Pull powerpc updates from Michael Ellerman:
"Livepatch support for 32-bit is probably the standout new feature,
otherwise mostly just lots of bits and pieces all over the board.
There's a series of commits cleaning up function descriptor handling,
which touches a few other arches as well as LKDTM. It has acks from
Arnd, Kees and Helge.
Summary:
- Enforce kernel RO, and implement STRICT_MODULE_RWX for 603.
- Add support for livepatch to 32-bit.
- Implement CONFIG_DYNAMIC_FTRACE_WITH_ARGS.
- Merge vdso64 and vdso32 into a single directory.
- Fix build errors with newer binutils.
- Add support for UADDR64 relocations, which are emitted by some
toolchains. This allows powerpc to build with the latest lld.
- Fix (another) potential userspace r13 corruption in transactional
memory handling.
- Cleanups of function descriptor handling & related fixes to LKDTM.
Thanks to Abdul Haleem, Alexey Kardashevskiy, Anders Roxell, Aneesh
Kumar K.V, Anton Blanchard, Arnd Bergmann, Athira Rajeev, Bhaskar
Chowdhury, Cédric Le Goater, Chen Jingwen, Christophe JAILLET,
Christophe Leroy, Corentin Labbe, Daniel Axtens, Daniel Henrique
Barboza, David Dai, Fabiano Rosas, Ganesh Goudar, Guo Zhengkui, Hangyu
Hua, Haren Myneni, Hari Bathini, Igor Zhbanov, Jakob Koschel, Jason
Wang, Jeremy Kerr, Joachim Wiberg, Jordan Niethe, Julia Lawall, Kajol
Jain, Kees Cook, Laurent Dufour, Madhavan Srinivasan, Mamatha Inamdar,
Maxime Bizon, Maxim Kiselev, Maxim Kochetkov, Michal Suchanek,
Nageswara R Sastry, Nathan Lynch, Naveen N. Rao, Nicholas Piggin,
Nour-eddine Taleb, Paul Menzel, Ping Fang, Pratik R. Sampat, Randy
Dunlap, Ritesh Harjani, Rohan McLure, Russell Currey, Sachin Sant,
Segher Boessenkool, Shivaprasad G Bhat, Sourabh Jain, Thierry Reding,
Tobias Waldekranz, Tyrel Datwyler, Vaibhav Jain, Vladimir Oltean,
Wedson Almeida Filho, and YueHaibing"
* tag 'powerpc-5.18-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (179 commits)
powerpc/pseries: Fix use after free in remove_phb_dynamic()
powerpc/time: improve decrementer clockevent processing
powerpc/time: Fix KVM host re-arming a timer beyond decrementer range
powerpc/tm: Fix more userspace r13 corruption
powerpc/xive: fix return value of __setup handler
powerpc/64: Add UADDR64 relocation support
powerpc: 8xx: fix a return value error in mpc8xx_pic_init
powerpc/ps3: remove unneeded semicolons
powerpc/64: Force inlining of prevent_user_access() and set_kuap()
powerpc/bitops: Force inlining of fls()
powerpc: declare unmodified attribute_group usages const
powerpc/spufs: Fix build warning when CONFIG_PROC_FS=n
powerpc/secvar: fix refcount leak in format_show()
powerpc/64e: Tie PPC_BOOK3E_64 to PPC_FSL_BOOK3E
powerpc: Move C prototypes out of asm-prototypes.h
powerpc/kexec: Declare kexec_paca static
powerpc/smp: Declare current_set static
powerpc: Cleanup asm-prototypes.c
powerpc/ftrace: Use STK_GOT in ftrace_mprofile.S
powerpc/ftrace: Regroup PPC64 specific operations in ftrace_mprofile.S
...
This is straightforward for everything except nohash64 where we
indirect through pmd_page(). There must be a better way to do this.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
It has been reported some configuration where the kernel doesn't
boot with KASAN enabled.
This is due to wrong BAT allocation for the KASAN area:
---[ Data Block Address Translation ]---
0: 0xc0000000-0xcfffffff 0x00000000 256M Kernel rw m
1: 0xd0000000-0xdfffffff 0x10000000 256M Kernel rw m
2: 0xe0000000-0xefffffff 0x20000000 256M Kernel rw m
3: 0xf8000000-0xf9ffffff 0x2a000000 32M Kernel rw m
4: 0xfa000000-0xfdffffff 0x2c000000 64M Kernel rw m
A BAT must have both virtual and physical addresses alignment matching
the size of the BAT. This is not the case for BAT 4 above.
