From 1c7f4fe86f17f296bafab1d418c040533324bf4f Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Mon, 28 Oct 2019 19:54:24 +1100 Subject: powerpc/pci: Remove pcibios_setup_bus_devices() With the previous patch applied pcibios_setup_device() will always be run when pcibios_bus_add_device() is called. There are several code paths where pcibios_setup_bus_device() is still called (the PowerPC specific PCI hotplug support is one) so with just the previous patch applied the setup can be run multiple times on a device, once before the device is added to the bus and once after. There's no need to run the setup in the early case any more so just remove it entirely. Signed-off-by: Oliver O'Halloran Tested-by: Alexey Kardashevskiy Reviewed-by: Alexey Kardashevskiy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20191028085424.12006-3-oohall@gmail.com --- arch/powerpc/include/asm/pci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 327567b8f7d6..63ed7e3b0ba3 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -113,7 +113,6 @@ extern pgprot_t pci_phys_mem_access_prot(struct file *file, pgprot_t prot); extern resource_size_t pcibios_io_space_offset(struct pci_controller *hose); -extern void pcibios_setup_bus_devices(struct pci_bus *bus); extern void pcibios_setup_bus_self(struct pci_bus *bus); extern void pcibios_setup_phb_io_space(struct pci_controller *hose); extern void pcibios_scan_phb(struct pci_controller *hose); -- cgit v1.2.3 From 17a0364cb07c173f64cefe973a93b8dbd9c61795 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Mon, 16 Dec 2019 15:19:23 +1100 Subject: powerpc/pseries/iommu: Separate FW_FEATURE_MULTITCE to put/stuff features H_PUT_TCE_INDIRECT allows packing up to 512 TCE updates into a single hypercall; H_STUFF_TCE can clear lots in a single hypercall too. However, unlike H_STUFF_TCE (which writes the same TCE to all entries), H_PUT_TCE_INDIRECT uses a 4K page with new TCEs. In a secure VM environment this means sharing a secure VM page with a hypervisor which we would rather avoid. This splits the FW_FEATURE_MULTITCE feature into FW_FEATURE_PUT_TCE_IND and FW_FEATURE_STUFF_TCE. "hcall-multi-tce" in the "/rtas/ibm,hypertas-functions" device tree property sets both; the "multitce=off" kernel command line parameter disables both. This should not cause behavioural change. Signed-off-by: Alexey Kardashevskiy Reviewed-by: Thiago Jung Bauermann Tested-by: Thiago Jung Bauermann Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20191216041924.42318-4-aik@ozlabs.ru --- arch/powerpc/include/asm/firmware.h | 6 ++++-- arch/powerpc/platforms/pseries/firmware.c | 3 ++- arch/powerpc/platforms/pseries/iommu.c | 12 +++++++----- 3 files changed, 13 insertions(+), 8 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index b3e214a97f3a..ca33f4ef6cb4 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -33,7 +33,7 @@ #define FW_FEATURE_LLAN ASM_CONST(0x0000000000010000) #define FW_FEATURE_BULK_REMOVE ASM_CONST(0x0000000000020000) #define FW_FEATURE_XDABR ASM_CONST(0x0000000000040000) -#define FW_FEATURE_MULTITCE ASM_CONST(0x0000000000080000) +#define FW_FEATURE_PUT_TCE_IND ASM_CONST(0x0000000000080000) #define FW_FEATURE_SPLPAR ASM_CONST(0x0000000000100000) #define FW_FEATURE_LPAR ASM_CONST(0x0000000000400000) #define FW_FEATURE_PS3_LV1 ASM_CONST(0x0000000000800000) @@ -51,6 +51,7 @@ #define FW_FEATURE_BLOCK_REMOVE ASM_CONST(0x0000001000000000) #define FW_FEATURE_PAPR_SCM ASM_CONST(0x0000002000000000) #define FW_FEATURE_ULTRAVISOR ASM_CONST(0x0000004000000000) +#define FW_FEATURE_STUFF_TCE ASM_CONST(0x0000008000000000) #ifndef __ASSEMBLY__ @@ -63,7 +64,8 @@ enum { FW_FEATURE_MIGRATE | FW_FEATURE_PERFMON | FW_FEATURE_CRQ | FW_FEATURE_VIO | FW_FEATURE_RDMA | FW_FEATURE_LLAN | FW_FEATURE_BULK_REMOVE | FW_FEATURE_XDABR | - FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR | + FW_FEATURE_PUT_TCE_IND | FW_FEATURE_STUFF_TCE | + FW_FEATURE_SPLPAR | FW_FEATURE_LPAR | FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO | FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY | FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN | diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index d4a8f1702417..d3acff23f2e3 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -55,7 +55,8 @@ hypertas_fw_features_table[] = { {FW_FEATURE_LLAN, "hcall-lLAN"}, {FW_FEATURE_BULK_REMOVE, "hcall-bulk"}, {FW_FEATURE_XDABR, "hcall-xdabr"}, - {FW_FEATURE_MULTITCE, "hcall-multi-tce"}, + {FW_FEATURE_PUT_TCE_IND | FW_FEATURE_STUFF_TCE, + "hcall-multi-tce"}, {FW_FEATURE_SPLPAR, "hcall-splpar"}, {FW_FEATURE_VPHN, "hcall-vphn"}, {FW_FEATURE_SET_MODE, "hcall-set-mode"}, diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index b4ce9d472dfe..2e0a8eab5588 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -192,7 +192,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, int ret = 0; unsigned long flags; - if ((npages == 1) || !firmware_has_feature(FW_FEATURE_MULTITCE)) { + if ((npages == 1) || !firmware_has_feature(FW_FEATURE_PUT_TCE_IND)) { return tce_build_pSeriesLP(tbl->it_index, tcenum, tbl->it_page_shift, npages, uaddr, direction, attrs); @@ -286,7 +286,7 @@ static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long n { u64 rc; - if (!firmware_has_feature(FW_FEATURE_MULTITCE)) + if (!firmware_has_feature(FW_FEATURE_STUFF_TCE)) return tce_free_pSeriesLP(tbl->it_index, tcenum, npages); rc = plpar_tce_stuff((u64)tbl->it_index, (u64)tcenum << 12, 0, npages); @@ -402,7 +402,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, u64 rc = 0; long l, limit; - if (!firmware_has_feature(FW_FEATURE_MULTITCE)) { + if (!firmware_has_feature(FW_FEATURE_PUT_TCE_IND)) { unsigned long tceshift = be32_to_cpu(maprange->tce_shift); unsigned long dmastart = (start_pfn << PAGE_SHIFT) + be64_to_cpu(maprange->dma_base); @@ -1341,9 +1341,11 @@ static int __init disable_multitce(char *str) { if (strcmp(str, "off") == 0 && firmware_has_feature(FW_FEATURE_LPAR) && - firmware_has_feature(FW_FEATURE_MULTITCE)) { + (firmware_has_feature(FW_FEATURE_PUT_TCE_IND) || + firmware_has_feature(FW_FEATURE_STUFF_TCE))) { printk(KERN_INFO "Disabling MULTITCE firmware feature\n"); - powerpc_firmware_features &= ~FW_FEATURE_MULTITCE; + powerpc_firmware_features &= + ~(FW_FEATURE_PUT_TCE_IND | FW_FEATURE_STUFF_TCE); } return 1; } -- cgit v1.2.3 From 6ad4afc97bc6c5cca9786030492ddfab871ce79e Mon Sep 17 00:00:00 2001 From: Bai Yingjie Date: Mon, 6 Jan 2020 12:29:53 +0800 Subject: powerpc32/booke: consistently return phys_addr_t in __pa() When CONFIG_RELOCATABLE=y is set, VIRT_PHYS_OFFSET is a 64bit variable, thus __pa() returns as 64bit value. But when CONFIG_RELOCATABLE=n, __pa() returns 32bit value. When CONFIG_PHYS_64BIT is set, __pa() should consistently return as 64bit value irrelevant to CONFIG_RELOCATABLE. So we'd make __pa() consistently return phys_addr_t, which is 64bit when CONFIG_PHYS_64BIT is set. Signed-off-by: Bai Yingjie Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200106042957.26494-1-yingjie_bai@126.com --- arch/powerpc/include/asm/page.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 7f1fd41e3065..86332080399a 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -209,7 +209,7 @@ static inline bool pfn_valid(unsigned long pfn) */ #if defined(CONFIG_PPC32) && defined(CONFIG_BOOKE) #define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + VIRT_PHYS_OFFSET)) -#define __pa(x) ((unsigned long)(x) - VIRT_PHYS_OFFSET) +#define __pa(x) ((phys_addr_t)(unsigned long)(x) - VIRT_PHYS_OFFSET) #else #ifdef CONFIG_PPC64 /* -- cgit v1.2.3 From ed0bc98f8cbe4f8254759d333a47aedc816ff8c5 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 11 Jul 2019 12:24:03 +1000 Subject: powerpc/64s: Reimplement power4_idle code in C This implements the tricky tracing and soft irq handling bits in C, leaving the low level bit to asm. A functional difference is that this redirects the interrupt exit to a return stub to execute blr, rather than the lr address itself. This is probably barely measurable on real hardware, but it keeps the link stack balanced. Tested with QEMU. Signed-off-by: Nicholas Piggin [mpe: Move power4_fixup_nap back into exceptions-64s.S] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190711022404.18132-1-npiggin@gmail.com --- arch/powerpc/include/asm/processor.h | 3 ++ arch/powerpc/kernel/Makefile | 3 +- arch/powerpc/kernel/exceptions-64s.S | 13 +++++- arch/powerpc/kernel/idle.c | 25 +++++++++++ arch/powerpc/kernel/idle_book3s.S | 20 +++++++++ arch/powerpc/kernel/idle_power4.S | 83 ------------------------------------ arch/powerpc/platforms/Kconfig | 4 ++ 7 files changed, 64 insertions(+), 87 deletions(-) delete mode 100644 arch/powerpc/kernel/idle_power4.S (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index a9993e7a443b..e114eb36721c 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -412,6 +412,9 @@ static inline unsigned long get_clean_sp(unsigned long sp, int is_32) extern unsigned long isa300_idle_stop_noloss(unsigned long psscr_val); extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val); extern unsigned long isa206_idle_insn_mayloss(unsigned long type); +#ifdef CONFIG_PPC_970_NAP +extern void power4_idle_nap(void); +#endif extern unsigned long cpuidle_disable; enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF}; diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 157b0147921f..78a1b22d4fd8 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -62,8 +62,7 @@ obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o -obj-$(CONFIG_PPC_970_NAP) += idle_power4.o -obj-$(CONFIG_PPC_P7_NAP) += idle_book3s.o +obj-$(CONFIG_PPC_BOOK3S_IDLE) += idle_book3s.o procfs-y := proc_powerpc.o obj-$(CONFIG_PROC_FS) += $(procfs-y) rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI) := rtas_pci.o diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 46508b148e16..b049c0bfa883 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -2208,11 +2208,20 @@ __end_interrupts: DEFINE_FIXED_SYMBOL(__end_interrupts) #ifdef CONFIG_PPC_970_NAP + /* + * Called by exception entry code if _TLF_NAPPING was set, this clears + * the NAPPING flag, and redirects the exception exit to + * power4_fixup_nap_return. + */ + .globl power4_fixup_nap EXC_COMMON_BEGIN(power4_fixup_nap) andc r9,r9,r10 std r9,TI_LOCAL_FLAGS(r11) - ld r10,_LINK(r1) /* make idle task do the */ - std r10,_NIP(r1) /* equivalent of a blr */ + LOAD_REG_ADDR(r10, power4_idle_nap_return) + std r10,_NIP(r1) + blr + +power4_idle_nap_return: blr #endif diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index a36fd053c3db..422e31d2f5a2 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -77,6 +77,31 @@ void arch_cpu_idle(void) int powersave_nap; +#ifdef CONFIG_PPC_970_NAP +void power4_idle(void) +{ + if (!cpu_has_feature(CPU_FTR_CAN_NAP)) + return; + + if (!powersave_nap) + return; + + if (!prep_irq_for_idle()) + return; + + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + asm volatile("DSSALL ; sync" ::: "memory"); + + power4_idle_nap(); + + /* + * power4_idle_nap returns with interrupts enabled (soft and hard). + * to our caller with interrupts enabled (soft and hard). Our caller + * can cope with either interrupts disabled or enabled upon return. + */ +} +#endif + #ifdef CONFIG_SYSCTL /* * Register the sysctl to set/clear powersave_nap. diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index d32751994a62..22f249b6f58d 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -15,7 +15,9 @@ #include #include #include +#include /* TLF_NAPPING */ +#ifdef CONFIG_PPC_P7_NAP /* * Desired PSSCR in r3 * @@ -181,4 +183,22 @@ _GLOBAL(isa206_idle_insn_mayloss) bne 2f IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP) 2: IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE) +#endif +#ifdef CONFIG_PPC_970_NAP +_GLOBAL(power4_idle_nap) + LOAD_REG_IMMEDIATE(r7, MSR_KERNEL|MSR_EE|MSR_POW) + ld r9,PACA_THREAD_INFO(r13) + ld r8,TI_LOCAL_FLAGS(r9) + ori r8,r8,_TLF_NAPPING + std r8,TI_LOCAL_FLAGS(r9) + /* + * NAPPING bit is set, from this point onward power4_fixup_nap + * will cause exceptions to return to power4_idle_nap_return. + */ +1: sync + isync + mtmsrd r7 + isync + b 1b +#endif diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S deleted file mode 100644 index 33c625329078..000000000000 --- a/arch/powerpc/kernel/idle_power4.S +++ /dev/null @@ -1,83 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * This file contains the power_save function for 970-family CPUs. