- 22 Aug, 2019 2 commits
-
-
Sam Bobroff authored
The pcibios_init() function for PowerPC 64 currently calls pci_bus_add_devices() before pcibios_resource_survey(). This means that at boot time, when the pcibios_bus_add_device() hooks are called by pci_bus_add_devices(), device resources have not been allocated and they are unable to perform EEH setup, so a separate pass is needed. This patch adjusts that order so that it will become possible to consolidate the EEH setup work into a single location. The only functional change is to execute pcibios_resource_survey() (excepting ppc_md.pcibios_fixup(), see below) before pci_bus_add_devices() instead of after it. Because pcibios_scan_phb() and pci_bus_add_devices() are called together in a loop, this must be broken into one loop for each call. Then the call to pcibios_resource_survey() is moved up in between them. This changes the ordering but because pcibios_resource_survey() also calls ppc_md.pcibios_fixup(), that call is extracted out into pcibios_init() to where pcibios_resource_survey() was, so that it is not moved. The only other caller of pcibios_resource_survey() is the PowerPC 32 version of pcibios_init(), and therefore, that is modified to call ppc_md.pcibios_fixup() right after pcibios_resource_survey() so that there is no functional change there at all. The re-arrangement will cause very few side-effects because at this stage in the boot, pci_bus_add_devices() does very little: - pci_create_sysfs_dev_files() does nothing (no sysfs yet) - pci_proc_attach_device() does nothing (no proc yet) - device_attach() does nothing (no drivers yet) This leaves only the pci_final_fixup calls, D3 support, and marking the device as added. Of those, only the pci_final_fixup calls have the potential to be affected by resource allocation. The only pci_final_fixup handlers that touch resources seem to be one for x86 (pci_amd_enable_64bit_bar()), and a PowerPC 32 platform driver (quirk_final_uli1575()), neither of which use this pcibios_init() function. Even if they did, it would almost certainly be a bug, under the current ordering, to rely on or make changes to resources before they were allocated. Signed-off-by:
Sam Bobroff <sbobroff@linux.ibm.com> Reviewed-by:
Alexey Kardashevskiy <aik@ozlabs.ru> Signed-off-by:
Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/4506b0489eabd0921a3587d90bd44c7683f3472d.1565930772.git.sbobroff@linux.ibm.com
-
Masahiro Yamada authored
The KBUILD_ARFLAGS addition in arch/powerpc/Makefile has never worked in a useful way because it is always overridden by the following code in the top Makefile: # use the deterministic mode of AR if available KBUILD_ARFLAGS := $(call ar-option,D) The code in the top Makefile was added in 2011, by commit 40df759e ("kbuild: Fix build with binutils <= 2.19"). The KBUILD_ARFLAGS addition for ppc has always been dead code from the beginning. Nobody has reported a problem since 43c9127d ("powerpc: Add option to use thin archives"), so this code was unneeded. Signed-off-by:
Masahiro Yamada <yamada.masahiro@socionext.com> Signed-off-by:
-
- 21 Aug, 2019 7 commits
-
-
Santosh Sivaraj authored
Use memcpy_mcsafe() implementation to define copy_to_user_mcsafe() Signed-off-by:
Santosh Sivaraj <santosh@fossix.org> Signed-off-by:
-
Balbir Singh authored
The pmem infrastructure uses memcpy_mcsafe in the pmem layer so as to convert machine check exceptions into a return value on failure in case a machine check exception is encountered during the memcpy. The return value is the number of bytes remaining to be copied. This patch largely borrows from the copyuser_power7 logic and does not add the VMX optimizations, largely to keep the patch simple. If needed those optimizations can be folded in. Signed-off-by:
Balbir Singh <bsingharora@gmail.com> [arbab@linux.ibm.com: Added symbol export] Co-developed-by:
-
Balbir Singh authored
If we take a UE on one of the instructions with a fixup entry, set nip to continue execution at the fixup entry. Stop processing the event further or print it. Co-developed-by:
Reza Arbab <arbab@linux.ibm.com> Signed-off-by:
Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Reviewed-by:
Nicholas Piggin <npiggin@gmail.com> Signed-off-by:
-
Santosh Sivaraj authored
Certain architecture specific operating modes (e.g., in powerpc machine check handler that is unable to access vmalloc memory), the search_exception_tables cannot be called because it also searches the module exception tables if entry is not found in the kernel exception table. Signed-off-by:
-
Reza Arbab authored
The function doesn't get used outside this file, so make it static. Signed-off-by:
-
Balbir Singh authored
The current code would fail on huge pages addresses, since the shift would be incorrect. Use the correct page shift value returned by __find_linux_pte() to get the correct physical address. The code is more generic and can handle both regular and compound pages. Fixes: ba41e1e1 ("powerpc/mce: Hookup derror (load/store) UE errors") Signed-off-by:
-
Santosh Sivaraj authored
schedule_work() cannot be called from MCE exception context as MCE can interrupt even in interrupt disabled context. Fixes: 733e4a4c ("powerpc/mce: hookup memory_failure for UE errors") Cc: stable@vger.kernel.org # v4.15+ Reviewed-by:
-
- 20 Aug, 2019 27 commits
-
-
Nathan Lynch authored
After a partition migration, pseries_devicetree_update() processes changes to the device tree communicated from the platform to Linux. This is a relatively heavyweight operation, with multiple device tree searches, memory allocations, and conversations with partition firmware. There's a few levels of nested loops which are bounded only by decisions made by the platform, outside of Linux's control, and indeed we have seen RCU stalls on large systems while executing this call graph. Use cond_resched() in these loops so that the cpu is yielded when needed. Signed-off-by:
Nathan Lynch <nathanl@linux.ibm.com> Signed-off-by:
-
Nathan Lynch authored
rtas_cpu_state_change_mask() potentially operates on scores of cpus, so explicitly allow rescheduling in the loop body. Signed-off-by:
Gautham R. Shenoy <ego@linux.vnet.ibm.com> Signed-off-by:
-
Nathan Lynch authored
The LPAR migration implementation and userspace-initiated cpu hotplug can interleave their executions like so: 1. Set cpu 7 offline via sysfs. 2. Begin a partition migration, whose implementation requires the OS to ensure all present cpus are online; cpu 7 is onlined: rtas_ibm_suspend_me -> rtas_online_cpus_mask -> cpu_up This sets cpu 7 online in all respects except for the cpu's corresponding struct device; dev->offline remains true. 3. Set cpu 7 online via sysfs. _cpu_up() determines that cpu 7 is already online and returns success. The driver core (device_online) sets dev->offline = false. 4. The migration completes and restores cpu 7 to offline state: rtas_ibm_suspend_me -> rtas_offline_cpus_mask -> cpu_down This leaves cpu7 in a state where the driver core considers the cpu device online, but in all other respects it is offline and unused. Attempts to online the cpu via sysfs appear to succeed but the driver core actually does not pass the request to the lower-level cpuhp support code. This makes the cpu unusable until the cpu device is manually set offline and then online again via sysfs. Instead of directly calling cpu_up/cpu_down, the migration code should use the higher-level device core APIs to maintain consistent state and serialize operations. Fixes: 120496ac ("powerpc: Bring all threads online prior to migration/hibernation") Signed-off-by: -
Christophe Leroy authored
If a page is already mapped RW without the DIRTY flag, the DIRTY flag is never set and a TLB store miss exception is taken forever. This is easily reproduced with the following app: void main(void) { volatile char *ptr = mmap(0, 4096, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); *ptr = *ptr; } When DIRTY flag is not set, bail out of TLB miss handler and take a minor page fault which will set the DIRTY flag. Fixes: f8b58c64 ("powerpc/603: let's handle PAGE_DIRTY directly") Cc: stable@vger.kernel.org # v5.1+ Reported-by:Doug Crawford <doug.crawford@intelight-its.com> Signed-off-by:
Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by:
-
Nicholas Piggin authored
