From 8ded03ae48b3657e0fbca99d8a9d8fa1bfb8c9be Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Fri, 2 Feb 2024 18:26:46 -0600 Subject: [PATCH 01/14] powerpc/pseries/papr-sysparm: use u8 arrays for payloads Some PAPR system parameter values are formatted by firmware as nul-terminated strings (e.g. LPAR name, shared processor attributes). But the values returned for other parameters, such as processor module info and TLB block invalidate characteristics, are binary data with parameter-specific layouts. So char[] isn't the appropriate type for the general case. Use u8/__u8. Signed-off-by: Nathan Lynch Fixes: 905b9e48786e ("powerpc/pseries/papr-sysparm: Expose character device to user space") Signed-off-by: Michael Ellerman Link: https://msgid.link/20240202-papr-sysparm-ioblock-data-use-u8-v1-1-f5c6c89f65ec@linux.ibm.com --- arch/powerpc/include/asm/papr-sysparm.h | 2 +- arch/powerpc/include/uapi/asm/papr-sysparm.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/papr-sysparm.h b/arch/powerpc/include/asm/papr-sysparm.h index 0dbbff59101d..c3cd5b131033 100644 --- a/arch/powerpc/include/asm/papr-sysparm.h +++ b/arch/powerpc/include/asm/papr-sysparm.h @@ -32,7 +32,7 @@ typedef struct { */ struct papr_sysparm_buf { __be16 len; - char val[PAPR_SYSPARM_MAX_OUTPUT]; + u8 val[PAPR_SYSPARM_MAX_OUTPUT]; }; struct papr_sysparm_buf *papr_sysparm_buf_alloc(void); diff --git a/arch/powerpc/include/uapi/asm/papr-sysparm.h b/arch/powerpc/include/uapi/asm/papr-sysparm.h index 9f9a0f267ea5..f733467b1534 100644 --- a/arch/powerpc/include/uapi/asm/papr-sysparm.h +++ b/arch/powerpc/include/uapi/asm/papr-sysparm.h @@ -14,7 +14,7 @@ enum { struct papr_sysparm_io_block { __u32 parameter; __u16 length; - char data[PAPR_SYSPARM_MAX_OUTPUT]; + __u8 data[PAPR_SYSPARM_MAX_OUTPUT]; }; /** From ed8b94f6e0acd652ce69bd69d678a0c769172df8 Mon Sep 17 00:00:00 2001 From: Gaurav Batra Date: Mon, 22 Jan 2024 16:24:07 -0600 Subject: [PATCH 02/14] powerpc/pseries/iommu: Fix iommu initialisation during DLPAR add When a PCI device is dynamically added, the kernel oopses with a NULL pointer dereference: BUG: Kernel NULL pointer dereference on read at 0x00000030 Faulting instruction address: 0xc0000000006bbe5c Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA pSeries Modules linked in: rpadlpar_io rpaphp rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs xsk_diag bonding nft_compat nf_tables nfnetlink rfkill binfmt_misc dm_multipath rpcrdma sunrpc rdma_ucm ib_srpt ib_isert iscsi_target_mod target_core_mod ib_umad ib_iser libiscsi scsi_transport_iscsi ib_ipoib rdma_cm iw_cm ib_cm mlx5_ib ib_uverbs ib_core pseries_rng drm drm_panel_orientation_quirks xfs libcrc32c mlx5_core mlxfw sd_mod t10_pi sg tls ibmvscsi ibmveth scsi_transport_srp vmx_crypto pseries_wdt psample dm_mirror dm_region_hash dm_log dm_mod fuse CPU: 17 PID: 2685 Comm: drmgr Not tainted 6.7.0-203405+ #66 Hardware name: IBM,9080-HEX POWER10 (raw) 0x800200 0xf000006 of:IBM,FW1060.00 (NH1060_008) hv:phyp pSeries NIP: c0000000006bbe5c LR: c000000000a13e68 CTR: c0000000000579f8 REGS: c00000009924f240 TRAP: 0300 Not tainted (6.7.0-203405+) MSR: 8000000000009033 CR: 24002220 XER: 20040006 CFAR: c000000000a13e64 DAR: 0000000000000030 DSISR: 40000000 IRQMASK: 0 ... NIP sysfs_add_link_to_group+0x34/0x94 LR iommu_device_link+0x5c/0x118 Call Trace: iommu_init_device+0x26c/0x318 (unreliable) iommu_device_link+0x5c/0x118 iommu_init_device+0xa8/0x318 iommu_probe_device+0xc0/0x134 iommu_bus_notifier+0x44/0x104 notifier_call_chain+0xb8/0x19c blocking_notifier_call_chain+0x64/0x98 bus_notify+0x50/0x7c device_add+0x640/0x918 pci_device_add+0x23c/0x298 of_create_pci_dev+0x400/0x884 of_scan_pci_dev+0x124/0x1b0 __of_scan_bus+0x78/0x18c pcibios_scan_phb+0x2a4/0x3b0 init_phb_dynamic+0xb8/0x110 dlpar_add_slot+0x170/0x3b8 [rpadlpar_io] add_slot_store.part.0+0xb4/0x130 [rpadlpar_io] kobj_attr_store+0x2c/0x48 sysfs_kf_write+0x64/0x78 kernfs_fop_write_iter+0x1b0/0x290 vfs_write+0x350/0x4a0 ksys_write+0x84/0x140 system_call_exception+0x124/0x330 system_call_vectored_common+0x15c/0x2ec Commit a940904443e4 ("powerpc/iommu: Add iommu_ops to report capabilities and allow blocking domains") broke DLPAR add of PCI devices. The above added iommu_device structure to pci_controller. During system boot, PCI devices are discovered and this newly added iommu_device structure is initialized by a call to iommu_device_register(). During DLPAR add of a PCI device, a new pci_controller structure is allocated but there are no calls made to iommu_device_register() interface. Fix is to register the iommu device during DLPAR add as well. Fixes: a940904443e4 ("powerpc/iommu: Add iommu_ops to report capabilities and allow blocking domains") Signed-off-by: Gaurav Batra [mpe: Trim oops and tweak some change log wording] Signed-off-by: Michael Ellerman Link: https://msgid.link/20240122222407.39603-1-gbatra@linux.ibm.com --- arch/powerpc/include/asm/ppc-pci.h | 3 +++ arch/powerpc/kernel/iommu.c | 21 ++++++++++++++++----- arch/powerpc/platforms/pseries/pci_dlpar.c | 4 ++++ 3 files changed, 23 