commit ac29c64089 ("powerpc/mm: Replace _PAGE_USER with
_PAGE_PRIVILEGED") introduced _PAGE_PRIVILEGED for BOOK3S/64
This patch generalises _PAGE_PRIVILEGED for all CPUs, allowing
to have either _PAGE_PRIVILEGED or _PAGE_USER or both.
PPC_8xx has a _PAGE_SHARED flag which is set for and only for
all non user pages. Lets rename it _PAGE_PRIVILEGED to remove
confusion as it has nothing to do with Linux shared pages.
On BookE, there's a _PAGE_BAP_SR which has to be set for kernel
pages: defining _PAGE_PRIVILEGED as _PAGE_BAP_SR will make
this generic
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
_PAGE_WRITETHRU is only used in:
* AMIGA_Z2RAM block driver which is never activated on powerPC
* Video/FB driver which is for PPC_PMAC
Therefore, no need to spend time in 8xx TLB miss handlers for
handling it.
And by removing it, we free up bit 20 which then avoids having
to clear it on each TLB miss.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
In TLB miss handlers, updating the perf counter is only useful
when performing a perf analysis. As it has a noticeable overhead,
let's only do it when needed.
In order to do so, the exit of the miss handlers will be patched
when starting/stopping 'perf': the first register restore
instruction of each exit point will be replaced by a jump to
the counting code.
Once this is done, CONFIG_PPC_8xx_PERF_EVENT becomes useless as
this feature doesn't add any overhead.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
EXCEPTION_PROLOG_0 and EXCEPTION_EPILOG_0 were added some
time ago in order to regroup the two mtspr/mfspr to SCRATCH0 and
SCRATCH1 and the mfcr/mtcr in order to ease entry and exit of
function not using the full EXCEPTION_PROLOG.
Since then, the mfcr/mtcr has been taken out, hence just leaving
the two mtspr/mfspr in the macro.
In order to improve readability of the exception functions, we
remove those two macros and copy back the two mtspr/mfspr instead.
As r10 and r11 are used for SCRATCH0 and SCRATCH1, lets also use
r12 for SCRATCH2. It will also improve the readability/maintenance.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
CPU6 ERRATA affects only MPC860 revisions prior to C.0. Manufacturing
of those revisiosn was stopped in 1999-2000.
Therefore, it has been almost 20 years since this ERRATA has been
fixed in the silicon.
This patch removes the workaround for that ERRATA.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Since commit 0e6e01ff69 ("CPM/QE: use genalloc to manage CPM/QE
muram"), rheap is not used anymore.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Certain HMI's such as malfunction error propagate through
all threads/core on the system. If a thread was offline
prior to us crashing the system and jumping to the kdump
kernel, bad things happen when it wakes up due to an HMI
in the kdump kernel.
There are several possible ways to solve this problem
1. Put the offline cores in a state such that they are
not woken up for machine check and HMI errors. This
does not work, since we might need to wake up offline
threads to handle TB errors
2. Ignore HMI errors, setup HMEER to mask HMI errors,
but this still leads the window open for any MCEs
and masking them for the duration of the dump might
be a concern
3. Wake up offline CPUs, as in send them to
crash_ipi_callback (not wake them up as in mark them
online as seen by the hotplug). kexec does a
wake_online_cpus() call, this patch does something
similar, but instead sends an IPI and forces them to
crash_ipi_callback()
This patch takes approach #3.
Care is taken to enable this only for powenv platforms
via crash_wake_offline (a global value set at setup
time). The crash code sends out IPI's to all CPU's
which then move to crash_ipi_callback and kexec_smp_wait().
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Our check was extra cautious, we've audited crash_send_ipi
and it sends an IPI only to online CPU's. Removal of this
check should have not functional impact on crash kdump.
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Instead of manually coding the loop with of_find_node_by_type(), let's
switch to the standard macro for iterating over nodes with given type.