Fix kasan_init_region() by using block_size() function that is in
book3s32/mmu.c. To be able to reuse it here, make it non static and
change its name to bat_block_size() in order to avoid name conflict
with block_size() defined in <linux/blkdev.h>
Also reuse find_free_bat() to avoid an error message from setbat()
when no BAT is available.
And allocate memory outside of linear memory mapping to avoid
wasting that precious space.
With this change we get correct alignment for BATs and KASAN shadow
memory is allocated outside the linear memory space.
---[ Data Block Address Translation ]---
0: 0xc0000000-0xcfffffff 0x00000000 256M Kernel rw
1: 0xd0000000-0xdfffffff 0x10000000 256M Kernel rw
2: 0xe0000000-0xefffffff 0x20000000 256M Kernel rw
3: 0xf8000000-0xfbffffff 0x7c000000 64M Kernel rw
4: 0xfc000000-0xfdffffff 0x7a000000 32M Kernel rw
Fixes: 7974c47326 ("powerpc/32s: Implement dedicated kasan_init_region()")
Cc: stable@vger.kernel.org
Reported-by: Maxime Bizon <mbizon@freebox.fr>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Maxime Bizon <mbizon@freebox.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/7a50ef902494d1325227d47d33dada01e52e5518.1641818726.git.christophe.leroy@csgroup.eu
Make the following functions generic to all platforms.
- bad_kuap_fault()
- kuap_assert_locked()
- kuap_save_and_lock() (PPC32 only)
- kuap_kernel_restore()
- kuap_get_and_assert_locked()
And for all platforms except book3s/64
- allow_user_access()
- prevent_user_access()
- prevent_user_access_return()
- restore_user_access()
Prepend __ in front of the name of platform specific ones.
For now the generic just calls the platform specific, but
next patch will move redundant parts of specific functions
into the generic one.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/eaef143a8dae7288cd34565ffa7b49c16aee1ec3.1634627931.git.christophe.leroy@csgroup.eu
Calling 'mfsr' to get the content of segment registers is heavy,
in addition it requires clearing of the 'reserved' bits.
In order to avoid this operation, save it in mm context and in
thread struct.
The saved sr0 is the one used by kernel, this means that on
locking entry it can be used as is.
For unlocking, the only thing to do is to clear SR_NX.
This improves null_syscall selftest by 12 cycles, ie 4%.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/b02baf2ed8f09bad910dfaeeb7353b2ae6830525.1634627931.git.christophe.leroy@csgroup.eu
When interrupt and syscall entries where converted to C, KUEP locking
and unlocking was also converted. It improved performance by unrolling
the loop, and allowed easily implementing boot time deactivation of
KUEP.
However, null_syscall selftest shows that KUEP is still heavy
(361 cycles with KUEP, 212 cycles without).
A way to improve more is to group 'mtsr's together, instead of
repeating 'addi' + 'mtsr' several times.
In order to do that, more registers need to be available. In C, GCC
will always be able to provide the requested number of registers, but
at the cost of saving some data on the stack, which is counter
performant here.
So let's do it in assembly, when we have full control of which
register can be used. It also has the advantage of locking earlier
and unlocking later and it helps GCC generating less tricky code.
The only drawback is to make boot time deactivation less straight
forward and require 'hand' instruction patching.
Group 'mtsr's by 4.
With this change, null_syscall selftest reports 336 cycles. Without
the change it was 361 cycles, that's a 7% reduction.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/115cb279e9b9948dfd93a065e047081c59e3a2a6.1634627931.git.christophe.leroy@csgroup.eu
At interrupt exit, kuap_kernel_restore() calls kuap_unlock() with the
value contained in regs->kuap. However, when regs->kuap contains
0xffffffff it means that KUAP was not unlocked so calling kuap_unlock()
is unrelevant and results in jeopardising the contents of kernel space
segment registers.