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index ce2b1b5eebdd..c3a3f3df36d1 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -29,6 +29,9 @@ void *pci_traverse_device_nodes(struct device_node *start, void *(*fn)(struct device_node *, void *), void *data); extern void pci_devs_phb_init_dynamic(struct pci_controller *phb); +extern void ppc_iommu_register_device(struct pci_controller *phb); +extern void ppc_iommu_unregister_device(struct pci_controller *phb); + /* From rtas_pci.h */ extern void init_pci_config_tokens (void); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index ebe259bdd462..c6f62e130d55 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1388,6 +1388,21 @@ static const struct attribute_group *spapr_tce_iommu_groups[] = { NULL, }; +void ppc_iommu_register_device(struct pci_controller *phb) +{ + iommu_device_sysfs_add(&phb->iommu, phb->parent, + spapr_tce_iommu_groups, "iommu-phb%04x", + phb->global_number); + iommu_device_register(&phb->iommu, &spapr_tce_iommu_ops, + phb->parent); +} + +void ppc_iommu_unregister_device(struct pci_controller *phb) +{ + iommu_device_unregister(&phb->iommu); + iommu_device_sysfs_remove(&phb->iommu); +} + /* * This registers IOMMU devices of PHBs. This needs to happen * after core_initcall(iommu_init) + postcore_initcall(pci_driver_init) and @@ -1398,11 +1413,7 @@ static int __init spapr_tce_setup_phb_iommus_initcall(void) struct pci_controller *hose; list_for_each_entry(hose, &hose_list, list_node) { - iommu_device_sysfs_add(&hose->iommu, hose->parent, - spapr_tce_iommu_groups, "iommu-phb%04x", - hose->global_number); - iommu_device_register(&hose->iommu, &spapr_tce_iommu_ops, - hose->parent); + ppc_iommu_register_device(hose); } return 0; } diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 4ba824568119..4448386268d9 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -35,6 +35,8 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn) pseries_msi_allocate_domains(phb); + ppc_iommu_register_device(phb); + /* Create EEH devices for the PHB */ eeh_phb_pe_create(phb); @@ -76,6 +78,8 @@ int remove_phb_dynamic(struct pci_controller *phb) } } + ppc_iommu_unregister_device(phb); + pseries_msi_free_domains(phb); /* Keep a reference so phb isn't freed yet */ From aad98efd0b121f63a2e1c221dcb4d4850128c697 Mon Sep 17 00:00:00 2001 From: Naveen N Rao Date: Fri, 2 Feb 2024 21:13:16 +0530 Subject: [PATCH 03/14] powerpc/64: Set task pt_regs->link to the LR value on scv entry Nysal reported that userspace backtraces are missing in offcputime bcc tool. As an example: $ sudo ./bcc/tools/offcputime.py -uU Tracing off-CPU time (us) of user threads by user stack... Hit Ctrl-C to end. ^C write - python (9107) 8 write - sudo (9105) 9 mmap - python (9107) 16 clock_nanosleep - multipathd (697) 3001604 The offcputime bcc tool attaches a bpf program to a kprobe on finish_task_switch(), which is usually hit on a syscall from userspace. With the switch to system call vectored, we started setting pt_regs->link to zero. This is because system call vectored behaves like a function call with LR pointing to the system call return address, and with no modification to SRR0/SRR1. The LR value does indicate our next instruction, so it is being saved as pt_regs->nip, and pt_regs->link is being set to zero. This is not a problem by itself, but BPF uses perf callchain infrastructure for capturing stack traces, and that stores LR as the second entry in the stack trace. perf has code to cope with the second entry being zero, and skips over it. However, generic userspace unwinders assume that a zero entry indicates end of the stack trace, resulting in a truncated userspace stack trace. Rather than fixing all userspace unwinders to ignore/skip past the second entry, store the real LR value in pt_regs->link so that there continues to be a valid, though duplicate entry in the stack trace. With this change: $ sudo ./bcc/tools/offcputime.py -uU Tracing off-CPU time (us) of user threads by user stack... Hit Ctrl-C to end. ^C write write [unknown] [unknown] [unknown] [unknown] [unknown] PyObject_VectorcallMethod [unknown] [unknown] PyObject_CallOneArg PyFile_WriteObject PyFile_WriteString [unknown] [unknown] PyObject_Vectorcall _PyEval_EvalFrameDefault PyEval_EvalCode [unknown] [unknown] [unknown] _PyRun_SimpleFileObject _PyRun_AnyFileObject Py_RunMain [unknown] Py_BytesMain [unknown] __libc_start_main - python (1293) 7 write write [unknown] sudo_ev_loop_v1 sudo_ev_dispatch_v1 [unknown] [unknown] [unknown] [unknown] __libc_start_main - sudo (1291) 7 syscall syscall bpf_open_perf_buffer_opts [unknown] [unknown] [unknown] [unknown] _PyObject_MakeTpCall PyObject_Vectorcall _PyEval_EvalFrameDefault PyEval_EvalCode [unknown] [unknown] [unknown] _PyRun_SimpleFileObject _PyRun_AnyFileObject Py_RunMain [unknown] Py_BytesMain [unknown] __libc_start_main - python (1293) 11 clock_nanosleep clock_nanosleep nanosleep sleep [unknown] [unknown] __clone - multipathd (698) 3001661 Fixes: 7fa95f9adaee ("powerpc/64s: system call support for scv/rfscv instructions") Cc: stable@vger.kernel.org Reported-by: "Nysal Jan K.A" Signed-off-by: Naveen N Rao Signed-off-by: Michael Ellerman Link: https://msgid.link/20240202154316.395276-1-naveen@kernel.org --- arch/powerpc/kernel/interrupt_64.