Also fixed a couple of refcount leaks in the aforementioned loops.
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This patch remove CONFIG_PPC_HTDUMP if not PPC_BOOK3S_64 to avoid
below compile failure on BOOK3S_32:
In file included from arch/powerpc/mm/dump_hashpagetable.c:27:0:
./arch/powerpc/include/asm/plpar_wrappers.h: In function 'get_cede_latency_hint':
./arch/powerpc/include/asm/plpar_wrappers.h:27:2: error: implicit declaration of function 'get_lppaca' [-Werror=implicit-function-declaration]
...
arch/powerpc/mm/dump_hashpagetable.c: At top level:
arch/powerpc/mm/dump_hashpagetable.c:69:13: error: 'SLB_VSID_B' undeclared here (not in a function)
...
arch/powerpc/mm/dump_hashpagetable.c:506:38: error: 'VMEMMAP_BASE' undeclared (first use in this function)
arch/powerpc/mm/dump_hashpagetable.c:506:35: error: assignment makes integer from pointer without a cast [-Werror]
Fixes: dd5ac03e09 ("powerpc/mm: Fix page table dump build on non-Book3S")
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
[mpe: Trim change log]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Add required bits to the architecture vector to enable support
of the ibm,dynamic-memory-v2 device tree property.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The Power Hypervisor has introduced a new device tree format for
the property describing the dynamic reconfiguration LMBs for a system,
ibm,dynamic-memory-v2. This new format condenses the size of the
property, especially on large memory systems, by reporting sets
of LMBs that have the same properties (flags and associativity array
index).
This patch updates the powerpc/mm/drmem.c code to provide routines
that can parse the new device tree format during the walk_drmem_lmb*
routines used during boot, the creation of the LMB array, and updating
the device tree to create a new property in the proper format for
ibm,dynamic-memory-v2.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Now that the powerpc code parses dynamic reconfiguration memory
LMB information from the LMB array and not the device tree
directly we can move the of_drconf_cell struct to drmem.h where
it fits better.
In addition, the struct is renamed to of_drconf_cell_v1 in
anticipation of upcoming support for version 2 of the dynamic
reconfiguration property and the members are typed as __be*
values to reflect how they exist in the device tree.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Update the pseries memory hotplug code to use the newly added
dynamic reconfiguration LMB array. Doing this is required for the
upcoming support of version 2 of the dynamic reconfiguration
device tree property.
In addition, making this change cleans up the code that parses the
LMB information as we no longer need to worry about device tree
format. This allows us to discard one of the first steps on memory
hotplug where we make a working copy of the device tree property and
convert the entire property to cpu format. Instead we just use the
LMB array directly while holding the memory hotplug lock.
This patch also moves the updating of the device tree property to
powerpc/mm/drmem.c. This allows to the hotplug code to work without
needing to know the device tree format and provides a single
routine for updating the device tree property. This new routine
will handle determination of the proper device tree format and
generate a properly formatted device tree property.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Update code in powerpc/numa.c to use the walk_drmem_lmbs()
routine instead of parsing the device tree directly. This is
in anticipation of introducing a new ibm,dynamic-memory-v2
property with a different format. This will allow the numa code
to use a single initialization routine per-LMB irregardless of
the device tree format.
Additionally, to support additional routines in numa.c that need
to look up LMB information, an late_init routine is added to drmem.c
to allocate the array of LMB information. This LMB array will provide
per-LMB information to separate the LMB data from the device tree
format.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
We currently have code to parse the dynamic reconfiguration LMB
information from the ibm,dynamic-meory device tree property in
multiple locations; numa.c, prom.c, and pseries/hotplug-memory.c.
In anticipation of adding support for a version 2 of the
ibm,dynamic-memory property this patch aims to separate the device
tree information from the device tree format.
Doing this requires a two step process to avoid a possibly very large
bootmem allocation early in boot. During initial boot, new routines
are provided to walk the device tree property and make a call-back
for each LMB.