So check that regs->kuap doesn't contain KUAP_NONE before calling
kuap_unlock(). In the meantime it also means that if KUAP has not
been correcly locked back at interrupt exit, it must be locked
before continuing. This is done by checking the content of
current->thread.kuap which was returned by kuap_get_and_assert_locked()
Fixes: 16132529ce ("powerpc/32s: Rework Kernel Userspace Access Protection")
Reported-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/0d0c4d0f050a637052287c09ba521bad960a2790.1631715131.git.christophe.leroy@csgroup.eu
Commit b5efec00b6 ("powerpc/32s: Move KUEP locking/unlocking in C")
removed the 'isync' instruction after adding/removing NX bit in user
segments. The reasoning behind this change was that when setting the
NX bit we don't mind it taking effect with delay as the kernel never
executes text from userspace, and when clearing the NX bit this is
to return to userspace and then the 'rfi' should synchronise the
context.
However, it looks like on book3s/32 having a hash page table, at least
on the G3 processor, we get an unexpected fault from userspace, then
this is followed by something wrong in the verification of MSR_PR
at end of another interrupt.
This is fixed by adding back the removed isync() following update
of NX bit in user segment registers. Only do it for cores with an
hash table, as 603 cores don't exhibit that problem and the two isync
increase ./null_syscall selftest by 6 cycles on an MPC 832x.
First problem: unexpected WARN_ON() for mysterious PROTFAULT
WARNING: CPU: 0 PID: 1660 at arch/powerpc/mm/fault.c:354 do_page_fault+0x6c/0x5b0
Modules linked in:
CPU: 0 PID: 1660 Comm: Xorg Not tainted 5.13.0-pmac-00028-gb3c15b60339a #40
NIP: c001b5c8 LR: c001b6f8 CTR: 00000000
REGS: e2d09e40 TRAP: 0700 Not tainted (5.13.0-pmac-00028-gb3c15b60339a)
MSR: 00021032 <ME,IR,DR,RI> CR: 42d04f30 XER: 20000000
GPR00: c000424c e2d09f00 c301b680 e2d09f40 0000001e 42000000 00cba028 00000000
GPR08: 08000000 48000010 c301b680 e2d09f30 22d09f30 00c1fff0 00cba000 a7b7ba4c
GPR16: 00000031 00000000 00000000 00000000 00000000 00000000 a7b7b0d0 00c5c010
GPR24: a7b7b64c a7b7d2f0 00000004 00000000 c1efa6c0 00cba02c 00000300 e2d09f40
NIP [c001b5c8] do_page_fault+0x6c/0x5b0
LR [c001b6f8] do_page_fault+0x19c/0x5b0
Call Trace:
[e2d09f00] [e2d09f04] 0xe2d09f04 (unreliable)
[e2d09f30] [c000424c] DataAccess_virt+0xd4/0xe4
--- interrupt: 300 at 0xa7a261dc
NIP: a7a261dc LR: a7a253bc CTR: 00000000
REGS: e2d09f40 TRAP: 0300 Not tainted (5.13.0-pmac-00028-gb3c15b60339a)
MSR: 0000d032 <EE,PR,ME,IR,DR,RI> CR: 228428e2 XER: 20000000
DAR: 00cba02c DSISR: 42000000
GPR00: a7a27448 afa6b0e0 a74c35c0 a7b7b614 0000001e a7b7b614 00cba028 00000000
GPR08: 00020fd9 00000031 00cb9ff8 a7a273b0 220028e2 00c1fff0 00cba000 a7b7ba4c
GPR16: 00000031 00000000 00000000 00000000 00000000 00000000 a7b7b0d0 00c5c010
GPR24: a7b7b64c a7b7d2f0 00000004 00000002 0000001e a7b7b614 a7b7aff4 00000030
NIP [a7a261dc] 0xa7a261dc
LR [a7a253bc] 0xa7a253bc
--- interrupt: 300
Instruction dump:
7c4a1378 810300a0 75278410 83820298 83a300a4 553b018c 551e0036 4082038c
2e1b0000 40920228 75280800 41820220 <0fe00000> 3b600000 41920214 81420594
Second problem: MSR PR is seen unset allthough the interrupt frame shows it set
kernel BUG at arch/powerpc/kernel/interrupt.c:458!