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index bd863702d812..1ad059a9e2fe 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -52,7 +52,8 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) mr r10,r1 ld r1,PACAKSAVE(r13) std r10,0(r1) - std r11,_NIP(r1) + std r11,_LINK(r1) + std r11,_NIP(r1) /* Saved LR is also the next instruction */ std r12,_MSR(r1) std r0,GPR0(r1) std r10,GPR1(r1) @@ -70,7 +71,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) std r9,GPR13(r1) SAVE_NVGPRS(r1) std r11,_XER(r1) - std r11,_LINK(r1) std r11,_CTR(r1) li r11,\trapnr From f09696279b5dd1770a3de2e062f1c5d1449213ff Mon Sep 17 00:00:00 2001 From: R Nageswara Sastry Date: Wed, 31 Jan 2024 18:38:59 +0530 Subject: [PATCH 04/14] selftests/powerpc/papr_vpd: Check devfd before get_system_loc_code() Calling get_system_loc_code before checking devfd and errno fails the test when the device is not available, the expected behaviour is a SKIP. Change the order of 'SKIP_IF_MSG' to correctly SKIP when the /dev/ papr-vpd device is not available. Test output before: Test FAILED on line 271 Test output after: [SKIP] Test skipped on line 266: /dev/papr-vpd not present Signed-off-by: R Nageswara Sastry Signed-off-by: Michael Ellerman Link: https://msgid.link/20240131130859.14968-1-rnsastry@linux.ibm.com --- tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c index 98cbb9109ee6..505294da1b9f 100644 --- a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c +++ b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c @@ -263,10 +263,10 @@ static int papr_vpd_system_loc_code(void) off_t size; int fd; - SKIP_IF_MSG(get_system_loc_code(&lc), - "Cannot determine system location code"); SKIP_IF_MSG(devfd < 0 && errno == ENOENT, DEVPATH " not present"); + SKIP_IF_MSG(get_system_loc_code(&lc), + "Cannot determine system location code"); FAIL_IF(devfd < 0); From a038a3ff8c6582404834852c043dadc73a5b68b4 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Wed, 24 Jan 2024 11:38:38 +0100 Subject: [PATCH 05/14] powerpc/6xx: set High BAT Enable flag on G2_LE cores MMU_FTR_USE_HIGH_BATS is set for G2_LE cores and derivatives like e300cX, but the high BATs need to be enabled in HID2 to work. Add register definitions and add the needed setup to __setup_cpu_603. This fixes boot on CPUs like the MPC5200B with STRICT_KERNEL_RWX enabled on systems where the flag has not been set by the bootloader already. Fixes: e4d6654ebe6e ("powerpc/mm/32s: rework mmu_mapin_ram()") Signed-off-by: Matthias Schiffer Reviewed-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/20240124103838.43675-1-matthias.schiffer@ew.tq-group.com --- arch/powerpc/include/asm/reg.h | 2 ++ arch/powerpc/kernel/cpu_setup_6xx.S | 20 +++++++++++++++++++- 2 files changed, 21 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 7fd09f25452d..bb47af9054a9 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -617,6 +617,8 @@ #endif #define SPRN_HID2 0x3F8 /* Hardware Implementation Register 2 */ #define SPRN_HID2_GEKKO 0x398 /* Gekko HID2 Register */ +#define SPRN_HID2_G2_LE 0x3F3 /* G2_LE HID2 Register */ +#define HID2_G2_LE_HBE (1<<18) /* High BAT Enable (G2_LE) */ #define SPRN_IABR 0x3F2 /* Instruction Address Breakpoint Register */ #define SPRN_IABR2 0x3FA /* 83xx */ #define SPRN_IBCR 0x135 /* 83xx Insn Breakpoint Control Reg */ diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S index f29ce3dd6140..bfd3f442e5eb 100644 --- a/arch/powerpc/kernel/cpu_setup_6xx.S +++ b/arch/powerpc/kernel/cpu_setup_6xx.S @@ -26,6 +26,15 @@ BEGIN_FTR_SECTION bl __init_fpu_registers END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE) bl setup_common_caches + + /* + * This assumes that all cores using __setup_cpu_603 with + * MMU_FTR_USE_HIGH_BATS are G2_LE compatible + */ +BEGIN_MMU_FTR_SECTION + bl setup_g2_le_hid2 +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) + mtlr r5 blr _GLOBAL(__setup_cpu_604) @@ -115,6 +124,16 @@ SYM_FUNC_START_LOCAL(setup_604_hid0) blr SYM_FUNC_END(setup_604_hid0) +/* Enable high BATs for G2_LE and derivatives like e300cX */ +SYM_FUNC_START_LOCAL(setup_g2_le_hid2) + mfspr r11,SPRN_HID2_G2_LE + oris r11,r11,HID2_G2_LE_HBE@h + mtspr SPRN_HID2_G2_LE,r11 + sync + isync + blr +SYM_FUNC_END(setup_g2_le_hid2) + /* 7400 <= rev 2.7 and 7410 rev = 1.0 suffer from some * erratas we work around here. * Moto MPC710CE.pdf describes them, those are errata @@ -495,4 +514,3 @@ _GLOBAL(__restore_cpu_setup) mtcr r7 blr _ASM_NOKPROBE_SYMBOL(__restore_cpu_setup) - From 4a7aee96200ad281a5cc4cf5c7a2e2a49d2b97b0 Mon Sep 17 00:00:00 2001 From: Jiangfeng Xiao Date: Tue, 23 Jan 2024 09:45:59 +0800 Subject: [PATCH 06/14] powerpc/kasan: Fix addr error caused by page alignment In kasan_init_region, when k_start is not page aligned, at the begin of for loop, k_cur = k_start & PAGE_MASK is less than k_start, and then `va = block + k_cur - k_start` is less than