The second step (introduced in later patches) will allocate an
array of LMB information that can be used directly without needing
to know the DT format.
This approach provides the benefit of consolidating the device tree
property parsing to a single location and (eventually) providing
a common data structure for retrieving LMB information.
This patch introduces a routine to walk the ibm,dynamic-memory
property in the flattened device tree and updates the prom.c code
to use this to initialize memory.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Look up the associativity arrays in of_drconf_to_nid_single when
deriving the nid for a LMB instead of having it passed in as a
parameter.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Look up the device node for the usable memory property instead
of having it passed in as a parameter. This changes precedes an update
in which the calling routines for of_get_usable_memory() will not have
the device node pointer to pass in.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Look up the device node for the associativity array property instead
of having it passed in as a parameter. This changes precedes an update
in which the calling routines for of_get_assoc_arrays() will not have
the device node pointer to pass in.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This will be used by KVM in order to keep escalation interrupts
in the non-EOI (masked) state after they fire. They will be
re-enabled directly in HW by KVM when needed.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
From xive.h to xive-regs.h since it's a HW register definition
and it can be used from assembly
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This causes warnings from cpufreq mutex code. This is also rather
unnecessary and ineffective. If we really want to prevent concurrent
unplug, we could take the unplug read lock but I don't see this being
critical.
Fixes: cd77b5ce20 ("powerpc/powernv/cpufreq: Fix the frequency read by /proc/cpuinfo")
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Remember when the biggest problem we had to worry about was hashed
pointers, those were the days.
These were missed in my earlier patch because they don't match "%p",
but the macro is hiding a "%p", so these all end up being hashed,
which is not what we want in xmon. Convert them to "%px".
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
New device-tree properties are available which tell the hypervisor
settings related to the RFI flush. Use them to determine the
appropriate flush instruction to use, and whether the flush is
required.
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
A new hypervisor call is available which tells the guest settings
related to the RFI flush. Use it to query the appropriate flush
instruction(s), and whether the flush is required.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Because there may be some performance overhead of the RFI flush, add
kernel command line options to disable it.
We add a sensibly named 'no_rfi_flush' option, but we also hijack the
x86 option 'nopti'. The RFI flush is not the same as KPTI, but if we
see 'nopti' we can guess that the user is trying to avoid any overhead
of Meltdown mitigations, and it means we don't have to educate every
one about a different command line option.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
On some CPUs we can prevent the Meltdown vulnerability by flushing the
L1-D cache on exit from kernel to user mode, and from hypervisor to
guest.
This is known to be the case on at least Power7, Power8 and Power9. At
this time we do not know the status of the vulnerability on other CPUs
such as the 970 (Apple G5), pasemi CPUs (AmigaOne X1000) or Freescale
CPUs. As more information comes to light we can enable this, or other
mechanisms on those CPUs.
The vulnerability occurs when the load of an architecturally
inaccessible memory region (eg. userspace load of kernel memory) is
speculatively executed to the point where its result can influence the
address of a subsequent speculatively executed load.
In order for that to happen, the first load must hit in the L1,
because before the load is sent to the L2 the permission check is
performed. Therefore if no kernel addresses hit in the L1 the
vulnerability can not occur. We can ensure that is the case by
flushing the L1 whenever we return to userspace. Similarly for
hypervisor vs guest.
In order to flush the L1-D cache on exit, we add a section of nops at
each (h)rfi location that returns to a lower privileged context, and
patch that with some sequence. Newer firmwares are able to advertise
to us that there is a special nop instruction that flushes the L1-D.
If we do not see that advertised, we fall back to doing a displacement
flush in software.
For guest kernels we support migration between some CPU versions, and
different CPUs may use different flush instructions. So that we are
prepared to migrate to a machine with a different flush instruction
activated, we may have to patch more than one flush instruction at
boot if the hypervisor tells us to.