pfn_pte is never given a pte above the addressable physical memory limit, so the masking is redundant. In case of a software bug, it is not obviously better to silently truncate the pfn than to corrupt the pte (either one will result in memory corruption or crashes), so there is no reason to add this to the fast path. Add VM_BUG_ON to catch cases where the pfn is invalid. These would catch the create_section_mapping bug fixed by a previous commit. [16885.256466] ------------[ cut here ]------------ [16885.256492] kernel BUG at arch/powerpc/include/asm/book3s/64/pgtable.h:612! cpu 0x0: Vector: 700 (Program Check) at [c0000000ee0a36d0] pc: c000000000080738: __map_kernel_page+0x248/0x6f0 lr: c000000000080ac0: __map_kernel_page+0x5d0/0x6f0 sp: c0000000ee0a3960 msr: 9000000000029033 current = 0xc0000000ec63b400 paca = 0xc0000000017f0000 irqmask: 0x03 irq_happened: 0x01 pid = 85, comm = sh kernel BUG at arch/powerpc/include/asm/book3s/64/pgtable.h:612! Linux version 5.3.0-rc1-00001-g0fe93e5f3394 enter ? for help [c0000000ee0a3a00] c000000000d37378 create_physical_mapping+0x260/0x360 [c0000000ee0a3b10] c000000000d370bc create_section_mapping+0x1c/0x3c [c0000000ee0a3b30] c000000000071f54 arch_add_memory+0x74/0x130 Signed-off-by:Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Signed-off-by:
-
Nicholas Piggin authored
Ensure __va is given a physical address below PAGE_OFFSET, and __pa is given a virtual address above PAGE_OFFSET. Signed-off-by:
-
Nicholas Piggin authored
The alloc_pages_node return value should be tested for failure before being passed to page_address. Tested-by:
Anju T Sudhakar <anju@linux.vnet.ibm.com> Signed-off-by:
-
Nicholas Piggin authored
create_physical_mapping expects physical addresses, but splitting these mapping on hot unplug is supplying virtual (effective) addresses. Fixes: 4dd5f8a9 ("powerpc/mm/radix: Split linear mapping on hot-unplug") Signed-off-by:
-
Nicholas Piggin authored
create_physical_mapping expects physical addresses, but creating and splitting these mappings after boot is supplying virtual (effective) addresses. This can be irritated by booting with mem= to limit memory then probing an unused physical memory range: echo <addr> > /sys/devices/system/memory/probe This mostly works by accident, firstly because __va(__va(x)) == __va(x) so the virtual address does not get corrupted. Secondly because pfn_pte masks out the upper bits of the pfn beyond the physical address limit, so a pfn constructed with a 0xc000000000000000 virtual linear address will be masked back to the correct physical address in the pte. Fixes: 6cc27341 ("powerpc/mm: add radix__create_section_mapping()") Signed-off-by:
-
Nicholas Piggin authored
current may be cached by the compiler, so remove the volatile asm restriction. This results in better generated code, as well as being smaller and fewer dependent loads, it can avoid store-hit-load flushes like this one that shows up in irq_exit(): preempt_count_sub(HARDIRQ_OFFSET); if (!in_interrupt() && ...) Which ends up as: ((struct thread_info *)current)->preempt_count -= HARDIRQ_OFFSET; if (((struct thread_info *)current)->preempt_count ... Evaluating current twice presently means it has to be loaded twice, and here gcc happens to pick a different register each time, then preempt_count is accessed via that base register: 1058: ld r10,2392(r13) <-- current 105c: lwz r9,0(r10) <-- preempt_count 1060: addis r9,r9,-1 1064: stw r9,0(r10) <-- preempt_count 1068: ld r9,2392(r13) <-- current 106c: lwz r9,0(r9) <-- preempt_count 1070: rlwinm. r9,r9,0,11,23 1074: bne 1090 <irq_exit+0x60> This can frustrate store-hit-load detection heuristics and cause flushes. Allowing the compiler to cache current in a reigster with this patch results in the same base register being used for all accesses, which is more likely to be detected as an alias: 1058: ld r31,2392(r13) ... 1070: lwz r9,0(r31) 1074: addis r9,r9,-1 1078: stw r9,0(r31) 107c: lwz r9,0(r31) 1080: rlwinm. r9,r9,0,11,23 1084: bne 10a0 <irq_exit+0x60> Signed-off-by: -
Christophe Leroy authored