block, the addr va is invalid, because the memory address space from va to block is not alloced by memblock_alloc, which will not be reserved by memblock_reserve later, it will be used by other places. As a result, memory overwriting occurs. for example: int __init __weak kasan_init_region(void *start, size_t size) { [...] /* if say block(dcd97000) k_start(feef7400) k_end(feeff3fe) */ block = memblock_alloc(k_end - k_start, PAGE_SIZE); [...] for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) { /* at the begin of for loop * block(dcd97000) va(dcd96c00) k_cur(feef7000) k_start(feef7400) * va(dcd96c00) is less than block(dcd97000), va is invalid */ void *va = block + k_cur - k_start; [...] } [...] } Therefore, page alignment is performed on k_start before memblock_alloc() to ensure the validity of the VA address. Fixes: 663c0c9496a6 ("powerpc/kasan: Fix shadow area set up for modules.") Signed-off-by: Jiangfeng Xiao Signed-off-by: Michael Ellerman Link: https://msgid.link/1705974359-43790-1-git-send-email-xiaojiangfeng@huawei.com --- arch/powerpc/mm/kasan/init_32.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/mm/kasan/init_32.c b/arch/powerpc/mm/kasan/init_32.c index a70828a6d935..aa9aa11927b2 100644 --- a/arch/powerpc/mm/kasan/init_32.c +++ b/arch/powerpc/mm/kasan/init_32.c @@ -64,6 +64,7 @@ int __init __weak kasan_init_region(void *start, size_t size) if (ret) return ret; + k_start = k_start & PAGE_MASK; block = memblock_alloc(k_end - k_start, PAGE_SIZE); if (!block) return -ENOMEM; From 5c84bc8b617bf90e722cc57d447abd9a468d3a52 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 23 Jan 2024 13:51:41 +0100 Subject: [PATCH 07/14] powerpc: udbg_memcons: mark functions static ppc64_book3e_allmodconfig has one more driver that triggeres a few missing-prototypes warnings: arch/powerpc/sysdev/udbg_memcons.c:44:6: error: no previous prototype for 'memcons_putc' [-Werror=missing-prototypes] arch/powerpc/sysdev/udbg_memcons.c:57:5: error: no previous prototype for 'memcons_getc_poll' [-Werror=missing-prototypes] arch/powerpc/sysdev/udbg_memcons.c:80:5: error: no previous prototype for 'memcons_getc' [-Werror=missing-prototypes] Mark all these function static as there are no other users. Signed-off-by: Arnd Bergmann Signed-off-by: Michael Ellerman Link: https://msgid.link/20240123125148.2004648-1-arnd@kernel.org --- arch/powerpc/sysdev/udbg_memcons.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/sysdev/udbg_memcons.c b/arch/powerpc/sysdev/udbg_memcons.c index 5020044400dc..4de57ba52236 100644 --- a/arch/powerpc/sysdev/udbg_memcons.c +++ b/arch/powerpc/sysdev/udbg_memcons.c @@ -41,7 +41,7 @@ struct memcons memcons = { .input_end = &memcons_input[CONFIG_PPC_MEMCONS_INPUT_SIZE], }; -void memcons_putc(char c) +static void memcons_putc(char c) { char *new_output_pos; @@ -54,7 +54,7 @@ void memcons_putc(char c) memcons.output_pos = new_output_pos; } -int memcons_getc_poll(void) +static int memcons_getc_poll(void) { char c; char *new_input_pos; @@ -77,7 +77,7 @@ int memcons_getc_poll(void) return -1; } -int memcons_getc(void) +static int memcons_getc(void) { int c; From 1c57b9f63ab34f01b8c73731cc0efacb5a9a2f16 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 23 Jan 2024 13:51:42 +0100 Subject: [PATCH 08/14] powerpc: 85xx: mark local functions static These functions are either used in only one file and can just be made static or need an #include statement to avoid a warning: arch/powerpc/platforms/85xx/mpc8536_ds.c:30:13: error: no previous prototype for 'mpc8536_ds_pic_init' [-Werror=missing-prototypes] arch/powerpc/platforms/85xx/p1010rdb.c:27:13: error: no previous prototype for 'p1010_rdb_pic_init' [-Werror=missing-prototypes] arch/powerpc/platforms/85xx/p1022_ds.c:373:6: error: no previous prototype for 'p1022ds_set_pixel_clock' [-Werror=missing-prototypes] arch/powerpc/platforms/85xx/p1022_ds.c:422:1: error: no previous prototype for 'p1022ds_valid_monitor_port' [-Werror=missing-prototypes] arch/powerpc/platforms/85xx/p1022_ds.c:435:13: error: no previous prototype for 'p1022_ds_pic_init' [-Werror=missing-prototypes] arch/powerpc/platforms/85xx/p1022_rdk.c:43:6: error: no previous prototype for 'p1022rdk_set_pixel_clock' [-Werror=missing-prototypes] arch/powerpc/platforms/85xx/p1022_rdk.c:92:1: error: no previous prototype for 'p1022rdk_valid_monitor_port' [-Werror=missing-prototypes] arch/powerpc/platforms/85xx/p1022_rdk.c:99:13: error: no previous prototype for 'p1022_rdk_pic_init' [-Werror=missing-prototypes] arch/powerpc/platforms/85xx/socrates_fpga_pic.c:273:13: error: no previous prototype for 'socrates_fpga_pic_init' [-Werror=missing-prototypes] arch/powerpc/platforms/85xx/xes_mpc85xx.c:40:13: error: no previous prototype for 'xes_mpc85xx_pic_init' [-Werror=missing-prototypes] arch/powerpc/platforms/85xx/mvme2500.c:24:13: error: no previous prototype for 'mvme2500_pic_init' [-Werror=missing-prototypes] Signed-off-by: Arnd Bergmann Signed-off-by: Michael Ellerman Link: https://msgid.link/20240123125148.2004648-2-arnd@kernel.org --- arch/powerpc/platforms/85xx/mpc8536_ds.c | 2 +- arch/powerpc/platforms/85xx/mvme2500.c | 2 +- arch/powerpc/platforms/85xx/p1010rdb.c | 2 +- arch/powerpc/platforms/85xx/p1022_ds.c | 6 +++--- arch/powerpc/platforms/85xx/p1022_rdk.c | 6 +++--- arch/powerpc/platforms/85xx/socrates_fpga_pic.c | 2 ++ arch/powerpc/platforms/85xx/xes_mpc85xx.c | 2 +- 7 files changed, 12 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c index e966b2ad8ecd..b3327a358eb4 100644 --- a/arch/powerpc/platforms/85xx/mpc8536_ds.c +++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c @@ -27,7 +27,7 @@ #include "mpc85xx.h" -void __init mpc8536_ds_pic_init(void) +static void __init mpc8536_ds_pic_init(void) { struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN, 0, 256, " OpenPIC "); diff --git a/arch/powerpc/platforms/85xx/mvme2500.c b/arch/powerpc/platforms/85xx/mvme2500.c index 1b59e45a0c64..19122daadb55 100644 --- a/arch/powerpc/platforms/85xx/mvme2500.c +++ b/arch/powerpc/platforms/85xx/mvme2500.c @@ -21,7 +21,7 @@ #include "mpc85xx.h" -void __init mvme2500_pic_init(void) +static void __init mvme2500_pic_init(void) { struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU, diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c index 10d6f1fa3327..491895ac8bcf 100644 --- a/arch/powerpc/platforms/85xx/p1010rdb.c +++ b/arch/powerpc/platforms/85xx/p1010rdb.c @@ -24,7 +24,7 @@ #include "mpc85xx.h" -void __init p1010_rdb_pic_init(void) +static void __init p1010_rdb_pic_init(void) { struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU, diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c index 0dd786a061a6..adc3a2ee1415 100644 --- a/arch/powerpc/platforms/85xx/p1022_ds.c +++ b/arch/powerpc/platforms/85xx/p1022_ds.c @@ -370,7 +370,7 @@ exit: * * @pixclock: the wavelength, in picoseconds, of the clock */ -void p1022ds_set_pixel_clock(unsigned int pixclock) +static void p1022ds_set_pixel_clock(unsigned int pixclock) { struct device_node *guts_np = NULL; struct ccsr_guts __iomem *guts; @@ -418,7 +418,7 @@ void p1022ds_set_pixel_clock(unsigned int pixclock) /** * p1022ds_valid_monitor_port: set the monitor port for sysfs */ -enum fsl_diu_monitor_port +static enum fsl_diu_monitor_port p1022ds_valid_monitor_port(enum fsl_diu_monitor_port port) { switch (port) { @@ -432,7 +432,7 @@ p1022ds_valid_monitor_port(enum fsl_diu_monitor_port port) #endif -void __init p1022_ds_pic_init(void) +static void __init p1022_ds_pic_init(void) { struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU, diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c index 25ab6e9c1470..6198299d95b1 100644 --- a/arch/powerpc/platforms/85xx/p1022_rdk.c +++ b/arch/powerpc/platforms/85xx/p1022_rdk.c @@ -40,7 +40,7 @@ * * @pixclock: the wavelength, in picoseconds, of the clock */ -void p1022rdk_set_pixel_clock(unsigned int pixclock) +static void p1022rdk_set_pixel_clock(unsigned int pixclock) { struct device_node *guts_np = NULL; struct ccsr_guts __iomem *guts; @@ -88,7 +88,7 @@ void p1022rdk_set_pixel_clock(unsigned int pixclock) /** * p1022rdk_valid_monitor_port: set the monitor port for sysfs */ -enum fsl_diu_monitor_port +static enum fsl_diu_monitor_port p1022rdk_valid_monitor_port(enum fsl_diu_monitor_port port) { return FSL_DIU_PORT_DVI; @@ -96,7 +96,7 @@ p1022rdk_valid_monitor_port(enum fsl_diu_monitor_port port) #endif -void __init p1022_rdk_pic_init(void) +static void __init p1022_rdk_pic_init(void) { struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU, diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c index baa12eff6d5d..60e0b8947ce6 100644 --- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c +++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c @@ -8,6 +8,8 @@ #include #include +#include "socrates_fpga_pic.h" + /* * The FPGA supports 9 interrupt sources, which can be routed to 3 * interrupt request lines of the MPIC. The line to be used can be diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c index 45f257fc1ade..2582427d8d01 100644 --- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c +++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c @@ -37,7 +37,7 @@ #define MPC85xx_L2CTL_L2I 0x40000000 /* L2 flash invalidate */ #define MPC85xx_L2CTL_L2SIZ_MASK 0x30000000 /* L2 SRAM size (R/O) */ -void __init xes_mpc85xx_pic_init(void) +static void __init xes_mpc85xx_pic_init(void) { struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN, 0, 256, " OpenPIC "); From 1fba2bf8e9d5a27b7394856181b6200de7260b79 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 14 Feb 2024 11:00:41 +1100 Subject: [PATCH 09/14] Revert "powerpc/pseries/iommu: Fix iommu initialisation during DLPAR add" This reverts commit ed8b94f6e0acd652ce69bd69d678a0c769172df8. Gaurav reported that there are still problems with the patch and it should be reverted pending a fuller fix. Link: https://lore.kernel.org/all/4f6fc1ac-7a76-4447-9d0e-f55c0be373f8@linux.ibm.com/ Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/ppc-pci.h | 3 --- arch/powerpc/kernel/iommu.c | 21 +++++---------------- arch/powerpc/platforms/pseries/pci_dlpar.c | 4 ---- 3 files changed, 5 insertions(+), 23 deletions(-) diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index c3a3f3df36d1..ce2b1b5eebdd 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -29,9 +29,6 @@ void *pci_traverse_device_nodes(struct device_node *start, void *(*fn)(struct device_node *, void *), void *data); extern void pci_devs_phb_init_dynamic(struct pci_controller *phb); -extern void ppc_iommu_register_device(struct pci_controller *phb); -extern void ppc_iommu_unregister_device(struct pci_controller *phb); - /* From rtas_pci.h */ extern void init_pci_config_tokens (void); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index c6f62e130d55..ebe259bdd462 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1388,21 +1388,6 @@ static const struct attribute_group *spapr_tce_iommu_groups[] = { NULL, }; -void ppc_iommu_register_device(struct pci_controller *phb) -{ - iommu_device_sysfs_add(&phb->iommu, phb->parent, - spapr_tce_iommu_groups, "iommu-phb%04x", - phb->global_number); - iommu_device_register(&phb->iommu, &spapr_tce_iommu_ops, - phb->parent); -} - -void ppc_iommu_unregister_device(struct pci_controller *phb) -{ - iommu_device_unregister(&phb->iommu); - iommu_device_sysfs_remove(&phb->iommu); -} - /* * This registers IOMMU devices of PHBs. This needs to happen * after core_initcall(iommu_init) + postcore_initcall(pci_driver_init) and @@ -1413,7 +1398,11 @@ static int __init spapr_tce_setup_phb_iommus_initcall(void) struct pci_controller *hose; list_for_each_entry(hose, &hose_list, list_node) { - ppc_iommu_register_device(hose); + iommu_device_sysfs_add(&hose->iommu, hose->parent, + spapr_tce_iommu_groups, "iommu-phb%04x", + hose->global_number); + iommu_device_register(&hose->iommu, &spapr_tce_iommu_ops, + hose->parent); } return 0; } diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 4448386268d9..4ba824568119 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -35,8 +35,6 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn) pseries_msi_allocate_domains(phb); - ppc_iommu_register_device(phb); - /* Create EEH devices for the PHB */ eeh_phb_pe_create(phb); @@ -78,8 +76,6 @@ int remove_phb_dynamic(struct pci_controller *phb) } } - ppc_iommu_unregister_device(phb); - pseries_msi_free_domains(phb); /* Keep a reference so phb isn't freed yet */ From f1acb109505d983779bbb7e20a1ee6244d2b5736 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 12 Feb 2024 17:42:44 +1100 Subject: [PATCH 10/14] powerpc/kasan: Limit KASAN thread size increase to 32KB KASAN is seen to increase stack usage, to the point that it was reported to lead to stack overflow on some 32-bit machines (see link). To avoid overflows the stack size was doubled for KASAN builds in commit 3e8635fb2e07 ("powerpc/kasan: Force thread size increase with KASAN"). However with a 32KB stack size to begin with, the doubling leads to a 64KB stack, which causes build errors: arch/powerpc/kernel/switch.S:249: Error: operand out of range (0x000000000000fe50 is not between 0xffffffffffff8000 and 0x0000000000007fff) Although the asm could be reworked, in practice a 32KB stack seems sufficient even for KASAN builds - the additional usage seems to be in the 2-3KB range for a 64-bit KASAN build. So only increase the stack for KASAN if the stack size is < 32KB. Fixes: 18f14afe2816 ("powerpc/64s: Increase default stack size to 32KB") Reported-by: Spoorthy Reported-by: Benjamin Gray Reviewed-by: Benjamin Gray Link: https://lore.kernel.org/linuxppc-dev/bug-207129-206035@https.bugzilla.kernel.org%2F/ Signed-off-by: Michael Ellerman Link: https://msgid.link/20240212064244.3924505-1-mpe@ellerman.id.au --- arch/powerpc/include/asm/thread_info.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index bf5dde1a4114..15c5691dd218 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -14,7 +14,7 @@ #ifdef __KERNEL__ -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN) && CONFIG_THREAD_SHIFT < 15 #define MIN_THREAD_SHIFT (CONFIG_THREAD_SHIFT + 1) #else #define MIN_THREAD_SHIFT CONFIG_THREAD_SHIFT From eb6d871f4ba49ac8d0537e051fe983a3a4027f61 Mon Sep 17 00:00:00 2001 From: David Engraf Date: Wed, 7 Feb 2024 10:27:58 +0100 Subject: [PATCH 11/14] powerpc/cputable: Add missing PPC_FEATURE_BOOKE on PPC64 Book-E Commit e320a76db4b0 ("powerpc/cputable: Split cpu_specs[] out of cputable.h") moved the cpu_specs to separate header files. Previously PPC_FEATURE_BOOKE was enabled by CONFIG_PPC_BOOK3E_64. The definition in cpu_specs_e500mc.h for PPC64 no longer enables PPC_FEATURE_BOOKE. This breaks user space reading the ELF hwcaps and expect PPC_FEATURE_BOOKE. Debugging an application with gdb is no longer working on e5500/e6500 because the 64-bit detection relies on PPC_FEATURE_BOOKE for Book-E. Fixes: e320a76db4b0 ("powerpc/cputable: Split cpu_specs[] out of cputable.h") Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: David Engraf Reviewed-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/20240207092758.1058893-1-david.engraf@sysgo.com --- arch/powerpc/kernel/cpu_specs_e500mc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/cpu_specs_e500mc.h