In the end this patch is mostly the work of Nicholas Piggin and
Michael Ellerman. However a cast of thousands contributed to analysis
of the issue, earlier versions of the patch, back ports testing etc.
Many thanks to all of them.
Tested-by: Jon Masters <jcm@redhat.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
In the SLB miss handler we may be returning to user or kernel. We need
to add a check early on and save the result in the cr4 register, and
then we bifurcate the return path based on that.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Similar to the syscall return path, in fast_exception_return we may be
returning to user or kernel context. We already have a test for that,
because we conditionally restore r13. So use that existing test and
branch, and bifurcate the return based on that.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
In the syscall exit path we may be returning to user or kernel
context. We already have a test for that, because we conditionally
restore r13. So use that existing test and branch, and bifurcate the
return based on that.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This commit does simple conversions of rfi/rfid to the new macros that
include the expected destination context. By simple we mean cases
where there is a single well known destination context, and it's
simply a matter of substituting the instruction for the appropriate
macro.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The rfid/hrfid ((Hypervisor) Return From Interrupt) instruction is
used for switching from the kernel to userspace, and from the
hypervisor to the guest kernel. However it can and is also used for
other transitions, eg. from real mode kernel code to virtual mode
kernel code, and it's not always clear from the code what the
destination context is.
To make it clearer when reading the code, add macros which encode the
expected destination context.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
A new hypervisor call has been defined to communicate various
characteristics of the CPU to guests. Add definitions for the hcall
number, flags and a wrapper function.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The hotplug code uses its own workqueue to handle IRQ requests
(pseries_hp_wq), however that workqueue is initialized after
init_ras_IRQ(). That can lead to a kernel panic if any hotplug
interrupts fire after init_ras_IRQ() but before pseries_hp_wq is
initialised. eg:
UDP-Lite hash table entries: 2048 (order: 0, 65536 bytes)
NET: Registered protocol family 1
Unpacking initramfs...
(qemu) object_add memory-backend-ram,id=mem1,size=10G
(qemu) device_add pc-dimm,id=dimm1,memdev=mem1
Unable to handle kernel paging request for data at address 0xf94d03007c421378
Faulting instruction address: 0xc00000000012d744
Oops: Kernel access of bad area, sig: 11 [#1]
LE SMP NR_CPUS=2048 NUMA pSeries
Modules linked in:
CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.15.0-rc2-ziviani+ #26
task: (ptrval) task.stack: (ptrval)
NIP: c00000000012d744 LR: c00000000012d744 CTR: 0000000000000000
REGS: (ptrval) TRAP: 0380 Not tainted (4.15.0-rc2-ziviani+)
MSR: 8000000000009033 <SF,EE,ME,IR,DR,RI,LE> CR: 28088042 XER: 20040000
CFAR: c00000000012d3c4 SOFTE: 0
...
NIP [c00000000012d744] __queue_work+0xd4/0x5c0
LR [c00000000012d744] __queue_work+0xd4/0x5c0
Call Trace:
[c0000000fffefb90] [c00000000012d744] __queue_work+0xd4/0x5c0 (unreliable)
[c0000000fffefc70] [c00000000012dce4] queue_work_on+0xb4/0xf0
This commit makes the RAS IRQ registration explicitly dependent on the
creation of the pseries_hp_wq.
Reported-by: Min Deng <mdeng@redhat.com>
Reported-by: Daniel Henrique Barboza <danielhb@linux.vnet.ibm.com>
Tested-by: Jose Ricardo Ziviani <joserz@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Add a test case of the error code reported when we take a SEGV on a
mapped but inaccessible area. We broke this recently.
Based on a test case from John Sperbeck <jsperbeck@google.com>.