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#undef DEBUG - - .text - -_GLOBAL(power4_idle) -BEGIN_FTR_SECTION - blr -END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP) - /* Now check if user or arch enabled NAP mode */ - LOAD_REG_ADDRBASE(r3,powersave_nap) - lwz r4,ADDROFF(powersave_nap)(r3) - cmpwi 0,r4,0 - beqlr - - /* This sequence is similar to prep_irq_for_idle() */ - - /* Hard disable interrupts */ - mfmsr r7 - rldicl r0,r7,48,1 - rotldi r0,r0,16 - mtmsrd r0,1 - - /* Check if something happened while soft-disabled */ - lbz r0,PACAIRQHAPPENED(r13) - cmpwi cr0,r0,0 - bne- 2f - - /* - * Soft-enable interrupts. This will make power4_fixup_nap return - * to our caller with interrupts enabled (soft and hard). The caller - * can cope with either interrupts disabled or enabled upon return. - */ -#ifdef CONFIG_TRACE_IRQFLAGS - /* Tell the tracer interrupts are on, because idle responds to them. */ - mflr r0 - std r0,16(r1) - stdu r1,-128(r1) - bl trace_hardirqs_on - addi r1,r1,128 - ld r0,16(r1) - mtlr r0 - mfmsr r7 -#endif /* CONFIG_TRACE_IRQFLAGS */ - - li r0,IRQS_ENABLED - stb r0,PACAIRQSOFTMASK(r13) /* we'll hard-enable shortly */ -BEGIN_FTR_SECTION - DSSALL - sync -END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) - ld r9, PACA_THREAD_INFO(r13) - ld r8,TI_LOCAL_FLAGS(r9) /* set napping bit */ - ori r8,r8,_TLF_NAPPING /* so when we take an exception */ - std r8,TI_LOCAL_FLAGS(r9) /* it will return to our caller */ - ori r7,r7,MSR_EE - oris r7,r7,MSR_POW@h -1: sync - isync - mtmsrd r7 - isync - b 1b - -2: /* Return if an interrupt had happened while soft disabled */ - /* Set the HARD_DIS flag because interrupts are now hard disabled */ - ori r0,r0,PACA_IRQ_HARD_DIS - stb r0,PACAIRQHAPPENED(r13) - blr diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index e28df298df56..1f8025383caa 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -177,6 +177,10 @@ config PPC_970_NAP config PPC_P7_NAP bool +config PPC_BOOK3S_IDLE + def_bool y + depends on (PPC_970_NAP || PPC_P7_NAP) + config PPC_INDIRECT_PIO bool select GENERIC_IOMAP -- cgit v1.2.3 From 1e1c8b2cc37afb333c1829e8e0360321813bf220 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 14 Jan 2020 07:14:40 +0000 Subject: powerpc/ptdump: don't entirely rebuild kernel when selecting CONFIG_PPC_DEBUG_WX Selecting CONFIG_PPC_DEBUG_WX only impacts ptdump and pgtable_32/64 init calls. Declaring related functions in asm/pgtable.h implies rebuilding almost everything. Move ptdump_check_wx() declaration in mm/mmu_decl.h Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/bf34fd9dca61eadf9a134a9f89ebbc162cfd5f86.1578986011.git.christophe.leroy@c-s.fr --- arch/powerpc/include/asm/pgtable.h | 6 ------ arch/powerpc/mm/mmu_decl.h | 6 ++++++ arch/powerpc/mm/ptdump/ptdump.c | 2 ++ 3 files changed, 8 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 0e4ec8cc37b7..8cc543ed114c 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -94,12 +94,6 @@ void mark_initmem_nx(void); static inline void mark_initmem_nx(void) { } #endif -#ifdef CONFIG_PPC_DEBUG_WX -void ptdump_check_wx(void); -#else -static inline void ptdump_check_wx(void) { } -#endif - /* * When used, PTE_FRAG_NR is defined in subarch pgtable.h * so we are sure it is included when arriving here. diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index 8e99649c24fc..7097e07a209a 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -181,3 +181,9 @@ void mmu_mark_rodata_ro(void); static inline void mmu_mark_initmem_nx(void) { } static inline void mmu_mark_rodata_ro(void) { } #endif + +#ifdef CONFIG_PPC_DEBUG_WX +void ptdump_check_wx(void); +#else +static inline void ptdump_check_wx(void) { } +#endif diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c index 2f9ddc29c535..4af0d5d9589e 100644 --- a/arch/powerpc/mm/ptdump/ptdump.c +++ b/arch/powerpc/mm/ptdump/ptdump.c @@ -24,6 +24,8 @@ #include #include +#include + #include "ptdump.h" /* -- cgit v1.2.3 From 39413ae009674c6ba745850515b551bbb9d6374b Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 26 Nov 2019 17:43:29 +0000 Subject: powerpc/hw_breakpoints: Rewrite 8xx breakpoints to allow any address range size. Unlike standard powerpc, Powerpc 8xx doesn't have SPRN_DABR, but it has a breakpoint support based on a set of comparators which allow more flexibility. Commit 4ad8622dc548 ("powerpc/8xx: Implement hw_breakpoint") implemented breakpoints by emulating the DABR behaviour. It did this by setting one comparator the match 4 bytes at breakpoint address and the other comparator to match 4 bytes at breakpoint address + 4. Rewrite 8xx hw_breakpoint to make breakpoints match all addresses defined by the breakpoint address and length by making full use of comparators. Now, comparator E is set to match any address greater than breakpoint address minus one. Comparator F is set to match any address lower than breakpoint address plus breakpoint length. Addresses are aligned to 32 bits. When the breakpoint range starts at address 0, the breakpoint is set to match comparator F only. When the breakpoint range end at address 0xffffffff, the breakpoint is set to match comparator E only. Otherwise the breakpoint is set to match comparator E and F. At the same time, use registers bit names instead of hardcoded values. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/05105deeaf63bc02151aea2cdeaf525534e0e9d4.1574790198.git.christophe.leroy@c-s.fr --- arch/powerpc/include/asm/hw_breakpoint.h | 4 +++ arch/powerpc/include/asm/reg_8xx.h | 14 ++++++++ arch/powerpc/kernel/hw_breakpoint.c | 15 +++++---- arch/powerpc/kernel/process.c | 57 ++++++++++++++++++++------------ 4 files changed, 61 insertions(+), 29 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index 27ac6f5d2891..f2f8d8aa8e3b 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -34,7 +34,11 @@ struct arch_hw_breakpoint { #define HW_BRK_TYPE_PRIV_ALL (HW_BRK_TYPE_USER | HW_BRK_TYPE_KERNEL | \ HW_BRK_TYPE_HYP) +#ifdef CONFIG_PPC_8xx +#define HW_BREAKPOINT_ALIGN 0x3 +#else #define HW_BREAKPOINT_ALIGN 0x7 +#endif #define DABR_MAX_LEN 8 #define DAWR_MAX_LEN 512 diff --git a/arch/powerpc/include/asm/reg_8xx.h b/arch/powerpc/include/asm/reg_8xx.h index 07df35ee8cbc..299ee7be0f67 100644 --- a/arch/powerpc/include/asm/reg_8xx.h +++ b/arch/powerpc/include/asm/reg_8xx.h @@ -35,7 +35,21 @@ #define SPRN_CMPE 152 #define SPRN_CMPF 153 #define SPRN_LCTRL1 156 +#define LCTRL1_CTE_GT 0xc0000000 +#define LCTRL1_CTF_LT 0x14000000 +#define LCTRL1_CRWE_RW 0x00000000 +#define LCTRL1_CRWE_RO 0x00040000 +#define LCTRL1_CRWE_WO 0x000c0000 +#define LCTRL1_CRWF_RW 0x00000000 +#define LCTRL1_CRWF_RO 0x00010000 +#define LCTRL1_CRWF_WO 0x00030000 #define SPRN_LCTRL2 157 +#define LCTRL2_LW0EN 0x80000000 +#define LCTRL2_LW0LA_E 0x00000000 +#define LCTRL2_LW0LA_F 0x04000000 +#define LCTRL2_LW0LA_EandF 0x08000000 +#define LCTRL2_LW0LADC 0x02000000 +#define LCTRL2_SLW0EN 0x00000002 #ifdef CONFIG_PPC_8xx #define SPRN_ICTRL 158 #endif diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 58ce3d37c2a3..2462cd7c565c 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -160,6 +160,9 @@ static int hw_breakpoint_validate_len(struct arch_hw_breakpoint *hw) /* DAWR region can't cross 512 bytes boundary */ if ((start_addr >> 9) != (end_addr >> 9)) return -EINVAL; + } else if (IS_ENABLED(CONFIG_PPC_8xx)) { + /* 8xx can setup a range without limitation */ + max_len = U16_MAX; } if (hw_len > max_len) @@ -328,13 +331,11 @@ int hw_breakpoint_handler(struct die_args *args) } info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ; - if (IS_ENABLED(CONFIG_PPC_8xx)) { - if (!dar_within_range(regs->dar, info)) - info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; - } else { - if (!stepping_handler(regs, bp, info)) - goto out; - } + if (!dar_within_range(regs->dar, info)) + info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; + + if (!IS_ENABLED(CONFIG_PPC_8xx) && !stepping_handler(regs, bp, info)) + goto out; /* * As a policy, the callback is invoked in a 'trigger-after-execute' diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 4df94b6e2f32..7fcf72e58826 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -740,28 +740,6 @@ static inline int __set_dabr(unsigned long dabr, unsigned long dabrx) mtspr(SPRN_DABRX, dabrx); return 0; } -#elif defined(CONFIG_PPC_8xx) -static inline int __set_dabr(unsigned long dabr, unsigned long dabrx) -{ - unsigned long addr = dabr & ~HW_BRK_TYPE_DABR; - unsigned long lctrl1 = 0x90000000; /* compare type: equal on E & F */ - unsigned long lctrl2 = 0x8e000002; /* watchpoint 1 on cmp E | F */ - - if ((dabr & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_READ) - lctrl1 |= 0xa0000; - else if ((dabr & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_WRITE) - lctrl1 |= 0xf0000; - else if ((dabr & HW_BRK_TYPE_RDWR) == 0) - lctrl2 = 0; - - mtspr(SPRN_LCTRL2, 0); - mtspr(SPRN_CMPE, addr); - mtspr(SPRN_CMPF, addr + 4); - mtspr(SPRN_LCTRL1, lctrl1); - mtspr(SPRN_LCTRL2, lctrl2); - - return 0; -} #else static inline int __set_dabr(unsigned long dabr, unsigned long dabrx) { @@ -782,6 +760,39 @@ static inline int set_dabr(struct arch_hw_breakpoint *brk) return __set_dabr(dabr, dabrx); } +static inline int set_breakpoint_8xx(struct arch_hw_breakpoint *brk) +{ + unsigned long lctrl1 = LCTRL1_CTE_GT | LCTRL1_CTF_LT | LCTRL1_CRWE_RW | + LCTRL1_CRWF_RW; + unsigned long lctrl2 = LCTRL2_LW0EN | LCTRL2_LW0LADC | LCTRL2_SLW0EN; + unsigned long start_addr = brk->address & ~HW_BREAKPOINT_ALIGN; + unsigned long end_addr = (brk->address + brk->len - 1) | HW_BREAKPOINT_ALIGN; + + if (start_addr == 0) + lctrl2 |= LCTRL2_LW0LA_F; + else if (end_addr == ~0U) + lctrl2 |= LCTRL2_LW0LA_E; + else + lctrl2 |= LCTRL2_LW0LA_EandF; + + mtspr(SPRN_LCTRL2, 0); + + if ((brk->type & HW_BRK_TYPE_RDWR) == 0) + return 0; + + if ((brk->type & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_READ) + lctrl1 |= LCTRL1_CRWE_RO | LCTRL1_CRWF_RO; + if ((brk->type & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_WRITE) + lctrl1 |= LCTRL1_CRWE_WO | LCTRL1_CRWF_WO; + + mtspr(SPRN_CMPE, start_addr - 1); + mtspr(SPRN_CMPF, end_addr + 1); + mtspr(SPRN_LCTRL1, lctrl1); + mtspr(SPRN_LCTRL2, lctrl2); + + return 0; +} + void __set_breakpoint(struct arch_hw_breakpoint *brk) { memcpy(this_cpu_ptr(¤t_brk), brk, sizeof(*brk)); @@ -789,6 +800,8 @@ void __set_breakpoint(struct arch_hw_breakpoint *brk) if (dawr_enabled()) // Power8 or later set_dawr(brk); + else if (IS_ENABLED(CONFIG_PPC_8xx)) + set_breakpoint_8xx(brk); else if (!cpu_has_feature(CPU_FTR_ARCH_207S)) // Power7 or earlier set_dabr(brk); -- cgit v1.2.3 From ec0895f08f99515194e9fcfe1338becf6f759d38 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 2 Dec 2019 07:57:30 +0000 Subject: powerpc/vdso32: inline __get_datapage() __get_datapage() is only a few instructions to retrieve the address of the page where the kernel stores data to the VDSO. By inlining this function into its users, a bl/blr pair and a mflr/mtlr pair is avoided, plus a few reg moves. The improvement is noticeable (about 55 nsec/call on an 8xx) vdsotest before the patch: gettimeofday: vdso: 731 nsec/call clock-gettime-realtime-coarse: vdso: 668 nsec/call clock-gettime-monotonic-coarse: vdso: 745 nsec/call vdsotest after the patch: gettimeofday: vdso: 677 nsec/call clock-gettime-realtime-coarse: vdso: 613 nsec/call clock-gettime-monotonic-coarse: vdso: 690 nsec/call Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/c39ef7f3dfa25356b01e211d539671f279086c09.1575273217.git.christophe.leroy@c-s.fr --- arch/powerpc/include/asm/vdso_datapage.h | 10 ++++++++++ arch/powerpc/kernel/vdso32/cacheflush.S | 9 ++++----- arch/powerpc/kernel/vdso32/datapage.S | 28 +++------------------------- arch/powerpc/kernel/vdso32/gettimeofday.S | 12 +++++------- 4 files changed, 22 insertions(+), 37 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index 40f13f3626d3..ee5319a6f4e3 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -118,6 +118,16 @@ struct vdso_data { extern struct vdso_data *vdso_data; +#else /* __ASSEMBLY__ */ + +.macro get_datapage ptr, tmp + bcl 20, 31, .