b/arch/powerpc/kernel/cpu_specs_e500mc.h index ceb06b109f83..2ae8e9a7b461 100644 --- a/arch/powerpc/kernel/cpu_specs_e500mc.h +++ b/arch/powerpc/kernel/cpu_specs_e500mc.h @@ -8,7 +8,8 @@ #ifdef CONFIG_PPC64 #define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ - PPC_FEATURE_HAS_FPU | PPC_FEATURE_64) + PPC_FEATURE_HAS_FPU | PPC_FEATURE_64 | \ + PPC_FEATURE_BOOKE) #else #define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ PPC_FEATURE_BOOKE) From ea73179e64131bcd29ba6defd33732abdf8ca14b Mon Sep 17 00:00:00 2001 From: Naveen N Rao Date: Tue, 13 Feb 2024 23:24:10 +0530 Subject: [PATCH 12/14] powerpc/ftrace: Ignore ftrace locations in exit text sections Michael reported that we are seeing an ftrace bug on bootup when KASAN is enabled and we are using -fpatchable-function-entry: ftrace: allocating 47780 entries in 18 pages ftrace-powerpc: 0xc0000000020b3d5c: No module provided for non-kernel address ------------[ ftrace bug ]------------ ftrace faulted on modifying [] 0xc0000000020b3d5c Initializing ftrace call sites ftrace record flags: 0 (0) expected tramp: c00000000008cef4 ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at kernel/trace/ftrace.c:2180 ftrace_bug+0x3c0/0x424 Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 6.5.0-rc3-00120-g0f71dcfb4aef #860 Hardware name: IBM pSeries (emulated by qemu) POWER9 (raw) 0x4e1202 0xf000005 of:SLOF,HEAD hv:linux,kvm pSeries NIP: c0000000003aa81c LR: c0000000003aa818 CTR: 0000000000000000 REGS: c0000000033cfab0 TRAP: 0700 Not tainted (6.5.0-rc3-00120-g0f71dcfb4aef) MSR: 8000000002021033 CR: 28028240 XER: 00000000 CFAR: c0000000002781a8 IRQMASK: 3 ... NIP [c0000000003aa81c] ftrace_bug+0x3c0/0x424 LR [c0000000003aa818] ftrace_bug+0x3bc/0x424 Call Trace: ftrace_bug+0x3bc/0x424 (unreliable) ftrace_process_locs+0x5f4/0x8a0 ftrace_init+0xc0/0x1d0 start_kernel+0x1d8/0x484 With CONFIG_FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY=y and CONFIG_KASAN=y, compiler emits nops in functions that it generates for registering and unregistering global variables (unlike with -pg and -mprofile-kernel where calls to _mcount() are not generated in those functions). Those functions then end up in INIT_TEXT and EXIT_TEXT respectively. We don't expect to see any profiled functions in EXIT_TEXT, so ftrace_init_nop() assumes that all addresses that aren't in the core kernel text belongs to a module. Since these functions do not match that criteria, we see the above bug. Address this by having ftrace ignore all locations in the text exit sections of vmlinux. Fixes: 0f71dcfb4aef ("powerpc/ftrace: Add support for -fpatchable-function-entry") Cc: stable@vger.kernel.org # v6.6+ Reported-by: Michael Ellerman Signed-off-by: Naveen N Rao Reviewed-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20240213175410.1091313-1-naveen@kernel.org --- arch/powerpc/include/asm/ftrace.h | 10 ++-------- arch/powerpc/include/asm/sections.h | 1 + arch/powerpc/kernel/trace/ftrace.c | 12 ++++++++++++ arch/powerpc/kernel/trace/ftrace_64_pg.c | 5 +++++ arch/powerpc/kernel/vmlinux.lds.S | 2 ++ 5 files changed, 22 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index 1ebd2ca97f12..107fc5a48456 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -20,14 +20,6 @@ #ifndef __ASSEMBLY__ extern void _mcount(void); -static inline unsigned long ftrace_call_adjust(unsigned long addr) -{ - if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) - addr += MCOUNT_INSN_SIZE; - - return addr; -} - unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp); @@ -142,8 +134,10 @@ static inline u8 this_cpu_get_ftrace_enabled(void) { return 1; } #ifdef CONFIG_FUNCTION_TRACER extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[]; void ftrace_free_init_tramp(void); +unsigned long ftrace_call_adjust(unsigned long addr); #else static inline void ftrace_free_init_tramp(void) { } +static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; } #endif #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index ea26665f82cf..f43f3a6b0051 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -14,6 +14,7 @@ typedef struct func_desc func_desc_t; extern char __head_end[]; extern char __srwx_boundary[]; +extern char __exittext_begin[], __exittext_end[]; /* Patch sites */ extern s32 patch__call_flush_branch_caches1; diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 82010629cf88..d8d6b4fd9a14 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -27,10 +27,22 @@ #include #include #include +#include #define NUM_FTRACE_TRAMPS 2 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS]; +unsigned long ftrace_call_adjust(unsigned long addr) +{ + if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end) + return 0; + + if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) + addr += MCOUNT_INSN_SIZE; + + return addr; +} + static ppc_inst_t ftrace_create_branch_inst(unsigned long ip, unsigned long addr, int link) { ppc_inst_t op; diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c index 7b85c3b460a3..12fab1803bcf 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_pg.c +++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c @@ -37,6 +37,11 @@ #define NUM_FTRACE_TRAMPS 8 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS]; +unsigned long ftrace_call_adjust(unsigned long addr) +{ + return addr; +} + static ppc_inst_t ftrace_call_replace(unsigned long ip, unsigned long addr, int link) { diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 1c5970df3233..f420df7888a7 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -281,7 +281,9 @@ SECTIONS * to deal with references from __bug_table */ .