aboutsummaryrefslogtreecommitdiff
path: root/arch/sparc/mm
AgeCommit message (Collapse)Author
2009-09-04Merge branch 'master' of /home/davem/src/GIT/linux-2.6/David S. Miller
2009-08-25sparc64: Validate linear D-TLB misses.David S. Miller
When page alloc debugging is not enabled, we essentially accept any virtual address for linear kernel TLB misses. But with kgdb, kernel address probing, and other facilities we can try to access arbitrary crap. So, make sure the address we miss on will translate to physical memory that actually exists. In order to make this work we have to embed the valid address bitmap into the kernel image. And in order to make that less expensive we make an adjustment, in that the max physical memory address is decreased to "1 << 41", even on the chips that support a 42-bit physical address space. We can do this because bit 41 indicates "I/O space" and thus covers non-memory ranges. The result of this is that: 1) kpte_linear_bitmap shrinks from 2K to 1K in size 2) we need 64K more for the valid address bitmap We can't let the valid address bitmap be dynamically allocated once we start using it to validate TLB misses, otherwise we have crazy issues to deal with wrt. recursive TLB misses and such. If we're in a TLB miss it could be the deepest trap level that's legal inside of the cpu. So if we TLB miss referencing the bitmap, the cpu will be out of trap levels and enter RED state. To guard against out-of-range accesses to the bitmap, we have to check to make sure no bits in the physical address above bit 40 are set. We could export and use last_valid_pfn for this check, but that's just an unnecessary extra memory reference. On the plus side of all this, since we load all of these translations into the special 4MB mapping TSB, and we check the TSB first for TLB misses, there should be absolutely no real cost for these new checks in the TLB miss path. Reported-by: heyongli@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-17sparc, leon: sparc-leon specific SRMMU initialization and bootup fixes.Konrad Eisele
The sparc-leon caches are virtually tagged so a flush is needed on ctx switch. Signed-off-by: Konrad Eisele <konrad@gaisler.com> Reviewed-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-17sparc,leon: Introduce the sparc-leon CPU type.Konrad Eisele
Add sparc_leon enum, M_LEON|M_LEON3_SOC machine. Add compilation of leon.c in mm and kernel if CONFIG_SPARC_LEON is defined. Add sparc_leon dependent initialization to switch statements + head.S. Signed-off-by: Konrad Eisele <konrad@gaisler.com> Reviewed-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-17sparc,leon: CONFIG_SPARC_LEON option and leon specific files.Konrad Eisele
The macro CONFIG_SPARC_LEON will shield, if undefined, the sun-sparc code from LEON specific code. In particular include/asm/leon.h will get empty through #ifdef and leon_kernel.c and leon_mm.c will not be compiled. Signed-off-by: Konrad Eisele <konrad@gaisler.com> Reviewed-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-02sparc: Use page_fault_out_of_memory() for VM_FAULT_OOM.David S. Miller
As noted by Nick Piggin. Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-21Move FAULT_FLAG_xyz into handle_mm_fault() callersLinus Torvalds
This allows the callers to now pass down the full set of FAULT_FLAG_xyz flags to handle_mm_fault(). All callers have been (mechanically) converted to the new calling convention, there's almost certainly room for architectures to clean up their code and then add FAULT_FLAG_RETRY when that support is added. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18sparc64: Fix UP bootup regression.David S. Miller
Commit b696fdc259f0d94348a9327bed352fac44d4883d ("sparc64: Defer cpu_data() setup until end of per-cpu data initialization.") broke bootup for UP builds because the cpu_data() initialization only occurs in setup_per_cpu_areas() which is never compiled in nor called in UP builds. Fix this up by calling the setups directly from init_64.c when non-SMP. Reported-by: Alexander Beregalov <a.beregalov@gmail.com> Tested-by: Alexander Beregalov <a.beregalov@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-16sparc: replace uses of CPU_MASK_ALL_PTRStephen Rothwell
CPU_MASK_ALL is the (deprecated) "all bits set" cpumask, defined as so: #define CPU_MASK_ALL (cpumask_t) { { ... } } Taking the address of such a temporary is questionable at best, unfortunately 321a8e9d (cpumask: add CPU_MASK_ALL_PTR macro) added CPU_MASK_ALL_PTR: #define CPU_MASK_ALL_PTR (&CPU_MASK_ALL) Which formalizes this practice. One day gcc could bite us over this usage (though we seem to have gotten away with it so far). [Description by Rusty Russell] Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-16sparc: Simplify code using is_power_of_2() routine.Robert P. J. Day
Signed-off-by: Robert P. J. Day <rpjday@crashcourse.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-16sparc64: Get rid of real_setup_per_cpu_areas().David S. Miller