+4 + mflr \ptr + addi \ptr, \ptr, (__kernel_datapage_offset - (.-4))@l + lwz \tmp, 0(\ptr) + add \ptr, \tmp, \ptr +.endm + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S index 7f882e7b9f43..d178ec8c279d 100644 --- a/arch/powerpc/kernel/vdso32/cacheflush.S +++ b/arch/powerpc/kernel/vdso32/cacheflush.S @@ -8,6 +8,7 @@ #include #include #include +#include #include .text @@ -24,14 +25,12 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache) .cfi_startproc mflr r12 .cfi_register lr,r12 - mr r11,r3 - bl __get_datapage@local + get_datapage r10, r0 mtlr r12 - mr r10,r3 lwz r7,CFG_DCACHE_BLOCKSZ(r10) addi r5,r7,-1 - andc r6,r11,r5 /* round low to line bdy */ + andc r6,r3,r5 /* round low to line bdy */ subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10) @@ -48,7 +47,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache) lwz r7,CFG_ICACHE_BLOCKSZ(r10) addi r5,r7,-1 - andc r6,r11,r5 /* round low to line bdy */ + andc r6,r3,r5 /* round low to line bdy */ subf r8,r6,r4 /* compute length */ add r8,r8,r5 lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10) diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S index 6c7401bd284e..1095d818f94a 100644 --- a/arch/powerpc/kernel/vdso32/datapage.S +++ b/arch/powerpc/kernel/vdso32/datapage.S @@ -10,35 +10,13 @@ #include #include #include +#include .text .global __kernel_datapage_offset; __kernel_datapage_offset: .long 0 -V_FUNCTION_BEGIN(__get_datapage) - .cfi_startproc - /* We don't want that exposed or overridable as we want other objects - * to be able to bl directly to here - */ - .protected __get_datapage - .hidden __get_datapage - - mflr r0 - .cfi_register lr,r0 - - bcl 20,31,data_page_branch -data_page_branch: - mflr r3 - mtlr r0 - addi r3, r3, __kernel_datapage_offset-data_page_branch - lwz r0,0(r3) - .cfi_restore lr - add r3,r0,r3 - blr - .cfi_endproc -V_FUNCTION_END(__get_datapage) - /* * void *__kernel_get_syscall_map(unsigned int *syscall_count) ; * @@ -53,7 +31,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) mflr r12 .cfi_register lr,r12 mr r4,r3 - bl __get_datapage@local + get_datapage r3, r0 mtlr r12 addi r3,r3,CFG_SYSCALL_MAP32 cmpli cr0,r4,0 @@ -75,7 +53,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq) .cfi_startproc mflr r12 .cfi_register lr,r12 - bl __get_datapage@local + get_datapage r3, r0 lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3) lwz r3,CFG_TB_TICKS_PER_SEC(r3) mtlr r12 diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index e9ce8ee56edb..74973548529a 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -33,8 +34,7 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday) mr r10,r3 /* r10 saves tv */ mr r11,r4 /* r11 saves tz */ - bl __get_datapage@local /* get data page */ - mr r9, r3 /* datapage ptr in r9 */ + get_datapage r9, r0 cmplwi r10,0 /* check if tv is NULL */ beq 3f lis r7,1000000@ha /* load up USEC_PER_SEC */ @@ -80,8 +80,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) mflr r12 /* r12 saves lr */ .cfi_register lr,r12 mr r11,r4 /* r11 saves tp */ - bl __get_datapage@local /* get data page */ - mr r9,r3 /* datapage ptr in r9 */ + get_datapage r9, r0 lis r7,NSEC_PER_SEC@h /* want nanoseconds */ ori r7,r7,NSEC_PER_SEC@l beq cr5, .Lcoarse_clocks @@ -206,7 +205,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) mflr r12 .cfi_register lr,r12 - bl __get_datapage@local /* get data page */ + get_datapage r3, r0 lwz r5, CLOCK_HRTIMER_RES(r3) mtlr r12 li r3,0 @@ -240,8 +239,7 @@ V_FUNCTION_BEGIN(__kernel_time) .cfi_register lr,r12 mr r11,r3 /* r11 holds t */ - bl __get_datapage@local - mr r9, r3 /* datapage ptr in r9 */ + get_datapage r9, r0 lwz r3,STAMP_XTIME_SEC+LOPART(r9) -- cgit v1.2.3 From 2c29eef9fc6f61cfb81b54683be8f116dac80e7a Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 2 Dec 2019 07:57:31 +0000 Subject: powerpc/vdso32: Don't read cache line size from the datapage on PPC32. On PPC32, the cache lines have a fixed size known at build time. Don't read it from the datapage. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/dfa7b35e27e01964fcda84bf1ed8b2b31cf93826.1575273217.git.christophe.leroy@c-s.fr --- arch/powerpc/include/asm/vdso_datapage.h | 4 ---- arch/powerpc/kernel/asm-offsets.c | 2 +- arch/powerpc/kernel/vdso.c | 5 ----- arch/powerpc/kernel/vdso32/cacheflush.S | 23 +++++++++++++++++++++++ 4 files changed, 24 insertions(+), 10 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index ee5319a6f4e3..b9ef6cf50ea5 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -108,10 +108,6 @@ struct vdso_data { __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */ __u32 hrtimer_res; /* hrtimer resolution */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ - __u32 dcache_block_size; /* L1 d-cache block size */ - __u32 icache_block_size; /* L1 i-cache block size */ - __u32 dcache_log_block_size; /* L1 d-cache log block size */ - __u32 icache_log_block_size; /* L1 i-cache log block size */ }; #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 3d47aec7becf..0013197d89a6 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -389,11 +389,11 @@ int main(void) OFFSET(STAMP_XTIME_NSEC, vdso_data, stamp_xtime_nsec); OFFSET(STAMP_SEC_FRAC, vdso_data, stamp_sec_fraction); OFFSET(CLOCK_HRTIMER_RES, vdso_data, hrtimer_res); +#ifdef CONFIG_PPC64 OFFSET(CFG_ICACHE_BLOCKSZ, vdso_data, icache_block_size); OFFSET(CFG_DCACHE_BLOCKSZ, vdso_data, dcache_block_size); OFFSET(CFG_ICACHE_LOGBLOCKSZ, vdso_data, icache_log_block_size); OFFSET(CFG_DCACHE_LOGBLOCKSZ, vdso_data, dcache_log_block_size); -#ifdef CONFIG_PPC64 OFFSET(CFG_SYSCALL_MAP64, vdso_data, syscall_map_64); OFFSET(TVAL64_TV_SEC, __kernel_old_timeval, tv_sec); OFFSET(TVAL64_TV_USEC, __kernel_old_timeval, tv_usec); diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index eae9ddaecbcf..b9a108411c0d 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -728,11 +728,6 @@ static int __init vdso_init(void) */ vdso64_pages = (&vdso64_end - &vdso64_start) >> PAGE_SHIFT; DBG("vdso64_kbase: %p, 0x%x pages\n", vdso64_kbase, vdso64_pages); -#else - vdso_data->dcache_block_size = L1_CACHE_BYTES; - vdso_data->dcache_log_block_size = L1_CACHE_SHIFT; - vdso_data->icache_block_size = L1_CACHE_BYTES; - vdso_data->icache_log_block_size = L1_CACHE_SHIFT; #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S index d178ec8c279d..3440ddf21c8b 100644 --- a/arch/powerpc/kernel/vdso32/cacheflush.S +++ b/arch/powerpc/kernel/vdso32/cacheflush.S @@ -10,6 +10,7 @@ #include #include #include +#include .text @@ -23,28 +24,44 @@ */ V_FUNCTION_BEGIN(__kernel_sync_dicache) .cfi_startproc +#ifdef CONFIG_PPC64 mflr r12 .cfi_register lr,r12 get_datapage r10, r0 mtlr r12 +#endif +#ifdef CONFIG_PPC64 lwz r7,CFG_DCACHE_BLOCKSZ(r10) addi r5,r7,-1 +#else + li r5, L1_CACHE_BYTES - 1 +#endif andc r6,r3,r5 /* round low to line bdy */ subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ +#ifdef CONFIG_PPC64 lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10) srw. r8,r8,r9 /* compute line count */ +#else + srwi. r8, r8, L1_CACHE_SHIFT + mr r7, r6 +#endif crclr cr0*4+so beqlr /* nothing to do? */ mtctr r8 1: dcbst 0,r6 +#ifdef CONFIG_PPC64 add r6,r6,r7 +#else + addi r6, r6, L1_CACHE_BYTES +#endif bdnz 1b sync /* Now invalidate the instruction cache */ +#ifdef CONFIG_PPC64 lwz r7,CFG_ICACHE_BLOCKSZ(r10) addi r5,r7,-1 andc r6,r3,r5 /* round low to line bdy */ @@ -54,9 +71,15 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache) srw. r8,r8,r9 /* compute line count */ crclr cr0*4+so beqlr /* nothing to do? */ +#endif mtctr r8 +#ifdef CONFIG_PPC64 2: icbi 0,r6 add r6,r6,r7 +#else +2: icbi 0, r7 + addi r7, r7, L1_CACHE_BYTES +#endif bdnz 2b isync li r3,0 -- cgit v1.2.3 From bbb789046084d18fff1a32a7bcdeca36dfa0ac14 Mon Sep 17 00:00:00 2001 From: Frederic Barrat Date: Thu, 21 Nov 2019 14:49:12 +0100 Subject: powerpc/powernv/ioda: Find opencapi slot for a device node Unlike real PCI slots, opencapi slots are directly associated to the (virtual) opencapi PHB, there's no intermediate bridge. So when looking for a slot ID, we must start the search from the device node itself and not its parent. Also, the slot ID is not attached to a specific bdfn, so let's build it from the PHB ID, like skiboot. Signed-off-by: Frederic Barrat Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20191121134918.7155-6-fbarrat@linux.ibm.com --- arch/powerpc/include/asm/pnv-pci.h | 1 + arch/powerpc/platforms/powernv/pci.c | 24 ++++++++++++++---------- 2 files changed, 15 insertions(+), 10 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h index edcb1fc50aeb..d0ee0ede5767 100644 --- a/arch/powerpc/include/asm/pnv-pci.h +++ b/arch/powerpc/include/asm/pnv-pci.h @@ -15,6 +15,7 @@ #define PCI_SLOT_ID_PREFIX (1UL << 63) #define PCI_SLOT_ID(phb_id, bdfn) \ (PCI_SLOT_ID_PREFIX | ((uint64_t)(bdfn) << 16) | (phb_id)) +#define PCI_PHB_SLOT_ID(phb_id) (phb_id) extern int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id); extern int pnv_pci_get_device_tree(uint32_t phandle, void *buf, uint64_t len); diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index e8e58a2cccdd..929e0241d862 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -38,7 +38,7 @@ static DEFINE_MUTEX(tunnel_mutex); int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id) { - struct device_node *parent = np; + struct device_node *node = np; u32 bdfn; u64 phbid; int ret; @@ -48,25 +48,29 @@ int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id) return -ENXIO; bdfn = ((bdfn & 0x00ffff00) >> 8); - while ((parent = of_get_parent(parent))) { - if (!PCI_DN(parent)) { - of_node_put(parent); + for (node = np; node; node = of_get_parent(node)) { + if (!PCI_DN(node)) { + of_node_put(node); break; } - if (!of_device_is_compatible(parent, "ibm,ioda2-phb") && - !of_device_is_compatible(parent, "ibm,ioda3-phb")) { - of_node_put(parent); + if (!of_device_is_compatible(node, "ibm,ioda2-phb") && + !of_device_is_compatible(node, "ibm,ioda3-phb") && + !of_device_is_compatible(node, "ibm,ioda2-npu2-opencapi-phb")) { + of_node_put(node); continue; } - ret = of_property_read_u64(parent, "ibm,opal-phbid", &phbid); + ret = of_property_read_u64(node, "ibm,opal-phbid", &phbid); if (ret) { - of_node_put(parent); + of_node_put(node); return -ENXIO; } - *id = PCI_SLOT_ID(phbid, bdfn); + if (of_device_is_compatible(node, "ibm,ioda2-npu2-opencapi-phb")) + *id = PCI_PHB_SLOT_ID(phbid); + else + *id = PCI_SLOT_ID(phbid, bdfn); return 0; } -- cgit v1.2.3 From 8cd6aacc640116213f9373808a627ecd3728accc Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Wed, 21 Aug 2019 16:26:54 +1000 Subject: powerpc/pcidn: Make VF pci_dn management CONFIG_PCI_IOV specific The powerpc PCI code requires that a pci_dn structure exists for all devices in the system. This is fine for real devices since at boot a pci_dn is created for each PCI device in the DT and it's fine for hotplugged devices since the hotplug slot driver will manage the pci_dn's devices in hotplug slots. For SR-IOV, we need the platform / pcibios to manage the pci_dn for virtual functions since firmware is unaware of VFs, and they aren't "hot plugged" in the traditional sense. Management of the pci_dn is handled by the, poorly named, functions: add_pci_dev_data() and remove_pci_dev_data(). The entire body of these functions is #ifdef`ed around CONFIG_PCI_IOV and they cannot be used in any other context, so make them only available when CONFIG_PCI_IOV is selected, and rename them to reflect their actual usage rather than having them masquerade as generic code. Signed-off-by: Oliver O'Halloran Reviewed-by: Sam Bobroff Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190821062655.19735-2-oohall@gmail.com --- arch/powerpc/include/asm/pci-bridge.h | 7 +++++-- arch/powerpc/kernel/pci_dn.c | 15 +++++---------- arch/powerpc/platforms/powernv/pci-ioda.c | 4 ++-- arch/powerpc/platforms/pseries/pci.c | 4 ++-- 4 files changed, 14 insertions(+), 16 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index ea6ec65970ef..69f4cb3b7c56 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -223,12 +223,15 @@ struct pci_dn { extern struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus, int devfn); extern struct pci_dn *pci_get_pdn(struct pci_dev *pdev); -extern struct pci_dn *add_dev_pci_data(struct pci_dev *pdev); -extern void remove_dev_pci_data(struct pci_dev *pdev); extern struct pci_dn *pci_add_device_node_info(struct pci_controller *hose, struct device_node *dn); extern void pci_remove_device_node_info(struct device_node *dn); +#ifdef CONFIG_PCI_IOV +struct pci_dn *add_sriov_vf_pdns(struct pci_dev *pdev); +void remove_sriov_vf_pdns(struct pci_dev *pdev); +#endif + static inline int pci_device_from_OF_node(struct device_node *np, u8 *bus, u8 *devfn) { diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index d876eda92609..c158ac897efb 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -125,7 +125,7 @@ struct pci_dn *pci_get_pdn(struct pci_dev *pdev) } #ifdef CONFIG_PCI_IOV -static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent, +static struct pci_dn *add_one_sriov_vf_pdn(struct pci_dn *parent, int vf_index, int busno, int devfn) { @@ -151,11 +151,9 @@ static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent, return pdn; } -#endif -struct pci_dn *add_dev_pci_data(struct pci_dev *pdev) +struct pci_dn *add_sriov_vf_pdns(struct pci_dev *pdev) { -#ifdef CONFIG_PCI_IOV struct pci_dn *parent, *pdn; int i; @@ -176,7 +174,7 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev) for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) { struct eeh_dev *edev __maybe_unused; - pdn = add_one_dev_pci_data(parent, i, + pdn = add_one_sriov_vf_pdn(parent, i, pci_iov_virtfn_bus(pdev, i), pci_iov_virtfn_devfn(pdev, i)); if (!pdn) { @@ -192,14 +190,11 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev) edev->physfn = pdev; #endif /* CONFIG_EEH */ } -#endif /* CONFIG_PCI_IOV */ - return pci_get_pdn(pdev); } -void remove_dev_pci_data(struct pci_dev *pdev) +void remove_sriov_vf_pdns(struct pci_dev *pdev) { -#ifdef CONFIG_PCI_IOV struct pci_dn *parent; struct pci_dn *pdn, *tmp; int i; @@ -271,8 +266,8 @@ void remove_dev_pci_data(struct pci_dev *pdev) kfree(pdn); } } -#endif /* CONFIG_PCI_IOV */ } +#endif /* CONFIG_PCI_IOV */ struct pci_dn *pci_add_device_node_info(struct pci_controller *hose, struct device_node *dn) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index e41d38299ae9..d178c572c474 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1747,14 +1747,14 @@ int pnv_pcibios_sriov_disable(struct pci_dev *pdev) pnv_pci_sriov_disable(pdev); /* Release PCI data */ - remove_dev_pci_data(pdev); + remove_sriov_vf_pdns(pdev); return 0; } int pnv_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs) { /* Allocate PCI data */ - add_dev_pci_data(pdev); + add_sriov_vf_pdns(pdev); return pnv_pci_sriov_enable(pdev, num_vfs); } diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index 722830978639..911534b89c85 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -192,7 +192,7 @@ int pseries_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs) int pseries_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs) { /* Allocate PCI data */ - add_dev_pci_data(pdev); + add_sriov_vf_pdns(pdev); return pseries_pci_sriov_enable(pdev, num_vfs); } @@ -204,7 +204,7 @@ int pseries_pcibios_sriov_disable(struct pci_dev *pdev) /* Releasing pe_num_map */ kfree(pdn->pe_num_map); /* Release PCI data */ - remove_dev_pci_data(pdev); + remove_sriov_vf_pdns(pdev); pci_vf_drivers_autoprobe(pdev, true); return 0; } -- cgit v1.2.3 From b059c63620fbba8a5da60f01d99d003681447e3c Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Fri, 15 Nov 2019 19:10:58 +0100 Subject: powerpc/xive: Drop extern qualifiers from header function prototypes As reported by ./scripts/checkpatch.pl --strict: CHECK: extern prototypes should be avoided in .h files Signed-off-by: Greg Kurz Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/157384145834.181768.944827793193636924.stgit@bahia.lan --- arch/powerpc/include/asm/xive.h | 92 ++++++++++++++++++++--------------------- 1 file changed, 46 insertions(+), 46 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h index 24cdf97376c4..93f982dbb3d4 100644 --- a/arch/powerpc/include/asm/xive.h +++ b/arch/powerpc/include/asm/xive.h @@ -87,56 +87,56 @@ extern bool __xive_enabled; static inline bool xive_enabled(void) { return __xive_enabled; } -extern bool xive_spapr_init(void); -extern bool xive_native_init(void); -extern void xive_smp_probe(void); -extern int xive_smp_prepare_cpu(unsigned int cpu); -extern void xive_smp_setup_cpu(void); -extern void xive_smp_disable_cpu(void); -extern void xive_teardown_cpu(void); -extern void xive_shutdown(void); -extern void xive_flush_interrupt(void); +bool xive_spapr_init(void); +bool xive_native_init(void); +void xive_smp_probe(void); +int xive_smp_prepare_cpu(unsigned int cpu); +void xive_smp_setup_cpu(void); +void xive_smp_disable_cpu(void); +void xive_teardown_cpu(void); +void xive_shutdown(void); +void xive_flush_interrupt(void); /* xmon hook */ -extern void xmon_xive_do_dump(int cpu); -extern int xmon_xive_get_irq_config(u32 hw_irq, struct irq_data *d); +void xmon_xive_do_dump(int cpu); +int xmon_xive_get_irq_config(u32 hw_irq, struct irq_data *d); /* APIs used by KVM */ -extern u32 xive_native_default_eq_shift(void); -extern u32 xive_native_alloc_vp_block(u32 max_vcpus); -extern void xive_native_free_vp_block(u32 vp_base); -extern int xive_native_populate_irq_data(u32 hw_irq, - struct xive_irq_data *data); -extern void xive_cleanup_irq_data(struct xive_irq_data *xd); -extern u32 xive_native_alloc_irq(void); -extern void xive_native_free_irq(u32 irq); -extern int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq); - -extern int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio, - __be32 *qpage, u32 order, bool can_escalate); -extern void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio); - -extern void xive_native_sync_source(u32 hw_irq); -extern void xive_native_sync_queue(u32 hw_irq); -extern bool is_xive_irq(struct irq_chip *chip); -extern int xive_native_enable_vp(u32 vp_id, bool single_escalation); -extern int xive_native_disable_vp(u32 vp_id); -extern int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id); -extern bool xive_native_has_single_escalation(void); - -extern int xive_native_get_queue_info(u32 vp_id, uint32_t prio, - u64 *out_qpage, - u64 *out_qsize, - u64 *out_qeoi_page, - u32 *out_escalate_irq, - u64 *out_qflags); - -extern int xive_native_get_queue_state(u32 vp_id, uint32_t prio, u32 *qtoggle, - u32 *qindex); -extern int xive_native_set_queue_state(u32 vp_id, uint32_t prio, u32 qtoggle, - u32 qindex); -extern int xive_native_get_vp_state(u32 vp_id, u64 *out_state); -extern bool xive_native_has_queue_state_support(void); +u32 xive_native_default_eq_shift(void); +u32 xive_native_alloc_vp_block(u32 max_vcpus); +void xive_native_free_vp_block(u32 vp_base); +int xive_native_populate_irq_data(u32 hw_irq, + struct xive_irq_data *data); +void xive_cleanup_irq_data(struct xive_irq_data *xd); +u32 xive_native_alloc_irq(void); +void xive_native_free_irq(u32 irq); +int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq); + +int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio, + __be32 *qpage, u32 order, bool can_escalate); +void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio); + +void xive_native_sync_source(u32 hw_irq); +void xive_native_sync_queue(u32 hw_irq); +bool is_xive_irq(struct irq_chip *chip); +int xive_native_enable_vp(u32 vp_id, bool single_escalation); +int xive_native_disable_vp(u32 vp_id); +int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id); +bool xive_native_has_single_escalation(void); + +int xive_native_get_queue_info(u32 vp_id, uint32_t prio, + u64 *out_qpage, + u64 *out_qsize, + u64 *out_qeoi_page, + u32 *out_escalate_irq, + u64 *out_qflags); + +int xive_native_get_queue_state(u32 vp_id, uint32_t prio, u32 *qtoggle, + u32 *qindex); +int xive_native_set_queue_state(u32 vp_id, uint32_t prio, u32 qtoggle, + u32 qindex); +int xive_native_get_vp_state(u32 vp_id, u64 *out_state); +bool xive_native_has_queue_state_support(void); #else -- cgit v1.2.3 From 736bcdd3a9fc672af33fb83230ecd0570ec38ec6 Mon Sep 17 00:00:00 2001 From: Jordan Niethe Date: Fri, 6 Dec 2019 14:17:22 +1100 Subject: powerpc/mm: Remove kvm radix prefetch workaround for Power9 DD2.2 Commit a25bd72badfa ("powerpc/mm/radix: Workaround prefetch issue with KVM") introduced a number of workarounds as coming out of a guest with the mmu enabled would make the cpu would start running in hypervisor state with the PID value from the guest. The cpu will then start prefetching for the hypervisor with that PID value. In Power9 DD2.2 the cpu behaviour was modified to fix this. When accessing Quadrant 0 in hypervisor mode with LPID != 0 prefetching will not be performed. This means that we can get rid of the workarounds for Power9 DD2.2 and later revisions. Add a new cpu feature CPU_FTR_P9_RADIX_PREFETCH_BUG to indicate if the workarounds are needed. Signed-off-by: Jordan Niethe Acked-by: Paul Mackerras Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20191206031722.25781-1-jniethe5@gmail.com --- arch/powerpc/include/asm/cputable.h | 7 +++++-- arch/powerpc/kernel/dt_cpu_ftrs.c | 13 ++++++++----- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 2 ++ arch/powerpc/mm/book3s64/radix_pgtable.c | 6 +++++- arch/powerpc/mm/book3s64/radix_tlb.c | 3 +++ 5 files changed, 23 insertions(+), 8 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index cf00ff0d121d..40a4d3c6fd99 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -212,6 +212,7 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_P9_TLBIE_STQ_BUG LONG_ASM_CONST(0x0000400000000000) #define CPU_FTR_P9_TIDR LONG_ASM_CONST(0x0000800000000000) #define CPU_FTR_P9_TLBIE_ERAT_BUG