Acked-by: John Sperbeck <jsperbeck@google.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
pte_access_premitted get called in get_user_pages_fast path. If we
have marked the pte PROT_NONE, we should not allow a read access on
the address. With the current implementation we are not checking the
READ and only check for WRITE. This is needed on archs like ppc64 that
implement PROT_NONE using _PAGE_USER access instead of _PAGE_PRESENT.
Also add pte_user check just to make sure we are not accessing kernel
mapping.
Even though there is code duplication, keeping the low level pte
accessors different for different platforms helps in code readability.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
pte_access_premitted get called in get_user_pages_fast path. If we
have marked the pte PROT_NONE, we should not allow a read access on
the address. With the current implementation we are not checking the
READ and only check for WRITE. This is needed on archs like ppc64 that
implement PROT_NONE using RWX access instead of _PAGE_PRESENT. Also
add pte_user check just to make sure we are not accessing kernel
mapping.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
No functional change in this patch. This update gup_hugepte to use the
helper. This will help later when we add memory keys.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
When we migrate a VM from a POWER8 host (XICS) to a POWER9 host
(XICS-on-XIVE), we have an error:
qemu-kvm: Unable to restore KVM interrupt controller state \
(0xff000000) for CPU 0: Invalid argument
This is because kvmppc_xics_set_icp() checks the new state
is internaly consistent, and especially:
...
1129 if (xisr == 0) {
1130 if (pending_pri != 0xff)
1131 return -EINVAL;
...
On the other side, kvmppc_xive_get_icp() doesn't set
neither the pending_pri value, nor the xisr value (set to 0)
(and kvmppc_xive_set_icp() ignores the pending_pri value)
As xisr is 0, pending_pri must be set to 0xff.
Fixes: 5af5099385 ("KVM: PPC: Book3S HV: Native usage of the XIVE interrupt controller")
Cc: stable@vger.kernel.org # v4.12+
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
When restoring a pending interrupt, we are setting the Q bit to force
a retrigger in xive_finish_unmask(). But we also need to force an EOI
in this case to reach the same initial state : P=1, Q=0.
This can be done by not setting 'old_p' for pending interrupts which
will inform xive_finish_unmask() that an EOI needs to be sent.
Fixes: 5af5099385 ("KVM: PPC: Book3S HV: Native usage of the XIVE interrupt controller")
Cc: stable@vger.kernel.org # v4.12+
Suggested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Cédric Le Goater <clg@kaod.org>
Reviewed-by: Laurent Vivier <lvivier@redhat.com>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The H_PAGE_F_SECOND,H_PAGE_F_GIX are not in the 64K main-PTE.
capture these changes in the dump pte report.
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
replace redundant code in __hash_page_4K() and flush_hash_page()
with helper functions pte_get_hash_gslot() and pte_set_hidx()
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
We need PTE bits 3 ,4, 5, 6 and 57 to support protection-keys,
because these are the bits we want to consolidate on across all
configuration to support protection keys.
Bit 3,4,5 and 6 are currently used on 4K-pte kernels. But bit 9
and 10 are available. Hence we use the two available bits and
free up bit 5 and 6. We will still not be able to free up bit 3
and 4. In the absence of any other free bits, we will have to
stay satisfied with what we have :-(. This means we will not
be able to support 32 protection keys, but only 8. The bit
numbers are big-endian as defined in the ISA3.0
This patch does the following change to 4K PTE.
H_PAGE_F_SECOND (S) which occupied bit 4 moves to bit 7.
H_PAGE_F_GIX (G,I,X) which occupied bit 5, 6 and 7 also moves
to bit 8,9, 10 respectively.
H_PAGE_HASHPTE (H) which occupied bit 8 moves to bit 4.