Oops: Exception in kernel mode, sig: 5 [#1]
BE PAGE_SIZE=4K MMU=Hash SMP NR_CPUS=2 PowerMac
Modules linked in:
CPU: 0 PID: 1660 Comm: Xorg Tainted: G W 5.13.0-pmac-00028-gb3c15b60339a #40
NIP: c0011434 LR: c001629c CTR: 00000000
REGS: e2d09e70 TRAP: 0700 Tainted: G W (5.13.0-pmac-00028-gb3c15b60339a)
MSR: 00029032 <EE,ME,IR,DR,RI> CR: 42d09f30 XER: 00000000
GPR00: 00000000 e2d09f30 c301b680 e2d09f40 83440000 c44d0e68 e2d09e8c 00000000
GPR08: 00000002 00dc228a 00004000 e2d09f30 22d09f30 00c1fff0 afa6ceb4 00c26144
GPR16: 00c25fb8 00c26140 afa6ceb8 90000000 00c944d8 0000001c 00000000 00200000
GPR24: 00000000 000001fb afa6d1b4 00000001 00000000 a539a2a0 a530fd80 00000089
NIP [c0011434] interrupt_exit_kernel_prepare+0x10/0x70
LR [c001629c] interrupt_return+0x9c/0x144
Call Trace:
[e2d09f30] [c000424c] DataAccess_virt+0xd4/0xe4 (unreliable)
--- interrupt: 300 at 0xa09be008
NIP: a09be008 LR: a09bdfe8 CTR: a09bdfc0
REGS: e2d09f40 TRAP: 0300 Tainted: G W (5.13.0-pmac-00028-gb3c15b60339a)
MSR: 0000d032 <EE,PR,ME,IR,DR,RI> CR: 420028e2 XER: 20000000
DAR: a539a308 DSISR: 0a000000
GPR00: a7b90d50 afa6b2d0 a74c35c0 a0a8b690 a0a8b698 a5365d70 a4fa82a8 00000004
GPR08: 00000000 a09bdfc0 00000000 a5360000 a09bde7c 00c1fff0 afa6ceb4 00c26144
GPR16: 00c25fb8 00c26140 afa6ceb8 90000000 00c944d8 0000001c 00000000 00200000
GPR24: 00000000 000001fb afa6d1b4 00000001 00000000 a539a2a0 a530fd80 00000089
NIP [a09be008] 0xa09be008
LR [a09bdfe8] 0xa09bdfe8
--- interrupt: 300
Instruction dump:
80010024 83e1001c 7c0803a6 4bffff80 3bc00800 4bffffd0 486b42fd 4bffffcc
81430084 71480002 41820038 554a0462 <0f0a0000> 80620060 74630001 40820034
Fixes: b5efec00b6 ("powerpc/32s: Move KUEP locking/unlocking in C")
Cc: stable@vger.kernel.org # v5.13+
Reported-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/4856f5574906e2aec0522be17bf3848a22b2cd0b.1629269345.git.christophe.leroy@csgroup.eu
KUEP implements the update of user segment registers.
Move it into mmu-hash.h in order to use it from other places.
And inline kuep_lock() and kuep_unlock(). Inlining kuep_lock() is
important for system_call_exception(), otherwise system_call_exception()
has to save into stack the system call parameters that are used just
after, and doing that takes more instructions than kuep_lock() itself.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/24591ca480d14a62ef910e38a5273d551262c4a2.1622708530.git.christophe.leroy@csgroup.eu
Function names should tell what the function does, not how.
mfsrin() and mtsrin() are read/writing segment registers.
They are called that way because they are using mfsrin and mtsrin
instructions, but it doesn't matter for the caller.
In preparation of following patch, change their name to mfsr() and mtsr()
in order to make it obvious they manipulate segment registers without
messing up with how they do 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/f92d99f4349391b77766745900231aa880a0efb5.1612612022.git.christophe.leroy@csgroup.eu
Pull powerpc updates from Michael Ellerman:
- Switch to the generic C VDSO, as well as some cleanups of our VDSO
setup/handling code.
- Support for KUAP (Kernel User Access Prevention) on systems using the
hashed page table MMU, using memory protection keys.
- Better handling of PowerVM SMT8 systems where all threads of a core
do not share an L2, allowing the scheduler to make better scheduling
decisions.
- Further improvements to our machine check handling.
- Show registers when unwinding interrupt frames during stack traces.
- Improvements to our pseries (PowerVM) partition migration code.