Now that we defer the cpu_data() initializations to the end of per-cpu setup, we can get rid of this local hack we had to setup the per-cpu areas eary. This is a necessary step in order to support HAVE_DYNAMIC_PER_CPU_AREA since the per-cpu setup must run when page structs are available. Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-16sparc64: Defer cpu_data() setup until end of per-cpu data initialization.David S. Miller
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-16sparc64: Make mdesc_fill_in_cpu_data take a cpumask_t pointer.David S. Miller
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-16sparc: Call OF and MD cpu scanning explicitly from paging_init()David S. Miller
We need to split up the cpu present mask setup from the cpu_data initialization, and this is a first step towards that. Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-12module: trim exception table on init free.Rusty Russell
It's theoretically possible that there are exception table entries which point into the (freed) init text of modules. These could cause future problems if other modules get loaded into that memory and cause an exception as we'd see the wrong fixup. The only case I know of is kvm-intel.ko (when CONFIG_CC_OPTIMIZE_FOR_SIZE=n). Amerigo fixed this long-standing FIXME in the x86 version, but this patch is more general. This implements trim_init_extable(); most archs are simple since they use the standard lib/extable.c sort code. Alpha and IA64 use relative addresses in their fixups, so thier trimming is a slight variation. Sparc32 is unique; it doesn't seem to define ARCH_HAS_SORT_EXTABLE, yet it defines its own sort_extable() which overrides the one in lib. It doesn't sort, so we have to mark deleted entries instead of actually trimming them. Inspired-by: Amerigo Wang <amwang@redhat.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> Cc: linux-alpha@vger.kernel.org Cc: sparclinux@vger.kernel.org Cc: linux-ia64@vger.kernel.org
2009-04-08sparc64: add_node_ranges() must be __initDavid S. Miller
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-04-08sparc64: Fix section mismatch warnings in PCI controller drivers.David S. Miller
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-04-01mm: use debug_kmap_atomicAkinobu Mita
Use debug_kmap_atomic in kmap_atomic, kmap_atomic_pfn, and iomap_atomic_prot_pfn. Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-29Merge branch 'master' of ↵David S. Miller
ssh://master.kernel.org/home/ftp/pub/scm/linux/kernel/git/rusty/linux-2.6-cpumask-for-sparc Conflicts: arch/sparc/kernel/smp_64.c
2009-03-18sparc64: Reschedule KGDB capture to a software interrupt.David S. Miller
Otherwise it might interrupt switch_to() midstream and use half-cooked register window state. Reported-by: Chris Torek <chris.torek@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-16cpumask: prepare for iterators to only go to nr_cpu_ids/nr_cpumask_bits.: sparcRusty Russell
Impact: cleanup, futureproof In fact, all cpumask ops will only be valid (in general) for bit numbers < nr_cpu_ids. So use that instead of NR_CPUS in various places. This is always safe: no cpu number can be >= nr_cpu_ids, and nr_cpu_ids is initialized to NR_CPUS at boot. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Mike Travis <travis@sgi.com> Acked-by: Ingo Molnar <mingo@elte.hu>
2009-03-16cpumask: prepare for iterators to only go to nr_cpu_ids/nr_cpumask_bits.: ↵Rusty Russell
sparc64 Impact: cleanup, futureproof In fact, all cpumask ops will only be valid (in general) for bit numbers < nr_cpu_ids. So use that instead of NR_CPUS in various places. This is always safe: no cpu number can be >= nr_cpu_ids, and nr_cpu_ids is initialized to NR_CPUS at boot. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Mike Travis <travis@sgi.com> Acked-by: Ingo Molnar <mingo@elte.hu>
2009-02-03sparc64: Kill bogus TPC/address truncation during 32-bit faults.David S. Miller
This builds upon eeabac7386ca13bfe1a58afeb04326a9e1a3a20e ("sparc64: Validate kernel generated fault addresses on sparc64.") Upon further consideration, we actually should never see any fault addresses for 32-bit tasks with the upper 32-bits set. If it does every happen, by definition it's a bug. Whatever context created that fault would only have that fault satisfied if we used the full 64-bit address. If we truncate it, we'll always fault the wrong address and we'll always loop faulting forever. So catch such conditions and mark them as errors always. Log the error and fail the fault. Signed-off-by: David S. Miller <davem@davemloft.net>
2009-02-02sparc64: Validate kernel generated fault addresses on sparc64.David S. Miller
In order to handle all of the cases of address calculation overflow properly, we run sparc 32-bit processes in "address masking" mode when running on a 64-bit kernel. Address masking mode zeros out the top 32-bits of the address calculated for every load and store instruction. However, when we're in privileged mode we have to run with that address masking mode disabled even when accessing userspace from the kernel. To "simulate" the address masking mode we clear the top-bits by hand for 32-bit processes in the fault handler. It is the responsibility of code in the compat layer to properly zero extend addresses used to access userspace. If this isn't followed properly we can get into a fault loop. Say that the user address is 0xf0000000 but for whatever reason the kernel code sign extends this to 64-bit, and then the kernel tries to access the result. In such a case we'll fault on address 0xfffffffff0000000 but the fault handler will process that fault as if it were to address 0xf0000000. We'll loop faulting forever because the fault never gets satisfied. So add a check specifically for this case, when the kernel is faulting on a user address access and the addresses don't match up. This code path is sufficiently slow path, and this bug is sufficiently painful to diagnose, that this kind of bug check is warranted. Signed-off-by: David S. Miller <davem@davemloft.net>