Before the patch, the 4k PTE format was as follows
0 1 2 3 4 5 6 7 8 9 10....................57.....63
: : : : : : : : : : : : :
v v v v v v v v v v v v v
,-,-,-,-,--,--,--,--,-,-,-,-,-,------------------,-,-,-,
|x|x|x|B|S |G |I |X |H| | |x|x|................| |x|x|x|
'_'_'_'_'__'__'__'__'_'_'_'_'_'________________'_'_'_'_'
After the patch, the 4k PTE format is as follows
0 1 2 3 4 5 6 7 8 9 10....................57.....63
: : : : : : : : : : : : :
v v v v v v v v v v v v v
,-,-,-,-,--,--,--,--,-,-,-,-,-,------------------,-,-,-,
|x|x|x|B|H | | |S |G|I|X|x|x|................| |.|.|.|
'_'_'_'_'__'__'__'__'_'_'_'_'_'________________'_'_'_'_'
The patch has no code changes; just swizzles around bits.
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
0xf is considered invalid hidx value. It indicates absence of a backing
HPTE. A PTE is initialized to 0xf either
a) when it is new it is newly allocated to hold 4k-backing-HPTE
or
b) Any time it gets demoted to a 4k-backing-HPTE
This patch shifts the representation by one-modulo-0xf; i.e hidx 0 is
represented as 1, 1 as 2,... , and 0xf as 0. This convention lets us
initialize the secondary-part of the PTE to all zeroes. PTEs are anyway
zero'd when allocated. We do not have to zero them again; thus saving on
the initialization.
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Rearrange 64K PTE bits to free up bits 3, 4, 5 and 6
in the 64K backed HPTE pages. This along with the earlier
patch will entirely free up the four bits from 64K PTE.
The bit numbers are big-endian as defined in the ISA3.0
This patch does the following change to 64K PTE backed
by 64K HPTE.
H_PAGE_F_SECOND (S) which occupied bit 4 moves to the
second part of the pte to bit 60.
H_PAGE_F_GIX (G,I,X) which occupied bit 5, 6 and 7 also
moves to the second part of the pte to bit 61,
62, 63, 64 respectively
since bit 7 is now freed up, we move H_PAGE_BUSY (B) from
bit 9 to bit 7.
The second part of the PTE will hold
(H_PAGE_F_SECOND|H_PAGE_F_GIX) at bit 60,61,62,63.
NOTE: None of the bits in the secondary PTE were not used
by 64k-HPTE backed PTE.
Before the patch, the 64K HPTE backed 64k PTE format was
as follows
0 1 2 3 4 5 6 7 8 9 10...........................63
: : : : : : : : : : : :
v v v v v v v v v v v v
,-,-,-,-,--,--,--,--,-,-,-,-,-,------------------,-,-,-,
|x|x|x| |S |G |I |X |x|B| |x|x|................|x|x|x|x| <- primary pte
'_'_'_'_'__'__'__'__'_'_'_'_'_'________________'_'_'_'_'
| | | | | | | | | | | | |..................| | | | | <- secondary pte
'_'_'_'_'__'__'__'__'_'_'_'_'__________________'_'_'_'_'
After the patch, the 64k HPTE backed 64k PTE format is
as follows
0 1 2 3 4 5 6 7 8 9 10...........................63
: : : : : : : : : : : :
v v v v v v v v v v v v
,-,-,-,-,--,--,--,--,-,-,-,-,-,------------------,-,-,-,
|x|x|x| | | | |B |x| | |x|x|................|.|.|.|.| <- primary pte
'_'_'_'_'__'__'__'__'_'_'_'_'_'________________'_'_'_'_'
| | | | | | | | | | | | |..................|S|G|I|X| <- secondary pte
'_'_'_'_'__'__'__'__'_'_'_'_'__________________'_'_'_'_'
The above PTE changes is applicable to hugetlbpages aswell.
The patch does the following code changes:
a) moves the H_PAGE_F_SECOND and H_PAGE_F_GIX to 4k PTE
header since it is no more needed b the 64k PTEs.
b) abstracts out __real_pte() and __rpte_to_hidx() so the
caller need not know the bit location of the slot.
c) moves the slot bits to the secondary pte.