- Several series from Christophe refactoring and cleaning up various
parts of the 32-bit code.
- Other smaller features, fixes & cleanups.
Thanks to: Alan Modra, Alexey Kardashevskiy, Andrew Donnellan, Aneesh
Kumar K.V, Ard Biesheuvel, Athira Rajeev, Balamuruhan S, Bill Wendling,
Cédric Le Goater, Christophe Leroy, Christophe Lombard, Colin Ian King,
Daniel Axtens, David Hildenbrand, Frederic Barrat, Ganesh Goudar,
Gautham R. Shenoy, Geert Uytterhoeven, Giuseppe Sacco, Greg Kurz,
Harish, Jan Kratochvil, Jordan Niethe, Kaixu Xia, Laurent Dufour,
Leonardo Bras, Madhavan Srinivasan, Mahesh Salgaonkar, Mathieu
Desnoyers, Nathan Lynch, Nicholas Piggin, Oleg Nesterov, Oliver
O'Halloran, Oscar Salvador, Po-Hsu Lin, Qian Cai, Qinglang Miao, Randy
Dunlap, Ravi Bangoria, Sachin Sant, Sandipan Das, Sebastian Andrzej
Siewior , Segher Boessenkool, Srikar Dronamraju, Tyrel Datwyler, Uwe
Kleine-König, Vincent Stehlé, Youling Tang, and Zhang Xiaoxu.
* tag 'powerpc-5.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (304 commits)
powerpc/32s: Fix cleanup_cpu_mmu_context() compile bug
powerpc: Add config fragment for disabling -Werror
powerpc/configs: Add ppc64le_allnoconfig target
powerpc/powernv: Rate limit opal-elog read failure message
powerpc/pseries/memhotplug: Quieten some DLPAR operations
powerpc/ps3: use dma_mapping_error()
powerpc: force inlining of csum_partial() to avoid multiple csum_partial() with GCC10
powerpc/perf: Fix Threshold Event Counter Multiplier width for P10
powerpc/mm: Fix hugetlb_free_pmd_range() and hugetlb_free_pud_range()
KVM: PPC: Book3S HV: Fix mask size for emulated msgsndp
KVM: PPC: fix comparison to bool warning
KVM: PPC: Book3S: Assign boolean values to a bool variable
powerpc: Inline setup_kup()
powerpc/64s: Mark the kuap/kuep functions non __init
KVM: PPC: Book3S HV: XIVE: Add a comment regarding VP numbering
powerpc/xive: Improve error reporting of OPAL calls
powerpc/xive: Simplify xive_do_source_eoi()
powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_EOI_FW
powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_MASK_FW
powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_SHIFT_BUG
...
Currently pmac32_defconfig with SMP=y doesn't build:
arch/powerpc/platforms/powermac/smp.c:
error: implicit declaration of function 'cleanup_cpu_mmu_context'
It would be nice for consistency if all platforms clear mm_cpumask and
flush TLBs on unplug, but the TLB invalidation bug described in commit
01b0f0eae0 ("powerpc/64s: Trim offlined CPUs from mm_cpumasks") only
applies to 64s and for now we only have the TLB flush code for that
platform.
So just add an empty version for 32-bit Book3S.
Fixes: 01b0f0eae0 ("powerpc/64s: Trim offlined CPUs from mm_cpumasks")
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Change log based on comments from Nick]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This partially reverts commit eb232b1624 ("powerpc/book3s64/kuap: Improve
error reporting with KUAP") and update the fault handler to print
[ 55.022514] Kernel attempted to access user page (7e6725b70000) - exploit attempt? (uid: 0)
[ 55.022528] BUG: Unable to handle kernel data access on read at 0x7e6725b70000
[ 55.022533] Faulting instruction address: 0xc000000000e8b9bc
[ 55.022540] Oops: Kernel access of bad area, sig: 11 [#1]
....
when the kernel access userspace address without unlocking AMR.
bad_kuap_fault() is added as part of commit 5e5be3aed2 ("powerpc/mm: Detect
bad KUAP faults") to catch userspace access incorrectly blocked by AMR. Hence
retain the full stack dump there even with hash translation. Also, add a comment
explaining the difference between hash and radix.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201208031539.84878-1-aneesh.kumar@linux.ibm.com
The placeholder for instruction selection should use the second
argument's operand, which is %1, not %0. This could generate incorrect
assembly code if the memory addressing of operand %0 is a different
form from that of operand %1.