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) { + __exittext_begin = .; EXIT_TEXT + __exittext_end = .; } . = ALIGN(PAGE_SIZE); From cbecc9fcbbec60136b0180ba0609c829afed5c81 Mon Sep 17 00:00:00 2001 From: Shrikanth Hegde Date: Tue, 13 Feb 2024 10:56:35 +0530 Subject: [PATCH 13/14] powerpc/pseries: fix accuracy of stolen time powerVM hypervisor updates the VPA fields with stolen time data. It currently reports enqueue_dispatch_tb and ready_enqueue_tb for this purpose. In linux these two fields are used to report the stolen time. The VPA fields are updated at the TB frequency. On powerPC its mostly set at 512Mhz. Hence this needs a conversion to ns when reporting it back as rest of the kernel timings are in ns. This conversion is already handled in tb_to_ns function. So use that function to report accurate stolen time. Observed this issue and used an Capped Shared Processor LPAR(SPLPAR) to simplify the experiments. In all these cases, 100% VP Load is run using stress-ng workload. Values of stolen time is in percentages as reported by mpstat. With the patch values are close to expected. 6.8.rc1 +Patch 12EC/12VP 0.0 0.0 12EC/24VP 25.7 50.2 12EC/36VP 37.3 69.2 12EC/48VP 38.5 78.3 Fixes: 0e8a63132800 ("powerpc/pseries: Implement CONFIG_PARAVIRT_TIME_ACCOUNTING") Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Shrikanth Hegde Reviewed-by: Nicholas Piggin Reviewed-by: Srikar Dronamraju Signed-off-by: Michael Ellerman Link: https://msgid.link/20240213052635.231597-1-sshegde@linux.ibm.com --- arch/powerpc/platforms/pseries/lpar.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 4561667832ed..4e9916bb03d7 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -662,8 +662,12 @@ u64 pseries_paravirt_steal_clock(int cpu) { struct lppaca *lppaca = &lppaca_of(cpu); - return be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) + - be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb)); + /* + * VPA steal time counters are reported at TB frequency. Hence do a + * conversion to ns before returning + */ + return tb_to_ns(be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) + + be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb))); } #endif From 0846dd77c8349ec92ca0079c9c71d130f34cb192 Mon Sep 17 00:00:00 2001 From: Shivaprasad G Bhat Date: Tue, 13 Feb 2024 10:05:22 -0600 Subject: [PATCH 14/14] powerpc/iommu: Fix the missing iommu_group_put() during platform domain attach The function spapr_tce_platform_iommu_attach_dev() is missing to call iommu_group_put() when the domain is already set. This refcount leak shows up with BUG_ON() during DLPAR remove operation as: KernelBug: Kernel bug in state 'None': kernel BUG at arch/powerpc/platforms/pseries/iommu.c:100! Oops: Exception in kernel mode, sig: 5 [#1] LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=8192 NUMA pSeries Hardware name: IBM,9080-HEX POWER10 (raw) 0x800200 0xf000006 of:IBM,FW1060.00 (NH1060_016) hv:phyp pSeries NIP: c0000000000ff4d4 LR: c0000000000ff4cc CTR: 0000000000000000 REGS: c0000013aed5f840 TRAP: 0700 Tainted: G I (6.8.0-rc3-autotest-g99bd3cb0d12e) MSR: 8000000000029033 CR: 44002402 XER: 20040000 CFAR: c000000000a0d170 IRQMASK: 0 ... NIP iommu_reconfig_notifier+0x94/0x200 LR iommu_reconfig_notifier+0x8c/0x200 Call Trace: iommu_reconfig_notifier+0x8c/0x200 (unreliable) notifier_call_chain+0xb8/0x19c blocking_notifier_call_chain+0x64/0x98 of_reconfig_notify+0x44/0xdc of_detach_node+0x78/0xb0 ofdt_write.part.0+0x86c/0xbb8 proc_reg_write+0xf4/0x150 vfs_write+0xf8/0x488 ksys_write+0x84/0x140 system_call_exception+0x138/0x330 system_call_vectored_common+0x15c/0x2ec The patch adds the missing iommu_group_put() call. Fixes: a8ca9fc9134c ("powerpc/iommu: Do not do platform domain attach atctions after probe") Reported-by: Venkat Rao Bagalkote Closes: https://lore.kernel.org/all/274e0d2b-b5cc-475e-94e6-8427e88e271d@linux.vnet.ibm.com/ Signed-off-by: Shivaprasad G Bhat Tested-by: Venkat Rao Bagalkote Reviewed-by: Jason Gunthorpe Signed-off-by: Michael Ellerman Link: https://msgid.link/170784021983.6249.10039296655906636112.stgit@linux.ibm.com --- arch/powerpc/kernel/iommu.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index ebe259bdd462..df17b33b89d1 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1290,8 +1290,10 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain, int ret = -EINVAL; /* At first attach the ownership is already set */ - if (!domain) + if (!domain) { + iommu_group_put(grp); return 0; + } if (!grp) return -ENODEV;