LONG_ASM_CONST(0x0001000000000000) +#define CPU_FTR_P9_RADIX_PREFETCH_BUG LONG_ASM_CONST(0x0002000000000000) #ifndef __ASSEMBLY__ @@ -459,8 +460,10 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \ CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_PKEY | \ CPU_FTR_P9_TLBIE_STQ_BUG | CPU_FTR_P9_TLBIE_ERAT_BUG | CPU_FTR_P9_TIDR) -#define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9 -#define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1) +#define CPU_FTRS_POWER9_DD2_0 (CPU_FTRS_POWER9 | CPU_FTR_P9_RADIX_PREFETCH_BUG) +#define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | \ + CPU_FTR_P9_RADIX_PREFETCH_BUG | \ + CPU_FTR_POWER9_DD2_1) #define CPU_FTRS_POWER9_DD2_2 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1 | \ CPU_FTR_P9_TM_HV_ASSIST | \ CPU_FTR_P9_TM_XER_SO_BUG) diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 180b3a5d1001..182b4047c1ef 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -727,17 +727,20 @@ static __init void cpufeatures_cpu_quirks(void) /* * Not all quirks can be derived from the cpufeatures device tree. */ - if ((version & 0xffffefff) == 0x004e0200) - ; /* DD2.0 has no feature flag */ - else if ((version & 0xffffefff) == 0x004e0201) + if ((version & 0xffffefff) == 0x004e0200) { + /* DD2.0 has no feature flag */ + cur_cpu_spec->cpu_features |= CPU_FTR_P9_RADIX_PREFETCH_BUG; + } else if ((version & 0xffffefff) == 0x004e0201) { cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; - else if ((version & 0xffffefff) == 0x004e0202) { + cur_cpu_spec->cpu_features |= CPU_FTR_P9_RADIX_PREFETCH_BUG; + } else if ((version & 0xffffefff) == 0x004e0202) { cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST; cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG; cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; - } else if ((version & 0xffff0000) == 0x004e0000) + } else if ((version & 0xffff0000) == 0x004e0000) { /* DD2.1 and up have DD2_1 */ cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; + } if ((version & 0xffff0000) == 0x004e0000) { cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index c6fbbd29bd87..dbc2fecc37f0 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1801,6 +1801,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) tlbsync ptesync +BEGIN_FTR_SECTION /* Radix: Handle the case where the guest used an illegal PID */ LOAD_REG_ADDR(r4, mmu_base_pid) lwz r3, VCPU_GUEST_PID(r9) @@ -1830,6 +1831,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) addi r7,r7,0x1000 bdnz 1b ptesync +END_FTR_SECTION_IFSET(CPU_FTR_P9_RADIX_PREFETCH_BUG) 2: #endif /* CONFIG_PPC_RADIX_MMU */ diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 974109bb85db..dd1bea45325c 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -337,7 +337,11 @@ static void __init radix_init_pgtable(void) } /* Find out how many PID bits are supported */ - if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) { + if (!mmu_pid_bits) + mmu_pid_bits = 20; + mmu_base_pid = 1; + } else if (cpu_has_feature(CPU_FTR_HVMODE)) { if (!mmu_pid_bits) mmu_pid_bits = 20; #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index a95175c0972b..03f43c924e00 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -1161,6 +1161,9 @@ extern void radix_kvm_prefetch_workaround(struct mm_struct *mm) if (unlikely(pid == MMU_NO_CONTEXT)) return; + if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) + return; + /* * If this context hasn't run on that CPU before and KVM is * around, there's a slim chance that the guest on another -- cgit v1.2.3 From 028474876f472c3b6eee633aed528a1206609657 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:27 +0000 Subject: powerpc/32: prepare for CONFIG_VMAP_STACK To support CONFIG_VMAP_STACK, the kernel has to activate Data MMU Translation for accessing the stack. Before doing that it must save SRR0, SRR1 and also DAR and DSISR when relevant, in order to not loose them in case there is a Data TLB Miss once the translation is reactivated. This patch adds fields in thread struct for saving those registers. It prepares entry_32.S to handle exception entry with Data MMU Translation enabled and alters EXCEPTION_PROLOG macros to save SRR0, SRR1, DAR and DSISR then reenables Data MMU. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/a775a1fea60f190e0f63503463fb775310a2009b.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/include/asm/processor.h | 6 ++ arch/powerpc/include/asm/thread_info.h | 5 ++ arch/powerpc/kernel/asm-offsets.c | 6 ++ arch/powerpc/kernel/entry_32.S | 4 +- arch/powerpc/kernel/head_32.h | 128 +++++++++++++++++++++++++++++---- 5 files changed, 133 insertions(+), 16 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index e114eb36721c..8387698bd5b6 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -162,6 +162,12 @@ struct thread_struct { #endif #if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP) unsigned long kuap; /* opened segments for user access */ +#endif +#ifdef CONFIG_VMAP_STACK + unsigned long srr0; + unsigned long srr1; + unsigned long dar; + unsigned long dsisr; #endif /* Debug Registers */ struct debug_reg debug; diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 8e1d0195ac36..488d5c4670ff 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -10,10 +10,15 @@ #define _ASM_POWERPC_THREAD_INFO_H #include +#include #ifdef __KERNEL__ +#if defined(CONFIG_VMAP_STACK) && CONFIG_THREAD_SHIFT < PAGE_SHIFT +#define THREAD_SHIFT PAGE_SHIFT +#else #define THREAD_SHIFT CONFIG_THREAD_SHIFT +#endif #define THREAD_SIZE (1 << THREAD_SHIFT) diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 90e53d432f2e..c25e562f1cd9 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -127,6 +127,12 @@ int main(void) OFFSET(KSP_VSID, thread_struct, ksp_vsid); #else /* CONFIG_PPC64 */ OFFSET(PGDIR, thread_struct, pgdir); +#ifdef CONFIG_VMAP_STACK + OFFSET(SRR0, thread_struct, srr0); + OFFSET(SRR1, thread_struct, srr1); + OFFSET(DAR, thread_struct, dar); + OFFSET(DSISR, thread_struct, dsisr); +#endif #ifdef CONFIG_SPE OFFSET(THREAD_EVR0, thread_struct, evr[0]); OFFSET(THREAD_ACC, thread_struct, acc); diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 317ad9df8ba8..8f6617cf2689 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -140,6 +140,7 @@ transfer_to_handler: stw r12,_CTR(r11) stw r2,_XER(r11) mfspr r12,SPRN_SPRG_THREAD + tovirt_vmstack r12, r12 beq 2f /* if from user, fix up THREAD.regs */ addi r2, r12, -THREAD addi r11,r1,STACK_FRAME_OVERHEAD @@ -195,7 +196,8 @@ transfer_to_handler: transfer_to_handler_cont: 3: mflr r9 - tovirt(r2, r2) /* set r2 to current */ + tovirt_novmstack r2, r2 /* set r2 to current */ + tovirt_vmstack r9, r9 lwz r11,0(r9) /* virtual address of handler */ lwz r9,4(r9) /* where to go when done */ #if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS) diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index f19a1ab91fb5..e36987aede86 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -10,31 +10,54 @@ * We assume sprg3 has the physical address of the current * task's thread_struct. */ -.macro EXCEPTION_PROLOG - EXCEPTION_PROLOG_0 +.macro EXCEPTION_PROLOG handle_dar_dsisr=0 + EXCEPTION_PROLOG_0 handle_dar_dsisr=\handle_dar_dsisr EXCEPTION_PROLOG_1 - EXCEPTION_PROLOG_2 + EXCEPTION_PROLOG_2 handle_dar_dsisr=\handle_dar_dsisr .endm -.macro EXCEPTION_PROLOG_0 +.macro EXCEPTION_PROLOG_0 handle_dar_dsisr=0 mtspr SPRN_SPRG_SCRATCH0,r10 mtspr SPRN_SPRG_SCRATCH1,r11 +#ifdef CONFIG_VMAP_STACK + mfspr r10, SPRN_SPRG_THREAD + .if \handle_dar_dsisr + mfspr r11, SPRN_DAR + stw r11, DAR(r10) + mfspr r11, SPRN_DSISR + stw r11, DSISR(r10) + .endif + mfspr r11, SPRN_SRR0 + stw r11, SRR0(r10) +#endif mfspr r11, SPRN_SRR1 /* check whether user or kernel */ +#ifdef CONFIG_VMAP_STACK + stw r11, SRR1(r10) +#endif mfcr r10 andi. r11, r11, MSR_PR .endm .macro EXCEPTION_PROLOG_1 +#ifdef CONFIG_VMAP_STACK + li r11, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */ + mtmsr r11 + isync + subi r11, r1, INT_FRAME_SIZE /* use r1 if kernel */ +#else tophys(r11,r1) /* use tophys(r1) if kernel */ + subi r11, r11, INT_FRAME_SIZE /* alloc exc. frame */ +#endif beq 1f mfspr r11,SPRN_SPRG_THREAD + tovirt_vmstack r11, r11 lwz r11,TASK_STACK-THREAD(r11) - addi r11,r11,THREAD_SIZE - tophys(r11,r11) -1: subi r11,r11,INT_FRAME_SIZE /* alloc exc. frame */ + addi r11, r11, THREAD_SIZE - INT_FRAME_SIZE + tophys_novmstack r11, r11 +1: .endm -.macro EXCEPTION_PROLOG_2 +.macro EXCEPTION_PROLOG_2 handle_dar_dsisr=0 stw r10,_CCR(r11) /* save registers */ stw r12,GPR12(r11) stw r9,GPR9(r11) @@ -44,15 +67,32 @@ stw r12,GPR11(r11) mflr r10 stw r10,_LINK(r11) +#ifdef CONFIG_VMAP_STACK + mfspr r12, SPRN_SPRG_THREAD + tovirt(r12, r12) + .if \handle_dar_dsisr + lwz r10, DAR(r12) + stw r10, _DAR(r11) + lwz r10, DSISR(r12) + stw r10, _DSISR(r11) + .endif + lwz r9, SRR1(r12) + lwz r12, SRR0(r12) +#else mfspr r12,SPRN_SRR0 mfspr r9,SPRN_SRR1 +#endif stw r1,GPR1(r11) stw r1,0(r11) - tovirt(r1,r11) /* set new kernel sp */ + tovirt_novmstack r1, r11 /* set new kernel sp */ #ifdef CONFIG_40x rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */ +#else +#ifdef CONFIG_VMAP_STACK + li r10, MSR_KERNEL & ~MSR_IR /* can take exceptions */ #else li r10,MSR_KERNEL & ~(MSR_IR|MSR_DR) /* can take exceptions */ +#endif mtmsr r10 /* (except for mach check in rtas) */ #endif stw r0,GPR0(r11) @@ -65,24 +105,45 @@ .macro SYSCALL_ENTRY trapno mfspr r12,SPRN_SPRG_THREAD +#ifdef CONFIG_VMAP_STACK + mfspr r9, SPRN_SRR0 + mfspr r11, SPRN_SRR1 + stw r9, SRR0(r12) + stw r11, SRR1(r12) +#endif mfcr r10 lwz r11,TASK_STACK-THREAD(r12) - mflr r9 - addi r11,r11,THREAD_SIZE - INT_FRAME_SIZE rlwinm r10,r10,0,4,2 /* Clear SO bit in CR */ - tophys(r11,r11) + addi r11, r11, THREAD_SIZE - INT_FRAME_SIZE +#ifdef CONFIG_VMAP_STACK + li r9, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */ + mtmsr r9 + isync +#endif + tovirt_vmstack r12, r12 + tophys_novmstack r11, r11 + mflr r9 stw r10,_CCR(r11) /* save registers */ + stw r9, _LINK(r11) +#ifdef CONFIG_VMAP_STACK + lwz r10, SRR0(r12) + lwz r9, SRR1(r12) +#else mfspr r10,SPRN_SRR0 - stw r9,_LINK(r11) mfspr r9,SPRN_SRR1 +#endif stw r1,GPR1(r11) stw r1,0(r11) - tovirt(r1,r11) /* set new kernel sp */ + tovirt_novmstack r1, r11 /* set new kernel sp */ stw r10,_NIP(r11) #ifdef CONFIG_40x rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */ +#else +#ifdef CONFIG_VMAP_STACK + LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~MSR_IR) /* can take exceptions */ #else LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~(MSR_IR|MSR_DR)) /* can take exceptions */ +#endif mtmsr r10 /* (except for mach check in rtas) */ #endif lis r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */ @@ -121,7 +182,7 @@ #endif 3: - tovirt(r2, r2) /* set r2 to current */ + tovirt_novmstack r2, r2 /* set r2 to current */ lis r11, transfer_to_syscall@h ori r11, r11, transfer_to_syscall@l #ifdef CONFIG_TRACE_IRQFLAGS @@ -145,14 +206,51 @@ .endm .macro save_dar_dsisr_on_stack reg1, reg2, sp +#ifndef CONFIG_VMAP_STACK mfspr \reg1, SPRN_DAR mfspr \reg2, SPRN_DSISR stw \reg1, _DAR(\sp) stw \reg2, _DSISR(\sp) +#endif .endm .macro get_and_save_dar_dsisr_on_stack reg1, reg2, sp +#ifdef CONFIG_VMAP_STACK + lwz \reg1, _DAR(\sp) + lwz \reg2, _DSISR(\sp) +#else save_dar_dsisr_on_stack \reg1, \reg2, \sp +#endif +.endm + +.macro tovirt_vmstack dst, src +#ifdef CONFIG_VMAP_STACK + tovirt(\dst, \src) +#else + .ifnc \dst, \src + mr \dst, \src + .endif +#endif +.endm + +.macro tovirt_novmstack dst, src +#ifndef CONFIG_VMAP_STACK + tovirt(\dst, \src) +#else + .ifnc \dst, \src + mr \dst, \src + .endif +#endif +.endm + +.macro tophys_novmstack dst, src +#ifndef CONFIG_VMAP_STACK + tophys(\dst, \src) +#else + .ifnc \dst, \src + mr \dst, \src + .endif +#endif .endm /* -- cgit v1.2.3 From 63289e7d3a645a4291ec43c1d526dd4a811da1a0 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:28 +0000 Subject: powerpc: align stack to 2 * THREAD_SIZE with VMAP_STACK In order to ease stack overflow detection, align stack to 2 * THREAD_SIZE when using VMAP_STACK. This allows overflow detection using a single bit check. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/60e9ae86b7d2cdcf21468787076d345663648f46.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/include/asm/thread_info.h | 13 +++++++++++++ arch/powerpc/kernel/setup_32.c | 2 +- arch/powerpc/kernel/setup_64.c | 2 +- arch/powerpc/kernel/vmlinux.lds.S | 2 +- 4 files changed, 16 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 488d5c4670ff..a2270749b282 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -22,6 +22,19 @@ #define THREAD_SIZE (1 << THREAD_SHIFT) +/* + * By aligning VMAP'd stacks to 2 * THREAD_SIZE, we can detect overflow by + * checking sp & (1 << THREAD_SHIFT), which we can do cheaply in the entry + * assembly. + */ +#ifdef CONFIG_VMAP_STACK +#define THREAD_ALIGN_SHIFT (THREAD_SHIFT + 1) +#else +#define THREAD_ALIGN_SHIFT THREAD_SHIFT +#endif + +#define THREAD_ALIGN (1 << THREAD_ALIGN_SHIFT) + #ifndef __ASSEMBLY__ #include #include diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index dcffe927f5b9..f014c4f7a337 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -140,7 +140,7 @@ arch_initcall(ppc_init); static void *__init alloc_stack(void) { - void *ptr = memblock_alloc(THREAD_SIZE, THREAD_SIZE); + void *ptr = memblock_alloc(THREAD_SIZE, THREAD_ALIGN); if (!ptr) panic("cannot allocate %d bytes for stack at %pS\n", diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 6104917a282d..e05e6dd67ae6 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -633,7 +633,7 @@ static void *__init alloc_stack(unsigned long limit, int cpu) BUILD_BUG_ON(STACK_INT_FRAME_SIZE % 16); - ptr = memblock_alloc_try_nid(THREAD_SIZE, THREAD_SIZE, + ptr = memblock_alloc_try_nid(THREAD_SIZE, THREAD_ALIGN, MEMBLOCK_LOW_LIMIT, limit, early_cpu_to_node(cpu)); if (!ptr) diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 8834220036a5..b4c89a1acebb 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -323,7 +323,7 @@ SECTIONS #endif /* The initial task and kernel stack */ - INIT_TASK_DATA_SECTION(THREAD_SIZE) + INIT_TASK_DATA_SECTION(THREAD_ALIGN) .data..page_aligned : AT(ADDR(.data..page_aligned) - LOAD_OFFSET) { PAGE_ALIGNED_DATA(PAGE_SIZE) -- cgit v1.2.3 From 3d4247fcc938d0ab5cf6fdb752dae07fdeab9736 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 14 Jan 2020 17:54:00 +0000 Subject: powerpc/32: Add support of KASAN_VMALLOC Add support of KASAN_VMALLOC on PPC32. To allow this, the early shadow covering the VMALLOC space need to be removed once high_memory var is set and before freeing memblock. And the VMALLOC area need to be aligned such that boundaries are covered by a full shadow page. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/031dec5487bde9b2181c8b3c9800e1879cf98c1a.1579024426.git.christophe.leroy@c-s.fr --- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/book3s/32/pgtable.h | 5 +++++ arch/powerpc/include/asm/kasan.h | 2 ++ arch/powerpc/include/asm/nohash/32/pgtable.h | 5 +++++ arch/powerpc/mm/kasan/kasan_init_32.c | 33 +++++++++++++++++++++++++++- arch/powerpc/mm/mem.c | 4 ++++ 6 files changed, 49 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 6093c48976bf..a7f10a1b79f7 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -173,6 +173,7 @@ config PPC select HAVE_ARCH_HUGE_VMAP if PPC_BOOK3S_64 && PPC_RADIX_MMU select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_KASAN if PPC32 + select HAVE_ARCH_KASAN_VMALLOC if PPC32 select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 0796533d37dd..5b39c11e884a 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -193,7 +193,12 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); #else #define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))) #endif + +#ifdef CONFIG_KASAN_VMALLOC +#define VMALLOC_END _ALIGN_DOWN(ioremap_bot, PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) +#else #define VMALLOC_END ioremap_bot +#endif #ifndef __ASSEMBLY__ #include diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h index 296e51c2f066..fbff9ff9032e 100644 --- a/arch/powerpc/include/asm/kasan.h +++ b/arch/powerpc/include/asm/kasan.h @@ -31,9 +31,11 @@ void kasan_early_init(void); void kasan_mmu_init(void); void kasan_init(void); +void kasan_late_init(void); #else static inline void kasan_init(void) { } static inline void kasan_mmu_init(void) { } +static inline void kasan_late_init(void) { } #endif #endif /* __ASSEMBLY */ diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 552b96eef0c8..60c4d829152e 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -114,7 +114,12 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); #else #define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))) #endif + +#ifdef CONFIG_KASAN_VMALLOC +#define VMALLOC_END _ALIGN_DOWN(ioremap_bot, PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) +#else #define VMALLOC_END ioremap_bot +#endif /* * Bits in a linux-style PTE. These match the bits in the diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index 0e6ed4413eea..88036fb88350 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -129,6 +129,31 @@ static void __init kasan_remap_early_shadow_ro(void) flush_tlb_kernel_range(KASAN_SHADOW_START, KASAN_SHADOW_END); } +static void __init kasan_unmap_early_shadow_vmalloc(void) +{ + unsigned long k_start = (unsigned long)kasan_mem_to_shadow((void *)VMALLOC_START); + unsigned long k_end = (unsigned long)kasan_mem_to_shadow((void *)VMALLOC_END); + unsigned long k_cur; + phys_addr_t pa = __pa(kasan_early_shadow_page); + + if (!early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) { + int ret = kasan_init_shadow_page_tables(k_start, k_end); + + if (ret) + panic("kasan: kasan_init_shadow_page_tables() failed"); + } + for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) { + pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur); + pte_t *ptep = pte_offset_kernel(pmd, k_cur); + + if ((pte_val(*ptep) & PTE_RPN_MASK) != pa) + continue; + + __set_pte_at(&init_mm, k_cur, ptep, __pte(0), 0); + } + flush_tlb_kernel_range(k_start, k_end); +} + void __init kasan_mmu_init(void) { int ret; @@ -165,7 +190,13 @@ void __init kasan_init(void) pr_info("KASAN init done\n"); } -#ifdef CONFIG_MODULES +void __init kasan_late_init(void) +{ + if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) + kasan_unmap_early_shadow_vmalloc(); +} + +#if defined(CONFIG_MODULES) && !defined(CONFIG_KASAN_VMALLOC) void *module_alloc(unsigned long size) { void *base; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index f5535eae637f..ef7b1119b2e2 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -49,6 +49,7 @@ #include #include #include +#include #include @@ -301,6 +302,9 @@ void __init mem_init(void) high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); set_max_mapnr(max_pfn); + + kasan_late_init(); + memblock_free_all(); #ifdef CONFIG_HIGHMEM -- cgit v1.2.3 From 6ec20aa2e510b6297906c45f009aa08b2d97269a Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 24 Jan 2020 11:54:40 +0000 Subject: powerpc/32s: Fix bad_kuap_fault() At the moment, bad_kuap_fault() reports a fault only if a bad access to userspace occurred while access to userspace was not granted. But if a fault occurs for a write outside the allowed userspace segment(s) that have been unlocked, bad_kuap_fault() fails to detect it and the kernel loops forever in do_page_fault(). Fix it by checking that the accessed address is within the allowed range. Fixes: a68c31fc01ef ("powerpc/32s: Implement Kernel Userspace Access Protection") Cc: stable@vger.kernel.org # v5.2+ Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/f48244e9485ada0a304ed33ccbb8da271180c80d.1579866752.git.christophe.leroy@c-s.fr --- arch/powerpc/include/asm/book3s/32/kup.h | 9 +++++++-- arch/powerpc/include/asm/book3s/64/kup-radix.h | 3 ++- arch/powerpc/include/asm/kup.h | 6 +++++- arch/powerpc/include/asm/nohash/32/kup-8xx.h | 3 ++- arch/powerpc/mm/fault.c | 2 +- 5 files changed, 17 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index f9dc597b0b86..d88008c8eb85 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -131,12 +131,17 @@ static inline void prevent_user_access(void __user *to, const void __user *from, kuap_update_sr(mfsrin(addr) | SR_KS, addr, end); /* set Ks */ } -static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { + unsigned long begin = regs->kuap & 0xf0000000; + unsigned long end = regs->kuap << 28; + if (!is_write) return false; - return WARN(!regs->kuap, "Bug: write fault blocked by segment registers !"); + return WARN(address < begin || address >= end, + "Bug: write fault blocked by segment registers !"); } #endif /* CONFIG_PPC_KUAP */ diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h index f254de956d6a..dbbd22cb80f5 100644 --- a/arch/powerpc/include/asm/book3s/64/kup-radix.h +++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h @@ -95,7 +95,8 @@ static inline void prevent_user_access(void __user *to, const void __user *from, set_kuap(AMR_KUAP_BLOCKED); } -static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) && (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)), diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h index 5b5e39643a27..812e66f31934 100644 --- a/arch/powerpc/include/asm/kup.h +++ b/arch/powerpc/include/asm/kup.h @@ -45,7 +45,11 @@ static inline void allow_user_access(void __user *to, const void __user *from, unsigned long size) { } static inline void prevent_user_access(void __user *to, const void __user *from, unsigned long size) { } -static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) { return false; } +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + return false; +} #endif /* CONFIG_PPC_KUAP */ static inline void allow_read_from_user(const void __user *from, unsigned long size) diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h index 1006a427e99c..f2fea603b929 100644 --- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h @@ -46,7 +46,8 @@ static inline void prevent_user_access(void __user *to, const void __user *from, mtspr(SPRN_MD_AP, MD_APG_KUAP); } -static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xf0000000), "Bug: fault blocked by AP register !"); diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index b5047f9b5dec..1baeb045f7f4 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -233,7 +233,7 @@ static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code, // Read/write fault in a valid region (the exception table search passed // above), but blocked by KUAP is bad, it can never succeed. - if (bad_kuap_fault(regs, is_write)) + if (bad_kuap_fault(regs, address, is_write)) return true; // What's left? Kernel fault on user in well defined regions (extable -- cgit v1.2.3 From 1d8f739b07bd538f272f60bf53f10e7e6248d295 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 24 Jan 2020 11:54:41 +0000 Subject: powerpc/kuap: Fix set direction in allow/prevent_user_access() __builtin_constant_p() always return 0 for pointers, so on RADIX we always end up opening both direction (by writing 0 in SPR29): 0000000000000170 <._copy_to_user>: ... 1b0: 4c 00 01 2c isync 1b4: 39 20 00 00 li r9,0 1b8: 7d 3d 03 a6 mtspr 29,r9 1bc: 4c 00 01 2c isync 1c0: 48 00 00 01 bl 1c0 <._copy_to_user+0x50> 1c0: R_PPC64_REL24 .