Also remove the %Un placeholder because having %Un placeholders
for two operands which are based on the same local var (ptep) doesn't
make much sense. By the way, it doesn't change the current behaviour
because "<>" constraint is missing for the associated "=m".
[chleroy: revised commit log iaw segher's comments and removed %U0]
Fixes: 9bf2b5cdc5 ("powerpc: Fixes for CONFIG_PTE_64BIT for SMP support")
Cc: <stable@vger.kernel.org> # v2.6.28+
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Acked-by: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/96354bd77977a6a933fe9020da57629007fdb920.1603358942.git.christophe.leroy@csgroup.eu
Stefan Agner reported a bug when using zsram on 32-bit Arm machines
with RAM above the 4GB address boundary:
Unable to handle kernel NULL pointer dereference at virtual address 00000000
pgd = a27bd01c
[00000000] *pgd=236a0003, *pmd=1ffa64003
Internal error: Oops: 207 [#1] SMP ARM
Modules linked in: mdio_bcm_unimac(+) brcmfmac cfg80211 brcmutil raspberrypi_hwmon hci_uart crc32_arm_ce bcm2711_thermal phy_generic genet
CPU: 0 PID: 123 Comm: mkfs.ext4 Not tainted 5.9.6 #1
Hardware name: BCM2711
PC is at zs_map_object+0x94/0x338
LR is at zram_bvec_rw.constprop.0+0x330/0xa64
pc : [<c0602b38>] lr : [<c0bda6a0>] psr: 60000013
sp : e376bbe0 ip : 00000000 fp : c1e2921c
r10: 00000002 r9 : c1dda730 r8 : 00000000
r7 : e8ff7a00 r6 : 00000000 r5 : 02f9ffa0 r4 : e3710000
r3 : 000fdffe r2 : c1e0ce80 r1 : ebf979a0 r0 : 00000000
Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment user
Control: 30c5383d Table: 235c2a80 DAC: fffffffd
Process mkfs.ext4 (pid: 123, stack limit = 0x495a22e6)
Stack: (0xe376bbe0 to 0xe376c000)
As it turns out, zsram needs to know the maximum memory size, which
is defined in MAX_PHYSMEM_BITS when CONFIG_SPARSEMEM is set, or in
MAX_POSSIBLE_PHYSMEM_BITS on the x86 architecture.
The same problem will be hit on all 32-bit architectures that have a
physical address space larger than 4GB and happen to not enable sparsemem
and include asm/sparsemem.h from asm/pgtable.h.
After the initial discussion, I suggested just always defining
MAX_POSSIBLE_PHYSMEM_BITS whenever CONFIG_PHYS_ADDR_T_64BIT is
set, or provoking a build error otherwise. This addresses all
configurations that can currently have this runtime bug, but
leaves all other configurations unchanged.
I looked up the possible number of bits in source code and
datasheets, here is what I found:
- on ARC, CONFIG_ARC_HAS_PAE40 controls whether 32 or 40 bits are used
- on ARM, CONFIG_LPAE enables 40 bit addressing, without it we never
support more than 32 bits, even though supersections in theory allow
up to 40 bits as well.
- on MIPS, some MIPS32r1 or later chips support 36 bits, and MIPS32r5
XPA supports up to 60 bits in theory, but 40 bits are more than
anyone will ever ship
- On PowerPC, there are three different implementations of 36 bit
addressing, but 32-bit is used without CONFIG_PTE_64BIT
- On RISC-V, the normal page table format can support 34 bit
addressing. There is no highmem support on RISC-V, so anything
above 2GB is unused, but it might be useful to eventually support
CONFIG_ZRAM for high pages.
Fixes: 61989a80fb ("staging: zsmalloc: zsmalloc memory allocation library")
Fixes: 02390b87a9 ("mm/zsmalloc: Prepare to variable MAX_PHYSMEM_BITS")
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Reviewed-by: Stefan Agner <stefan@agner.ch>
Tested-by: Stefan Agner <stefan@agner.ch>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Link: https://lore.kernel.org/linux-mm/bdfa44bf1c570b05d6c70898e2bbb0acf234ecdf.1604762181.git.stefan@agner.ch/
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
