONFIG_PPC_64S_HASH_MMU is set
powerpc/xics: Include missing header
powerpc/powernv/pci: Drop VF MPS fixup
powerpc/fsl_book3e: Don't set rodata RO too early
powerpc/microwatt: Add mmu bits to device tree
powerpc/powernv/flash: Check OPAL flash calls exist before using
powerpc/powermac: constify device_node in of_irq_parse_oldworld()
powerpc/powermac: add missing g5_phy_disable_cpu1() declaration
selftests/powerpc/pmu: fix spelling mistake "mis-match" -> "mismatch"
powerpc: Enable the DAWR on POWER9 DD2.3 and above
powerpc/64s: Add CPU_FTRS_POWER10 to ALWAYS mask
powerpc/64s: Add CPU_FTRS_POWER9_DD2_2 to CPU_FTRS_ALWAYS mask
powerpc: Fix all occurences of "the the"
selftests/powerpc/pmu/ebb: remove fixed_instruction.S
powerpc/platforms/83xx: Use of_device_get_match_data()
powerpc/eeh: Drop redundant spinlock initialization
powerpc/iommu: Add missing of_node_put in iommu_init_early_dart
powerpc/pseries/vas: Call misc_deregister if sysfs init fails
powerpc/papr_scm: Fix leaking nvdimm_events_map elements
...
|
|
Pull dma-mapping updates from Christoph Hellwig:
- don't over-decrypt memory (Robin Murphy)
- takes min align mask into account for the swiotlb max mapping size
(Tianyu Lan)
- use GFP_ATOMIC in dma-debug (Mikulas Patocka)
- fix DMA_ATTR_NO_KERNEL_MAPPING on xen/arm (me)
- don't fail on highmem CMA pages in dma_direct_alloc_pages (me)
- cleanup swiotlb initialization and share more code with swiotlb-xen
(me, Stefano Stabellini)
* tag 'dma-mapping-5.19-2022-05-25' of git://git.infradead.org/users/hch/dma-mapping: (23 commits)
dma-direct: don't over-decrypt memory
swiotlb: max mapping size takes min align mask into account
swiotlb: use the right nslabs-derived sizes in swiotlb_init_late
swiotlb: use the right nslabs value in swiotlb_init_remap
swiotlb: don't panic when the swiotlb buffer can't be allocated
dma-debug: change allocation mode from GFP_NOWAIT to GFP_ATIOMIC
dma-direct: don't fail on highmem CMA pages in dma_direct_alloc_pages
swiotlb-xen: fix DMA_ATTR_NO_KERNEL_MAPPING on arm
x86: remove cruft from <asm/dma-mapping.h>
swiotlb: remove swiotlb_init_with_tbl and swiotlb_init_late_with_tbl
swiotlb: merge swiotlb-xen initialization into swiotlb
swiotlb: provide swiotlb_init variants that remap the buffer
swiotlb: pass a gfp_mask argument to swiotlb_init_late
swiotlb: add a SWIOTLB_ANY flag to lift the low memory restriction
swiotlb: make the swiotlb_init interface more useful
x86: centralize setting SWIOTLB_FORCE when guest memory encryption is enabled
x86: remove the IOMMU table infrastructure
MIPS/octeon: use swiotlb_init instead of open coding it
arm/xen: don't check for xen_initial_domain() in xen_create_contiguous_region
swiotlb: rename swiotlb_late_init_with_default_size
...
|
|
slot_errbuf_lock has declared and initialized by DEFINE_SPINLOCK,
so we don't need to spin_lock_init again, drop it.
Signed-off-by: Haowen Bai <baihaowen@meizu.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1652232476-9696-1-git-send-email-baihaowen@meizu.com
|
|
Undo effects of misc_register if sysfs init fails after
misc_register.
Signed-off-by: Zheng Bin <zhengbin13@huawei.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220511033507.2745992-1-zhengbin13@huawei.com
|
|
Right now 'char *' elements allocated for individual 'stat_id' in
'papr_scm_priv.nvdimm_events_map[]' during papr_scm_pmu_check_events(), get
leaked in papr_scm_remove() and papr_scm_pmu_register(),
papr_scm_pmu_check_events() error paths.
Also individual 'stat_id' arent NULL terminated 'char *' instead they are fixed
8-byte sized identifiers. However papr_scm_pmu_register() assumes it to be a
NULL terminated 'char *' and at other places it assumes it to be a
'papr_scm_perf_stat.stat_id' sized string which is 8-byes in size.
Fix this by allocating the memory for papr_scm_priv.nvdimm_events_map to also
include space for 'stat_id' entries. This is possible since number of available
events/stat_ids are known upfront. This saves some memory and one extra level of
indirection from 'nvdimm_events_map' to 'stat_id'. Also rest of the code
can continue to call 'kfree(papr_scm_priv.nvdimm_events_map)' without needing to
iterate over the array and free up individual elements.
Fixes: 4c08d4bbc089 ("powerpc/papr_scm: Add perf interface support")
Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220511082637.646714-1-vaibhav@linux.ibm.com
|
|
powerpc is the only platform that do not rely on
cpu_up()->try_online_node() to bring up a numa node,
and special cases it, instead, deep in its own machinery:
dlpar_online_cpu
find_and_online_cpu_nid
try_online_node
This should not be needed, but the thing is that the try_online_node()
from cpu_up() will not apply on the right node, because cpu_to_node()
will return the old mapping numa<->cpu that gets set on boot stage
for all possible cpus.
That can be seen easily if we try to print out the numa node passed
to try_online_node() in cpu_up().