2009-01-08sparc64: move EXPORT_SYMBOL to the symbols definitionSam Ravnborg
Move all applicable EXPORT_SYMBOL()s to the file where the respective symbol is defined. Removed all the includes that are no longer needed in sparc_ksyms_64.c Comment all remaining EXPORT_SYMBOL()s in sparc_ksyms_64.c Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Additions by Julian Calaby: * Moved EXPORT_SYMBOL()s for prom functions to their rightful places. * Made some minor cleanups to the includes and comments of sparc_ksyms_64.c * Updated and tidied commit message. * Rebased patch over sparc-2.6.git HEAD. * Ensured that all modified files have the correct includes. Signed-off-by: Julian Calaby <julian.calaby@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-01-08sparc: move EXPORT_SYMBOL to the symbols definitionSam Ravnborg
Move all applicable EXPORT_SYMBOL()s to the file where the respective symbol is defined. Removed all the includes that are no longer needed in sparc_ksyms_32.c Comment all remaining EXPORT_SYMBOL()s in sparc_ksyms_32.c Two symbols are shared with sparc64 thus the exports were removed from the sparc_ksyms_64.c too, along with the include their ommission made redundant. Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Additions by Julian Calaby: * Moved EXPORT_SYMBOL()s for prom functions to their rightful places. * Made some minor cleanups to the includes and comments of sparc_ksyms_32.c * Made another subtraction from sparc_ksyms_64.c * Updated and tidied commit message. * Rebased patch over sparc-2.6.git HEAD. * Ensured that all modified files have the correct includes. Signed-off-by: Julian Calaby <julian.calaby@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-01-06sparc64: Use unsigned long long for u64.Sam Ravnborg
Andrew Morton wrote: People keep on doing printk("%llu", some_u64); testing it only on x86_64 and this generates a warning storm on powerpc, sparc64, etc. Because they use `long', not `long long'. Quite a few 64-bit architectures are using `long' for their s64/u64 types. We should convert them all to `long long'. Update types.h so we use unsigned long long for u64 and fix all warnings in sparc64 code. Tested with an allnoconfig, defconfig and allmodconfig builds. This patch introduces additional warnings in several drivers. These will be dealt with in separate patches. Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-01-06sparc: refactor code in fault_32.cSam Ravnborg
The sparc allmodconfig build broke due to enabling of the branch_tracer that does some very clever things with all if conditions. This caused my gcc 3.4.5 to be so confused that it emitted a warning: arch/sparc/mm/fault_32.c: In function `do_sparc_fault': arch/sparc/mm/fault_32.c:176: warning: 'fixup' might be used uninitialized in this function And with -Werror this broke the build. Refactor code so it: 1) becomes more readable 2) no longer emit a warning with the branch_tracer enabled Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-01-06sparc64: refactor code in init_64.cSam Ravnborg
The sparc64 allmodconfig build broke due to enabling of the branch_tracer that does some very clever things with all if conditions. This caused my gcc 3.4.5 to be so confused that it emitted two warnings: arch/sparc/mm/init_64.c: In function `update_mmu_cache': arch/sparc/mm/init_64.c:271: warning: 'pg_flags' might be used uninitialized in this function arch/sparc/mm/init_64.c:272: warning: 'page' might be used uninitialized in this function And with -Werror this broke the build. Refactor code so it: 1) becomes more readable 2) no longer emit a warning with the branch_tracer enabled The refactoring uses a small helper function (flush_dcache()). Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-27sparc: drop SUN_IOSam Ravnborg
SUN_IO is always 'y' so drop it and thus killing an ifdef/endif pair Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-27sparc: unify sections.hSam Ravnborg
While doing this use standard names for start/end so we could use definitions straight from asm-generic for all the typical symbols. This also allowed us to drop the use of PROVIDE in the linker script so sprc is less non-standard on this area. Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-11sparc: use sparc64 version of scatterlist.hRobert Reif
Use sparc64 version of scatterlist.h. There are three main differences: dma_addr_t replaces __u32 dma_address replaces dvma_address dma_length replaces dvma_length dma_addr_t is a u32 on sparc32. Boot tested on sparc32. Signed-off-by: Robert Reif <reif@earthlink.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-04sparc: drop CONFIG_SUN_AUXIOSam Ravnborg