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Rearrange 64K PTE bits to free up bits 3, 4, 5 and 6,
in the 4K backed HPTE pages.These bits continue to be used
for 64K backed HPTE pages in this patch, but will be freed
up in the next patch. The bit numbers are big-endian as
defined in the ISA3.0
The patch does the following change to the 4k HTPE backed
64K PTE's format.
H_PAGE_BUSY moves from bit 3 to bit 9 (B bit in the figure
below)
V0 which occupied bit 4 is not used anymore.
V1 which occupied bit 5 is not used anymore.
V2 which occupied bit 6 is not used anymore.
V3 which occupied bit 7 is not used anymore.
Before the patch, the 4k backed 64k PTE format was as follows
0 1 2 3 4 5 6 7 8 9 10...........................63
: : : : : : : : : : : :
v v v v v v v v v v v v
,-,-,-,-,--,--,--,--,-,-,-,-,-,------------------,-,-,-,
|x|x|x|B|V0|V1|V2|V3|x| | |x|x|................|x|x|x|x| <- primary pte
'_'_'_'_'__'__'__'__'_'_'_'_'_'________________'_'_'_'_'
|S|G|I|X|S |G |I |X |S|G|I|X|..................|S|G|I|X| <- secondary pte
'_'_'_'_'__'__'__'__'_'_'_'_'__________________'_'_'_'_'
After the patch, the 4k backed 64k PTE format is as follows
0 1 2 3 4 5 6 7 8 9 10...........................63
: : : : : : : : : : : :
v v v v v v v v v v v v
,-,-,-,-,--,--,--,--,-,-,-,-,-,------------------,-,-,-,
|x|x|x| | | | | |x|B| |x|x|................|.|.|.|.| <- primary pte
'_'_'_'_'__'__'__'__'_'_'_'_'_'________________'_'_'_'_'
|S|G|I|X|S |G |I |X |S|G|I|X|..................|S|G|I|X| <- secondary pte
'_'_'_'_'__'__'__'__'_'_'_'_'__________________'_'_'_'_'
the four bits S,G,I,X (one quadruplet per 4k HPTE) that
cache the hash-bucket slot value, is initialized to
1,1,1,1 indicating -- an invalid slot. If a HPTE gets
cached in a 1111 slot(i.e 7th slot of secondary hash
bucket), it is released immediately. In other words,
even though 1111 is a valid slot value in the hash
bucket, we consider it invalid and release the slot and
the HPTE. This gives us the opportunity to determine
the validity of S,G,I,X bits based on its contents and
not on any of the bits V0,V1,V2 or V3 in the primary PTE
When we release a HPTE cached in the 1111 slot
we also release a legitimate slot in the primary
hash bucket and unmap its corresponding HPTE. This
is to ensure that we do get a HPTE cached in a slot
of the primary hash bucket, the next time we retry.
Though treating 1111 slot as invalid, reduces the
number of available slots in the hash bucket and may
have an effect on the performance, the probabilty of
hitting a 1111 slot is extermely low.
Compared to the current scheme, the above scheme
reduces the number of false hash table updates
significantly and has the added advantage of releasing
four valuable PTE bits for other purpose.
NOTE:even though bits 3, 4, 5, 6, 7 are not used when
the 64K PTE is backed by 4k HPTE, they continue to be
used if the PTE gets backed by 64k HPTE. The next
patch will decouple that aswell, and truely release the
bits.
This idea was jointly developed by Paul Mackerras,
Aneesh, Michael Ellermen and myself.
4K PTE format remains unchanged currently.
The patch does the following code changes
a) PTE flags are split between 64k and 4k header files.
b) __hash_page_4K() is reimplemented to reflect the
above logic.
Acked-by: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Introduce pte_get_hash_gslot()() which returns the global slot number of
the HPTE in the global hash table.
This function will come in handy as we work towards re-arranging the PTE
bits in the later patches.
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>