2.4.x arch/ia64 update
Hi Marcelo,
Please do a
bk pull http://lia64.bkbits.net/to-marcelo-2.4
This will update the following files:
arch/ia64/config.in | 30 +- arch/ia64/hp/common/sba_iommu.c | 544 ++++++++++++++++------------------------ arch/ia64/ia32/sys_ia32.c | 2 arch/ia64/kernel/acpi.c | 18 + arch/ia64/kernel/efi.c | 12 arch/ia64/kernel/ia64_ksyms.c | 4 arch/ia64/kernel/ivt.S | 24 + arch/ia64/kernel/mca.c | 111 ++++---- arch/ia64/kernel/mca_asm.S | 342 ++++++++++++++++--------- arch/ia64/kernel/pci.c | 10 arch/ia64/kernel/perfmon.c | 2 arch/ia64/kernel/salinfo.c | 9 arch/ia64/kernel/setup.c | 3 arch/ia64/kernel/sys_ia64.c | 5 arch/ia64/mm/Makefile | 1 arch/ia64/mm/hugetlbpage.c | 513 +++++++++++++++++++++++++++++++++++++ arch/ia64/mm/init.c | 24 + arch/ia64/tools/print_offsets.c | 2 include/asm-ia64/mca.h | 14 - include/asm-ia64/mmu_context.h | 9 include/asm-ia64/page.h | 35 ++ include/asm-ia64/pgtable.h | 6 include/asm-ia64/processor.h | 1 include/asm-ia64/tlb.h | 2 include/asm-ia64/xor.h | 10 25 files changed, 1213 insertions(+), 520 deletions(-)
through these ChangeSets:
<[email protected]> (04/01/20 1.1283)
ia64: Add acpi_register_irq() interface.
(This is only the ia64-specific part of this patch)
<[email protected]> (04/01/20 1.1282)
ia64: Add generic RAID xor routines with prefetch.
(This includes only the ia64-specific parts of this patch)
<[email protected]> (04/01/20 1.1281)
ia64: Move mmu_gathers[] to local_cpu_data on ia64 (only ia64-specific bits)
This is a patch that moves mmu_gathers into local_cpu_data on IA64 NUMA. I'm not exactly sure where to push this patch, because it does touch include/asm-generic/tlb.h although it has no effect on non ia64 arches.
The main reason for making this change is that the mmu_gathers array gets very large as the number of processors increases.
<[email protected]> (04/01/20 1.1280)
ia64: hugetlb support (ia64-specific parts)
<[email protected]> (04/01/15 1.1267.35.21)
ia64: Export acpi_hp_csr_space() for modular agpgart.
<[email protected]> (04/01/15 1.1267.35.20)
ia64: sba_iommu: print note about reserving IOVA space for agpgart.
<[email protected]> (04/01/15 1.1267.35.19)
ia64: sba_iommu: use memparse, long double
<[email protected]> (04/01/14 1.1267.35.18)
[PATCH] ia64: sba_iommu update
This patch does a couple things:
* Allows iommu page size different than PAGE_SIZE. This was largely done by Bjorn. The motivation for this is that sx1000 hardware officially only supports use of the iommu with a 4k page size. Thus the default is now 4k for sx1000 and PAGE_SIZE for zx1.
* Cleanup the runtime statistics gathering such that we can turn it on for some info w/o impacting runtime performance.
<[email protected]> (04/01/14 1.1267.35.17)
ia64: Skip zero-length resources in PCI root bridge _CRS
<[email protected]> (04/01/14 1.1267.35.16)
ia64: Fix broken merge (remove mmu_gathers[] defn)
<[email protected]> (04/01/14 1.1267.35.15)
ia64: Fix system type selection to workaround menuconfig bug (select "HP",
get "HP-simulator").
<[email protected]> (04/01/14 1.1267.35.14)
[PATCH] ia64: ia32 sigaltstack() fix
The attached patch fixes a bug introduced by the earlier patch to handle the differences between ia32 and ia64 in the definition of MINSIGSTKSZ.
<[email protected]> (04/01/14 1.1267.35.13)
[PATCH] ia64: fix ia64_ctx.lock deadlock
I hit a deadlock involving the ia64_ctx.lock. The lock
may be taken in interrupt context to process an IPI from smp_flush_tlb_mm.
<[email protected]> (04/01/14 1.1267.35.12)
[PATCH] ia64: Avoid double clear of CMC/CPE records
Credit to Ben Woodard <[email protected]>.
<[email protected]> (04/01/14 1.1267.35.11)
[PATCH] ia64: enable recovery from TLB errors
Here's the updated version of the MCA TLB recovery patch.
<[email protected]> (04/01/14 1.1267.35.10)
[PATCH] ia64: fix deadlock in ia64_mca_cmc_int_caller()
smp_call_function() must not be called from interrupt context (can deadlock on tasklist_lock). Use keventd to call smp_call_function().
<[email protected]> (04/01/14 1.1267.35.9)
ia64: work around a menuconfig bug.
Re-order "HP" and "HP-simulator" to workaround menuconfig bug. If "HP-simulator" appears first, menuconfig selects it when the user selects "HP".
<[email protected]> (04/01/14 1.1267.35.8)
ia64 HP iommu: add "sx1000" detection (no functional change).
<[email protected]> (04/01/14 1.1267.35.7)
ia64: Fix PFM_WRITE_PMCS failure in system-wide mode when PMC12 is zero
- fixes a typo in pfm_write_pmcs() by which we were not using the correct index variable to check for the default value of a PMC. This caused calls to PFM_WRITE_PMCS to fail in system wide mode when PMC12 is programmed to be zero.
Thanks!
Bjorn