The thing is that the numa<->cpu mapping does not get updated till a much
later stage in start_secondary:
start_secondary:
set_numa_node(numa_cpu_lookup_table[cpu])
But we do not really care, as we already now the
CPU <-> NUMA associativity back in find_and_online_cpu_nid(),
so let us make use of that and set the proper numa<->cpu mapping,
so cpu_to_node() in cpu_up() returns the right node and
try_online_node() can do its work.
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Tested-by: Geetika Moolchandani <Geetika.Moolchandani1@ibm.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220411074934.4632-1-osalvador@suse.de
|
|
Implement a limited form of KASAN for Book3S 64-bit machines running under
the Radix MMU, supporting only outline mode.
- Enable the compiler instrumentation to check addresses and maintain the
shadow region. (This is the guts of KASAN which we can easily reuse.)
- Require kasan-vmalloc support to handle modules and anything else in
vmalloc space.
- KASAN needs to be able to validate all pointer accesses, but we can't
instrument all kernel addresses - only linear map and vmalloc. On boot,
set up a single page of read-only shadow that marks all iomap and
vmemmap accesses as valid.
- Document KASAN in powerpc docs.
Background
----------
KASAN support on Book3S is a bit tricky to get right:
- It would be good to support inline instrumentation so as to be able to
catch stack issues that cannot be caught with outline mode.
- Inline instrumentation requires a fixed offset.
- Book3S runs code with translations off ("real mode") during boot,
including a lot of generic device-tree parsing code which is used to
determine MMU features.
[ppc64 mm note: The kernel installs a linear mapping at effective
address c000...-c008.... This is a one-to-one mapping with physical
memory from 0000... onward. Because of how memory accesses work on
powerpc 64-bit Book3S, a kernel pointer in the linear map accesses the
same memory both with translations on (accessing as an 'effective
address'), and with translations off (accessing as a 'real
address'). This works in both guests and the hypervisor. For more
details, see s5.7 of Book III of version 3 of the ISA, in particular
the Storage Control Overview, s5.7.3, and s5.7.5 - noting that this
KASAN implementation currently only supports Radix.]
- Some code - most notably a lot of KVM code - also runs with translations
off after boot.
- Therefore any offset has to point to memory that is valid with
translations on or off.
One approach is just to give up on inline instrumentation. This way
boot-time checks can be delayed until after the MMU is set is up, and we
can just not instrument any code that runs with translations off after
booting. Take this approach for now and require outline instrumentation.
Previous attempts allowed inline instrumentation. However, they came with
some unfortunate restrictions: only physically contiguous memory could be
used and it had to be specified at compile time. Maybe we can do better in
the future.
[paulus@ozlabs.org - Rebased onto 5.17. Note that a kernel with
CONFIG_KASAN=y will crash during boot on a machine using HPT
translation because not all the entry points to the generic
KASAN code are protected with a call to kasan_arch_is_ready().]
Originally-by: Balbir Singh <bsingharora@gmail.com> # ppc64 out-of-line radix version
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
[mpe: Update copyright year and comment formatting]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/YoTE69OQwiG7z+Gu@cleo
|
|
The kexec code paths involve code that necessarily run in real mode, as
CPUs are disabled and control is transferred to the new kernel. Disable
address sanitization for the kexec code and the functions called in real
mode on CPUs being disabled.
[paulus@ozlabs.org: combined a few work-in-progress commits of
Daniel's and wrote the commit message.]
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
[mpe: Move pseries_machine_kexec() into kexec.c so setup.c can be instrumented]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/YoTFSQ2TUSEaDdVC@cleo
|
|
VAS entry is created as a misc device and the sysfs comments
should list the proper entries
Reported-by: Matheus Castanho <mscastanho@ibm.com>
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/6dee950c7b72a4965c102208041f14a063cf5a8c.camel@linux.ibm.com
|
|
Merge our KVM topic branch.
|
|
LoPAPR defines guest visible IOMMU with hypercalls to use it -
H_PUT_TCE/etc. Implemented first on POWER7 where hypercalls would trap
in the KVM in the real mode (with MMU off). The problem with the real mode
is some memory is not available and some API usage crashed the host but
enabling MMU was an expensive operation.
The problems with the real mode handlers are:
1. Occasionally these cannot complete the request so the code is
copied+modified to work in the virtual mode, very little is shared;
2. The real mode handlers have to be linked into vmlinux to work;
3. An exception in real mode immediately reboots the machine.
If the small DMA window is used, the real mode handlers bring better
performance. However since POWER8, there has always been a bigger DMA
window which VMs use to map the entire VM memory to avoid calling
H_PUT_TCE. Such 1:1 mapping happens once and uses H_PUT_TCE_INDIRECT
(a bulk version of H_PUT_TCE) which virtual mode handler is even closer
to its real mode version.
On POWER9 hypercalls trap straight to the virtual mode so the real mode
handlers never execute on POWER9 and later CPUs.
So with the current use of the DMA windows and MMU improvements in
POWER9 and later, there is no point in duplicating the code.
The 32bit passed through devices may slow down but we do not have many
of these in practice. For example, with this applied, a 1Gbit ethernet
adapter still demostrates above 800Mbit/s of actual throughput.
This removes the real mode handlers from KVM and related code from
the powernv platform.
This updates the list of implemented hcalls in KVM-HV as the realmode
handlers are removed.
This changes ABI - kvmppc_h_get_tce() moves to the KVM module and
kvmppc_find_table() is static now.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220506053755.3820702-1-aik@ozlabs.ru
|