It is always equals y so no need to test for it Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-04sparc32: Don't btfixup cache flush ops for viking multiple times.David S. Miller
Just do it once. Pointed out by Al Viro. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-04sparc64: Make %pil level 15 a pseudo-NMI.David S. Miller
So that we can profile code even in a local_irq_disable() section, only write 14 (instead of 15) into the %pil register to disable IRQs. This allows PIL level 15 to serve as a pseudo NMI. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-04sparc64: Add tsb-ratio sysctl.David S. Miller
Add a sysctl to tweak the RSS limit used to decide when to grow the TSB for an address space. In order to avoid expensive divides and multiplies only simply positive and negative powers of two are supported. The function computed takes the number of TSB translations that will fit at one time in the TSB of a given size, and either adds or subtracts a percentage of entries. This final value is the RSS limit. See tsb_size_to_rss_limit(). Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-04sparc,sparc64: unify mm/Sam Ravnborg
- move all sparc64/mm/ files to arch/sparc/mm/ - commonly named files are named _64.c - add files to sparc/mm/Makefile preserving link order - delete now unused sparc64/mm/Makefile - sparc64 now finds mm/ in sparc Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-04sparc: prepare mm/ for unificationSam Ravnborg
- rename files where sparc64 has similar files to _32.c - Restructure Makefile - Sneak in -Werror as we have for sparc64 Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-30sparc32 cpuinit flase positivesAl Viro
All noise since we don't have CPU hotplug there. However, they did expose something very odd-looking in there - poke_viking() does a bunch of identical btfixup each time it's called (i.e. for each CPU). That one is left alone for now; just the trivial misannotation fixes. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-03sparc32: add init memory poisoningRobert Reif
This patch adds init memory poisoning. It looks like totalram_pages was not updated properly in free_initrd_mem so I fixed that as well. Signed-off-by: Robert Reif <reif@earthlink.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-02sparc32: Fix sun4c build warnings.David S. Miller
Reported by Stephen Rothwell. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-31sparc: remove CONFIG_SUN4Adrian Bunk
While doing some easy cleanups on the sparc code I noticed that the CONFIG_SUN4 code seems to be worse than the rest - there were some "I don't know how it should work, but the current code definitely cannot work." places. And while I have seen people running Linux on machines like a SPARCstation 5 a few years ago I don't recall having seen sun4 machines, even less ones running Linux. Signed-off-by: Adrian Bunk <bunk@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-29sparc: Kill now spurious includes of sbus.hDavid S. Miller
In order to make this week I also had to add an include of linux/dma-mapping.h to asm/pci_32.h because drivers/pci/pci.c really depends upon getting this header somehow. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-29sparc32: Kill iounit_map_dma_*().David S. Miller
Unused. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-29sparc: Remove generic SBUS probing layer.David S. Miller
The individual SBUS IOMMU arch code now sets the IOMMU information directly into the OF device objects. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-29sparc32: Make mmu_map_dma_area and mmu_unmap_dma_area take a device pointer.David S. Miller
This lets us kill this "map it in every IOMMU" crazy code, and also some of the final references to sbus_root. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-29sparc32: Kill mmu_translate_dvma and implementations.David S. Miller
No longer used. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-29sparc32: Make mmu_{get,release}_*() take a struct device pointer.David S. Miller
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-29sparc32: Make IOMMU and IO-UNIT init work with device nodes.David S. Miller
And stick the iommu archdata pointer into the generic OF device tree of_device struct as well. We still have to pass the sbus_bus object down into the routines so that the SBUS bus objects get the iommu cookies set properly. After drivers get converted to being pure OF drivers, that can go away. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-24mm: drop unneeded pgdat argument from free_area_init_node()Johannes Weiner
free_area_init_node() gets passed in the node id as well as the node descriptor. This is redundant as the function can trivially get the node descriptor itself by means of NODE_DATA() and the node's id. I checked all the users and NODE_DATA() seems to be usable everywhere from where this function is called. Signed-off-by: Johannes Weiner <hannes@saeurebad.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>