diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-01 11:21:57 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-01 11:21:57 -0700 |
commit | 9f159ae07f07fc540290f21937231034f554bdd7 (patch) | |
tree | f343157aefa90c11e1e136514e2222e8cba0dc33 /net/smc/smc_cdc.h | |
parent | 5fb181cba01088924a68441753843e5acfd012ff (diff) | |
parent | 7af0145067bc429a09ac4047b167c0971c9f0dc7 (diff) | |
download | linux-stable-9f159ae07f07fc540290f21937231034f554bdd7.tar.gz linux-stable-9f159ae07f07fc540290f21937231034f554bdd7.tar.bz2 linux-stable-9f159ae07f07fc540290f21937231034f554bdd7.zip |
Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fixes from Thomas Gleixner:
"A set of fixes for x86:
- Fix the bogus detection of 32bit user mode for uretprobes which
caused corruption of the user return address resulting in
application crashes. In the uprobes handler in_ia32_syscall() is
obviously always returning false on a 64bit kernel. Use
user_64bit_mode() instead which works correctly.
- Prevent large page splitting when ftrace flips RW/RO on the kernel
text which caused iTLB performance issues. Ftrace wants to be
converted to text_poke() which avoids the problem, but for now
allow large page preservation in the static protections check when
the change request spawns a full large page.
- Prevent arch_dynirq_lower_bound() from returning 0 when the IOAPIC
is configured via device tree. In the device tree case the GSI 1:1
mapping is meaningless therefore the lower bound which protects the
GSI range on ACPI machines is irrelevant. Return the lower bound
which the core hands to the function instead of blindly returning 0
which causes the core to allocate the invalid virtual interupt
number 0 which in turn prevents all drivers from allocating and
requesting an interrupt.
- Remove the bogus initialization of LDR and DFR in the 32bit bigsmp
APIC driver. That uses physical destination mode where LDR/DFR are
ignored, but the initialization and the missing clear of LDR caused
the APIC to be left in a inconsistent state on kexec/reboot.
- Clear LDR when clearing the APIC registers so the APIC is in a well
defined state.
- Initialize variables proper in the find_trampoline_placement()
code.
- Silence GCC( build warning for the real mode part of the build"
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/mm/cpa: Prevent large page split when ftrace flips RW on kernel text
x86/build: Add -Wnoaddress-of-packed-member to REALMODE_CFLAGS, to silence GCC9 build warning
x86/boot/compressed/64: Fix missing initialization in find_trampoline_placement()
x86/apic: Include the LDR when clearing out APIC registers
x86/apic: Do not initialize LDR and DFR for bigsmp
uprobes/x86: Fix detection of 32-bit user mode
x86/apic: Fix arch_dynirq_lower_bound() bug for DT enabled machines
Diffstat (limited to 'net/smc/smc_cdc.h')
0 files changed, 0 insertions, 0 deletions