copy_page() and clear_page() expect page aligned destination, and use dcbz instruction to clear entire cache lines based on the assumption that the destination is cache aligned. As shown during analysis of a bug in BTRFS filesystem, a misaligned copy_page() can create bugs that are difficult to locate (see Link). Add an explicit WARNING when copy_page() or clear_page() are called with misaligned destination. Signed-off-by:
-
Christophe Leroy authored
On powerpc 603, there is no hash table so get out of update_mmu_cache() early. Signed-off-by:
-
Christophe Leroy authored
On BOOK3S32, hash_preload() neither use is_exec nor trap, so drop those parameters and simplify update_mmu_cached(). Signed-off-by:
-
Christophe Leroy authored
update_mmu_cache() is only for BOOK3S, and can be simplified for BOOK3S32. Move it out of mem.c into respective BOOK3S32 and BOOK3S64 files containing hash utils. BOOK3S64 version of hash_preload() is only used locally, declare it static. Remove the radix_enabled() stuff in BOOK3S32 version. Signed-off-by:
-
Christophe Leroy authored
Move FSL_BOOK3E version of update_mmu_cache() at the same place as book3e_hugetlb_preload() as update_mmu_cache() is the only user of book3e_hugetlb_preload(). Signed-off-by:
-
Christophe Leroy authored
Only BOOK3S and FSL_BOOK3E have a usefull update_mmu_cache(). For the others, just define it static inline. In the meantime, simplify the FSL_BOOK3E related ifdef as book3e_hugetlb_preload() only exists when CONFIG_PPC_FSL_BOOK3E is selected. Signed-off-by:
-
Christophe Leroy authored
On the 8xx, the layout displayed at boot is: [ 0.000000] Memory: 121856K/131072K available (5728K kernel code, 592K rwdata, 1248K rodata, 560K init, 448K bss, 9216K reserved, 0K cma-reserved) [ 0.000000] Kernel virtual memory layout: [ 0.000000] * 0xffefc000..0xffffc000 : fixmap [ 0.000000] * 0xffefc000..0xffefc000 : early ioremap [ 0.000000] * 0xc9000000..0xffefc000 : vmalloc & ioremap [ 0.000000] SLUB: HWalign=16, Order=0-3, MinObjects=0, CPUs=1, Nodes=1 Remove display of an empty early ioremap. Signed-off-by:
-
Christophe Leroy authored
When KASAN is selected, the definitive hash table has to be set up later, but there is already an early temporary one. When KASAN is not selected, there is no early hash table, so the setup of the definitive hash table cannot be delayed. Fixes: 72f208c6 ("powerpc/32s: move hash code patching out of MMU_init_hw()") Cc: stable@vger.kernel.org # v5.2+ Reported-by:
Jonathan Neuschafer <j.neuschaefer@gmx.net> Tested-by:
-
Christophe Leroy authored
We see warnings such as: kernel/futex.c: In function 'do_futex': kernel/futex.c:1676:17: warning: 'oldval' may be used uninitialized in this function [-Wmaybe-uninitialized] return oldval == cmparg; ^ kernel/futex.c:1651:6: note: 'oldval' was declared here int oldval, ret; ^ This is because arch_futex_atomic_op_inuser() only sets *oval if ret is 0 and GCC doesn't see that it will only use it when ret is 0. Anyway, the non-zero ret path is an error path that won't suffer from setting *oval, and as *oval is a local var in futex_atomic_op_inuser() it will have no impact. Signed-off-by: -
Christophe Leroy authored
When loading modules, from time to time an Oops is encountered during the init of shadow area for globals. This is due to the last page not always being mapped depending on the exact distance between the start and the end of the shadow area and the alignment with the page addresses. Fix this by aligning the starting address with the page address. Fixes: 2edb16ef ("powerpc/32: Add KASAN support") Cc: stable@vger.kernel.org # v5.2+ Reported-by:
Erhard F. <erhard_f@mailbox.org> Signed-off-by:
-
Christophe Leroy authored
Parallel loading of modules may lead to bad setup of shadow page table entries. First, lets align modules so that two modules never share the same shadow page. Second, ensure that two modules cannot allocate two page tables for the same PMD entry at the same time. This is done by using init_mm.page_table_lock in the same way as __pte_alloc_kernel() Fixes: 2edb16ef ("powerpc/32: Add KASAN support") Cc: stable@vger.kernel.org # v5.2+ Signed-off-by:
-
Christophe Leroy authored
On 8xx, breakpoints stop after executing the instruction, so stepping/emulation is not needed. Move it into a sub-function and remove the #ifdefs. Signed-off-by:
Ravi Bangoria <ravi.bangoria@linux.ibm.com> Signed-off-by:
-
Christophe Leroy authored
hashpagetable.c is only compiled when CONFIG_PPC_BOOK3S_64 is defined, so drop the test and its 'else' branch. Use IS_ENABLED(CONFIG_PPC_PSERIES) instead of #ifdef, this allows the code to be checked at any build. It is still optimised out by GCC. Use IS_ENABLED(CONFIG_PPC_64K_PAGES) instead of #ifdef. Use IS_ENABLED(CONFIG_SPARSEMEN_VMEMMAP) instead of #ifdef. Signed-off-by:
-
Christophe Leroy authored
When CONFIG_PPC_DEBUG_WX, note_prot_wx() is useless. Get out of it early and inconditionnally in that case, so that GCC can kick all the code out. Signed-off-by:
-
Christophe Leroy authored
PPC32 doesn't have KERN_VIRT_START. Make PAGE_OFFSET the default starting address for the dump, and drop the dummy definition of KERN_VIRT_START. Only use KERN_VIRT_START for non radix PPC64. Signed-off-by:
-
Christophe Leroy authored
walk_pagetables() always walk the entire pgdir from address 0 but considers PAGE_OFFSET or KERN_VIRT_START as the starting address of the walk, resulting in a possible mismatch in the displayed addresses. Ex: on PPC32, when KERN_VIRT_START was locally defined as PAGE_OFFSET, ptdump displayed 0x80000000 instead of 0xc0000000 for the first kernel page, because 0xc0000000 + 0xc0000000 = 0x80000000 Start the walk at st->start_address instead of starting at 0. Signed-off-by:
-
Christophe Leroy authored
Commit 453d87f6 ("powerpc/mm: Warn if W+X pages found on boot") wrongly changed KERN_VIRT_START from 0 to PAGE_OFFSET, leading to a shift in the displayed addresses. Lets revert that change to resync walk_pagetables()'s addr val and pgd_t pointer for PPC32. Fixes: 453d87f6 ("powerpc/mm: Warn if W+X pages found on boot") Cc: stable@vger.kernel.org # v5.2+ Signed-off-by:
-
- 19 Aug, 2019 4 commits
-
-
Cédric Le Goater authored
Modify the xmon 'dxi' command to query all interrupts if no IRQ number is specified. Signed-off-by:
Cédric Le Goater <clg@kaod.org> Signed-off-by:
-
Cédric Le Goater authored
The xmon 'dxi' command calls OPAL to query the XIVE configuration of a interrupt. This can only be done on baremetal (PowerNV) and it will crash a pseries machine. Introduce a new XIVE get_irq_config() operation which implements a different query depending on the platform, PowerNV or pseries, and modify xmon to use a top level wrapper. Signed-off-by:
-
Cédric Le Goater authored
Currently, the xmon 'dx' command calls OPAL to dump the XIVE state in the OPAL logs and also outputs some of the fields of the internal XIVE structures in Linux. The OPAL calls can only be done on baremetal (PowerNV) and they crash a pseries machine. Fix by checking the hypervisor feature of the CPU. Signed-off-by:
-
Alexey Kardashevskiy authored
At the moment we create a small window only for 32bit devices, the window maps 0..2GB of the PCI space only. For other devices we either use a sketchy bypass or hardware bypass but the former can only work if the amount of RAM is no bigger than the device's DMA mask and the latter requires devices to support at least 59bit DMA. This extends the default DMA window to the maximum size possible to allow a wider DMA mask than just 32bit. The default window size is now limited by the the iommu_table::it_map allocation bitmap which is a contiguous array, 1 bit per an IOMMU page. This increases the default IOMMU page size from hard coded 4K to the system page size to allow wider DMA masks. This increases the level number to not exceed the max order allocation limit per TCE level. By the same time, this keeps minimal levels number as 2 in order to save memory. As the extended window now overlaps the 32bit MMIO region, this adds an area reservation to iommu_init_table(). After this change the default window size is 0x80000000000==1<<43 so devices limited to DMA mask smaller than the amount of system RAM can still use more than just 2GB of memory for DMA. This is an optimization and not a bug fix for DMA API usage. With the on-demand allocation of indirect TCE table levels enabled and 2 levels, the first TCE level size is just 1<<ceil((log2(0x7ffffffffff+1)-16)/2)=16384 TCEs or 2 system pages. Signed-off-by:
-