__copy_tofrom_user ... 0000000000000220 <._copy_from_user>: ... 2ac: 4c 00 01 2c isync 2b0: 39 20 00 00 li r9,0 2b4: 7d 3d 03 a6 mtspr 29,r9 2b8: 4c 00 01 2c isync 2bc: 7f c5 f3 78 mr r5,r30 2c0: 7f 83 e3 78 mr r3,r28 2c4: 48 00 00 01 bl 2c4 <._copy_from_user+0xa4> 2c4: R_PPC64_REL24 .__copy_tofrom_user ... Use an explicit parameter for direction selection, so that GCC is able to see it is a constant: 00000000000001b0 <._copy_to_user>: ... 1f0: 4c 00 01 2c isync 1f4: 3d 20 40 00 lis r9,16384 1f8: 79 29 07 c6 rldicr r9,r9,32,31 1fc: 7d 3d 03 a6 mtspr 29,r9 200: 4c 00 01 2c isync 204: 48 00 00 01 bl 204 <._copy_to_user+0x54> 204: R_PPC64_REL24 .__copy_tofrom_user ... 0000000000000260 <._copy_from_user>: ... 2ec: 4c 00 01 2c isync 2f0: 39 20 ff ff li r9,-1 2f4: 79 29 00 04 rldicr r9,r9,0,0 2f8: 7d 3d 03 a6 mtspr 29,r9 2fc: 4c 00 01 2c isync 300: 7f c5 f3 78 mr r5,r30 304: 7f 83 e3 78 mr r3,r28 308: 48 00 00 01 bl 308 <._copy_from_user+0xa8> 308: R_PPC64_REL24 .__copy_tofrom_user ... Signed-off-by: Christophe Leroy [mpe: Spell out the directions, s/KUAP_R/KUAP_READ/ etc.] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/f4e88ec4941d5facb35ce75026b0112f980086c3.1579866752.git.christophe.leroy@c-s.fr --- arch/powerpc/include/asm/book3s/32/kup.h | 13 ++++++++--- arch/powerpc/include/asm/book3s/64/kup-radix.h | 11 +++++----- arch/powerpc/include/asm/kup.h | 30 ++++++++++++++++++++------ arch/powerpc/include/asm/nohash/32/kup-8xx.h | 4 ++-- arch/powerpc/include/asm/uaccess.h | 4 ++-- 5 files changed, 43 insertions(+), 19 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index d88008c8eb85..91c8f1d9bcee 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -102,11 +102,13 @@ static inline void kuap_update_sr(u32 sr, u32 addr, u32 end) isync(); /* Context sync required after mtsrin() */ } -static inline void allow_user_access(void __user *to, const void __user *from, u32 size) +static __always_inline void allow_user_access(void __user *to, const void __user *from, + u32 size, unsigned long dir) { u32 addr, end; - if (__builtin_constant_p(to) && to == NULL) + BUILD_BUG_ON(!__builtin_constant_p(dir)); + if (!(dir & KUAP_WRITE)) return; addr = (__force u32)to; @@ -119,11 +121,16 @@ static inline void allow_user_access(void __user *to, const void __user *from, u kuap_update_sr(mfsrin(addr) & ~SR_KS, addr, end); /* Clear Ks */ } -static inline void prevent_user_access(void __user *to, const void __user *from, u32 size) +static __always_inline void prevent_user_access(void __user *to, const void __user *from, + u32 size, unsigned long dir) { u32 addr = (__force u32)to; u32 end = min(addr + size, TASK_SIZE); + BUILD_BUG_ON(!__builtin_constant_p(dir)); + if (!(dir & KUAP_WRITE)) + return; + if (!addr || addr >= TASK_SIZE || !size) return; diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h index dbbd22cb80f5..c8d1076e0ebb 100644 --- a/arch/powerpc/include/asm/book3s/64/kup-radix.h +++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h @@ -77,20 +77,21 @@ static inline void set_kuap(unsigned long value) isync(); } -static inline void allow_user_access(void __user *to, const void __user *from, - unsigned long size) +static __always_inline void allow_user_access(void __user *to, const void __user *from, + unsigned long size, unsigned long dir) { // This is written so we can resolve to a single case at build time - if (__builtin_constant_p(to) && to == NULL) + BUILD_BUG_ON(!__builtin_constant_p(dir)); + if (dir == KUAP_READ) set_kuap(AMR_KUAP_BLOCK_WRITE); - else if (__builtin_constant_p(from) && from == NULL) + else if (dir == KUAP_WRITE) set_kuap(AMR_KUAP_BLOCK_READ); else set_kuap(0); } static inline void prevent_user_access(void __user *to, const void __user *from, - unsigned long size) + unsigned long size, unsigned long dir) { set_kuap(AMR_KUAP_BLOCKED); } diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h index 812e66f31934..94f24928916a 100644 --- a/arch/powerpc/include/asm/kup.h +++ b/arch/powerpc/include/asm/kup.h @@ -2,6 +2,10 @@ #ifndef _ASM_POWERPC_KUP_H_ #define _ASM_POWERPC_KUP_H_ +#define KUAP_READ 1 +#define KUAP_WRITE 2 +#define KUAP_READ_WRITE (KUAP_READ | KUAP_WRITE) + #ifdef CONFIG_PPC64 #include #endif @@ -42,9 +46,9 @@ void setup_kuap(bool disabled); #else static inline void setup_kuap(bool disabled) { } static inline void allow_user_access(void __user *to, const void __user *from, - unsigned long size) { } + unsigned long size, unsigned long dir) { } static inline void prevent_user_access(void __user *to, const void __user *from, - unsigned long size) { } + unsigned long size, unsigned long dir) { } static inline bool bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { @@ -54,24 +58,36 @@ bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) static inline void allow_read_from_user(const void __user *from, unsigned long size) { - allow_user_access(NULL, from, size); + allow_user_access(NULL, from, size, KUAP_READ); } static inline void allow_write_to_user(void __user *to, unsigned long size) { - allow_user_access(to, NULL, size); + allow_user_access(to, NULL, size, KUAP_WRITE); +} + +static inline void allow_read_write_user(void __user *to, const void __user *from, + unsigned long size) +{ + allow_user_access(to, from, size, KUAP_READ_WRITE); } static inline void prevent_read_from_user(const void __user *from, unsigned long size) { - prevent_user_access(NULL, from, size); + prevent_user_access(NULL, from, size, KUAP_READ); } static inline void prevent_write_to_user(void __user *to, unsigned long size) { - prevent_user_access(to, NULL, size); + prevent_user_access(to, NULL, size, KUAP_WRITE); +} + +static inline void prevent_read_write_user(void __user *to, const void __user *from, + unsigned long size) +{ + prevent_user_access(to, from, size, KUAP_READ_WRITE); } #endif /* !__ASSEMBLY__ */ -#endif /* _ASM_POWERPC_KUP_H_ */ +#endif /* _ASM_POWERPC_KUAP_H_ */ diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h index f2fea603b929..1d70c80366fd 100644 --- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h @@ -35,13 +35,13 @@ #include static inline void allow_user_access(void __user *to, const void __user *from, - unsigned long size) + unsigned long size, unsigned long dir) { mtspr(SPRN_MD_AP, MD_APG_INIT); } static inline void prevent_user_access(void __user *to, const void __user *from, - unsigned long size) + unsigned long size, unsigned long dir) { mtspr(SPRN_MD_AP, MD_APG_KUAP); } diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index c92fe7fe9692..cafad1960e76 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -313,9 +313,9 @@ raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) unsigned long ret; barrier_nospec(); - allow_user_access(to, from, n); + allow_read_write_user(to, from, n); ret = __copy_tofrom_user(to, from, n); - prevent_user_access(to, from, n); + prevent_read_write_user(to, from, n); return ret; } #endif /* __powerpc64__ */ -- cgit v1.2.3 From 88f8c080d47f307871840a0a825ef556673eb592 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 24 Jan 2020 11:54:42 +0000 Subject: powerpc/32s: Drop NULL addr verification NULL addr is a user address. Don't waste time checking it. If someone tries to access it, it will SIGFAULT the same way as for address 1, so no need to make it special. The special case is when not doing a write, in that case we want to drop the entire function. This is now handled by 'dir' param and not by the nulity of 'to' anymore. Also make beginning of prevent_user_access() similar to beginning of allow_user_access(), and tell the compiler that writing in kernel space or with a 0 length is unlikely Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/85e971223dfe6ace734637db1841678939a76155.1579866752.git.christophe.leroy@c-s.fr --- arch/powerpc/include/asm/book3s/32/kup.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index 91c8f1d9bcee..de29fb752cca 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -113,7 +113,7 @@ static __always_inline void allow_user_access(void __user *to, const void __user addr = (__force u32)to; - if (!addr || addr >= TASK_SIZE || !size) + if (unlikely(addr >= TASK_SIZE || !size)) return; end = min(addr + size, TASK_SIZE); @@ -124,16 +124,18 @@ static __always_inline void allow_user_access(void __user *to, const void __user static __always_inline void prevent_user_access(void __user *to, const void __user *from, u32 size, unsigned long dir) { - u32 addr = (__force u32)to; - u32 end = min(addr + size, TASK_SIZE); + u32 addr, end; BUILD_BUG_ON(!__builtin_constant_p(dir)); if (!(dir & KUAP_WRITE)) return; - if (!addr || addr >= TASK_SIZE || !size) + addr = (__force u32)to; + + if (unlikely(addr >= TASK_SIZE || !size)) return; + end = min(addr + size, TASK_SIZE); current->thread.kuap = 0; kuap_update_sr(mfsrin(addr) | SR_KS, addr, end); /* set Ks */ } -- cgit v1.2.3 From bedb4dbe443c11ff551b4ae4e48c8676fdc96467 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 24 Jan 2020 11:54:43 +0000 Subject: powerpc/32s: Prepare prevent_user_access() for user_access_end() In preparation of implementing user_access_begin and friends on powerpc, the book3s/32 version of prevent_user_access() need to be prepared for user_access_end(). user_access_end() doesn't provide the address and size which were passed to user_access_begin(), required by prevent_user_access() to know which segment to modify. The list of segments which where unprotected by allow_user_access() are available in current->kuap. But we don't want prevent_user_access() to read this all the time, especially everytime it is 0 (for instance because the access was not a write access). Implement a special direction named KUAP_CURRENT. In this case only, the addr and end are retrieved from current->kuap. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/55bcc1f25d8200892a31f67a0b024ff3b816c3cc.1579866752.git.christophe.leroy@c-s.fr --- arch/powerpc/include/asm/book3s/32/kup.h | 23 ++++++++++++++++++----- arch/powerpc/include/asm/book3s/64/kup-radix.h | 4 +++- arch/powerpc/include/asm/kup.h | 11 +++++++++++ 3 files changed, 32 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index de29fb752cca..17e069291c72 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -108,6 +108,8 @@ static __always_inline void allow_user_access(void __user *to, const void __user u32 addr, end; BUILD_BUG_ON(!__builtin_constant_p(dir)); + BUILD_BUG_ON(dir == KUAP_CURRENT); + if (!(dir & KUAP_WRITE)) return; @@ -117,6 +119,7 @@ static __always_inline void allow_user_access(void __user *to, const void __user return; end = min(addr + size, TASK_SIZE); + current->thread.kuap = (addr & 0xf0000000) | ((((end - 1) >> 28) + 1) & 0xf); kuap_update_sr(mfsrin(addr) & ~SR_KS, addr, end); /* Clear Ks */ } @@ -127,15 +130,25 @@ static __always_inline void prevent_user_access(void __user *to, const void __us u32 addr, end; BUILD_BUG_ON(!__builtin_constant_p(dir)); - if (!(dir & KUAP_WRITE)) - return; - addr = (__force u32)to; + if (dir == KUAP_CURRENT) { + u32 kuap = current->thread.kuap; - if (unlikely(addr >= TASK_SIZE || !size)) + if (unlikely(!kuap)) + return; + + addr = kuap & 0xf0000000; + end = kuap << 28; + } else if (dir & KUAP_WRITE) { + addr = (__force u32)to; + end = min(addr + size, TASK_SIZE); + + if (unlikely(addr >= TASK_SIZE || !size)) + return; + } else { return; + } - end = min(addr + size, TASK_SIZE); current->thread.kuap = 0; kuap_update_sr(mfsrin(addr) | SR_KS, addr, end); /* set Ks */ } diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h index c8d1076e0ebb..a0263e94df33 100644 --- a/arch/powerpc/include/asm/book3s/64/kup-radix.h +++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h @@ -86,8 +86,10 @@ static __always_inline void allow_user_access(void __user *to, const void __user set_kuap(AMR_KUAP_BLOCK_WRITE); else if (dir == KUAP_WRITE) set_kuap(AMR_KUAP_BLOCK_READ); - else + else if (dir == KUAP_READ_WRITE) set_kuap(0); + else + BUILD_BUG(); } static inline void prevent_user_access(void __user *to, const void __user *from, diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h index 94f24928916a..c3ce7e8ae9ea 100644 --- a/arch/powerpc/include/asm/kup.h +++ b/arch/powerpc/include/asm/kup.h @@ -5,6 +5,12 @@ #define KUAP_READ 1 #define KUAP_WRITE 2 #define KUAP_READ_WRITE (KUAP_READ | KUAP_WRITE) +/* + * For prevent_user_access() only. + * Use the current saved situation instead of the to/from/size params. + * Used on book3s/32 + */ +#define KUAP_CURRENT 4 #ifdef CONFIG_PPC64 #include @@ -88,6 +94,11 @@ static inline void prevent_read_write_user(void __user *to, const void __user *f prevent_user_access(to, from, size, KUAP_READ_WRITE); } +static inline void prevent_current_access_user(void) +{ + prevent_user_access(NULL, NULL, ~0UL, KUAP_CURRENT); +} + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_KUAP_H_ */ -- cgit v1.2.3 From 5cd623333e7cf4e3a334c70529268b65f2a6c2c7 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 24 Jan 2020 11:54:44 +0000 Subject: powerpc: Implement user_access_begin and friends Today, when a function like strncpy_from_user() is called, the userspace access protection is de-activated and re-activated for every word read. By implementing user_access_begin and friends, the protection is de-activated at the beginning of the copy and re-activated at the end. Implement user_access_begin(), user_access_end() and unsafe_get_user(), unsafe_put_user() and unsafe_copy_to_user() For the time being, we keep user_access_save() and user_access_restore() as nops. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/36d4fbf9e56a75994aca4ee2214c77b26a5a8d35.1579866752.git.christophe.leroy@c-s.fr --- arch/powerpc/include/asm/uaccess.h | 85 +++++++++++++++++++++++++++++--------- 1 file changed, 66 insertions(+), 19 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index cafad1960e76..af905d7fc1df 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -91,9 +91,14 @@ static inline int __access_ok(unsigned long addr, unsigned long size, __put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) #define __get_user(x, ptr) \ - __get_user_nocheck((x), (ptr), sizeof(*(ptr))) + __get_user_nocheck((x), (ptr), sizeof(*(ptr)), true) #define __put_user(x, ptr) \ - __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) + __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), true) + +#define __get_user_allowed(x, ptr) \ + __get_user_nocheck((x), (ptr), sizeof(*(ptr)), false) +#define __put_user_allowed(x, ptr) \ + __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), false) #define __get_user_inatomic(x, ptr) \ __get_user_nosleep((x), (ptr), sizeof(*(ptr))) @@ -138,10 +143,9 @@ extern long __put_user_bad(void); : "r" (x), "b" (addr), "i" (-EFAULT), "0" (err)) #endif /* __powerpc64__ */ -#define __put_user_size(x, ptr, size, retval) \ +#define __put_user_size_allowed(x, ptr, size, retval) \ do { \ retval = 0; \ - allow_write_to_user(ptr, size); \ switch (size) { \ case 1: __put_user_asm(x, ptr, retval, "stb"); break; \ case 2: __put_user_asm(x, ptr, retval, "sth"); break; \ @@ -149,17 +153,26 @@ do { \ case 8: __put_user_asm2(x, ptr, retval); break; \ default: __put_user_bad(); \ } \ +} while (0) + +#define __put_user_size(x, ptr, size, retval) \ +do { \ + allow_write_to_user(ptr, size); \ + __put_user_size_allowed(x, ptr, size, retval); \ prevent_write_to_user(ptr, size); \ } while (0) -#define __put_user_nocheck(x, ptr, size) \ +#define __put_user_nocheck(x, ptr, size, do_allow) \ ({ \ long __pu_err; \ __typeof__(*(ptr)) __user *__pu_addr = (ptr); \ if (!is_kernel_addr((unsigned long)__pu_addr)) \ might_fault(); \ __chk_user_ptr(ptr); \ - __put_user_size((x), __pu_addr, (size), __pu_err); \ + if (do_allow) \ + __put_user_size((x), __pu_addr, (size), __pu_err); \ + else \ + __put_user_size_allowed((x), __pu_addr, (size), __pu_err); \ __pu_err; \ }) @@ -236,13 +249,12 @@ extern long __get_user_bad(void); : "b" (addr), "i" (-EFAULT), "0" (err)) #endif /* __powerpc64__ */ -#define __get_user_size(x, ptr, size, retval) \ +#define __get_user_size_allowed(x, ptr, size, retval) \ do { \ retval = 0; \ __chk_user_ptr(ptr); \ if (size > sizeof(x)) \ (x) = __get_user_bad(); \ - allow_read_from_user(ptr, size); \ switch (size) { \ case 1: __get_user_asm(x, ptr, retval, "lbz"); break; \ case 2: __get_user_asm(x, ptr, retval, "lhz"); break; \ @@ -250,6 +262,12 @@ do { \ case 8: __get_user_asm2(x, ptr, retval); break; \ default: (x) = __get_user_bad(); \ } \ +} while (0) + +#define __get_user_size(x, ptr, size, retval) \ +do { \ + allow_read_from_user(ptr, size); \ + __get_user_size_allowed(x, ptr, size, retval); \ prevent_read_from_user(ptr, size); \ } while (0) @@ -260,7 +278,7 @@ do { \ #define __long_type(x) \ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) -#define __get_user_nocheck(x, ptr, size) \ +#define __get_user_nocheck(x, ptr, size, do_allow) \ ({ \ long __gu_err; \ __long_type(*(ptr)) __gu_val; \ @@ -269,7 +287,10 @@ do { \ if (!is_kernel_addr((unsigned long)__gu_addr)) \ might_fault(); \ barrier_nospec(); \ - __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ + if (do_allow) \ + __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ + else \ + __get_user_size_allowed(__gu_val, __gu_addr, (size), __gu_err); \ (x) = (__typeof__(*(ptr)))__gu_val; \ __gu_err; \ }) @@ -356,33 +377,40 @@ static inline unsigned long raw_copy_from_user(void *to, return ret; } -static inline unsigned long raw_copy_to_user(void __user *to, - const void *from, unsigned long n) +static inline unsigned long +raw_copy_to_user_allowed(void __user *to, const void *from, unsigned long n) { - unsigned long ret; if (__builtin_constant_p(n) && (n <= 8)) { - ret = 1; + unsigned long ret = 1; switch (n) { case 1: - __put_user_size(*(u8 *)from, (u8 __user *)to, 1, ret); + __put_user_size_allowed(*(u8 *)from, (u8 __user *)to, 1, ret); break; case 2: - __put_user_size(*(u16 *)from, (u16 __user *)to, 2, ret); + __put_user_size_allowed(*(u16 *)from, (u16 __user *)to, 2, ret); break; case 4: - __put_user_size(*(u32 *)from, (u32 __user *)to, 4, ret); + __put_user_size_allowed(*(u32 *)from, (u32 __user *)to, 4, ret); break; case 8: - __put_user_size(*(u64 *)from, (u64 __user *)to, 8, ret); + __put_user_size_allowed(*(u64 *)from, (u64 __user *)to, 8, ret); break; } if (ret == 0) return 0; } + return __copy_tofrom_user(to, (__force const void __user *)from, n); +} + +static inline unsigned long +raw_copy_to_user(void __user *to, const void *from, unsigned long n) +{ + unsigned long ret; + allow_write_to_user(to, n); - ret = __copy_tofrom_user(to, (__force const void __user *)from, n); + ret = raw_copy_to_user_allowed(to, from, n); prevent_write_to_user(to, n); return ret; } @@ -428,4 +456,23 @@ extern long __copy_from_user_flushcache(void *dst, const void __user *src, extern void memcpy_page_flushcache(char *to, struct page *page, size_t offset, size_t len); +static __must_check inline bool user_access_begin(const void __user *ptr, size_t len) +{ + if (unlikely(!access_ok(ptr, len))) + return false; + allow_read_write_user((void __user *)ptr, ptr, len); + return true; +} +#define user_access_begin user_access_begin +#define user_access_end prevent_current_access_user + +static inline unsigned long user_access_save(void) { return 0UL; } +static inline void user_access_restore(unsigned long flags) { } + +#define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) +#define unsafe_get_user(x, p, e) unsafe_op_wrap(__get_user_allowed(x, p), e) +#define unsafe_put_user(x, p, e) unsafe_op_wrap(__put_user_allowed(x, p), e) +#define unsafe_copy_to_user(d, s, l, e) \ + unsafe_op_wrap(raw_copy_to_user_allowed(d, s, l), e) + #endif /* _ARCH_POWERPC_UACCESS_H */ -- cgit v1.2.3 From 3d7dfd632f9b60cfce069b4da517e6b1a1c3f613 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 24 Jan 2020 11:54:45 +0000 Subject: powerpc: Implement user_access_save() and user_access_restore() Implement user_access_save() and user_access_restore() On 8xx and radix: - On save, get the value of the associated special register then prevent user access. - On restore, set back the saved value to the associated special register. On book3s/32: - On save, get the value stored in current->thread.kuap and prevent user access. - On restore, regenerate address range from the stored value and reopen read/write access for that range. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/54f2f74938006b33c55a416674807b42ef222068.1579866752.git.christophe.leroy@c-s.fr --- arch/powerpc/include/asm/book3s/32/kup.h | 23 +++++++++++++++++++++++ arch/powerpc/include/asm/book3s/64/kup-radix.h | 22 ++++++++++++++++++++++ arch/powerpc/include/asm/kup.h | 2 ++ arch/powerpc/include/asm/nohash/32/kup-8xx.h | 14 ++++++++++++++ arch/powerpc/include/asm/uaccess.h | 5 ++--- 5 files changed, 63 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index 17e069291c72..3c0ba22dc360 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -153,6 +153,29 @@ static __always_inline void prevent_user_access(void __user *to, const void __us kuap_update_sr(mfsrin(addr) | SR_KS, addr, end); /* set Ks */ } +static inline unsigned long prevent_user_access_return(void) +{ + unsigned long flags = current->thread.kuap; + unsigned long addr = flags & 0xf0000000; + unsigned long end = flags << 28; + void __user *to = (__force void __user *)addr; + + if (flags) + prevent_user_access(to, to, end - addr, KUAP_READ_WRITE); + + return flags; +} + +static inline void restore_user_access(unsigned long flags) +{ + unsigned long addr = flags & 0xf0000000; + unsigned long end = flags << 28; + void __user *to = (__force void __user *)addr; + + if (flags) + allow_user_access(to, to, end - addr, KUAP_READ_WRITE); +} + static inline bool bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h index a0263e94df33..90dd3a3fc8c7 100644 --- a/arch/powerpc/include/asm/book3s/64/kup-radix.h +++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h @@ -63,6 +63,14 @@ * because that would require an expensive read/modify write of the AMR. */ +static inline unsigned long get_kuap(void) +{ + if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP)) + return 0; + + return mfspr(SPRN_AMR); +} + static inline void set_kuap(unsigned long value) { if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP)) @@ -98,6 +106,20 @@ static inline void prevent_user_access(void __user *to, const void __user *from, set_kuap(AMR_KUAP_BLOCKED); } +static inline unsigned long prevent_user_access_return(void) +{ + unsigned long flags = get_kuap(); + + set_kuap(AMR_KUAP_BLOCKED); + + return flags; +} + +static inline void restore_user_access(unsigned long flags) +{ + set_kuap(flags); +} + static inline bool bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h index c3ce7e8ae9ea..92bcd1a26d73 100644 --- a/arch/powerpc/include/asm/kup.h +++ b/arch/powerpc/include/asm/kup.h @@ -55,6 +55,8 @@ static inline void allow_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { } static inline void prevent_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { } +static inline unsigned long prevent_user_access_return(void) { return 0UL; } +static inline void restore_user_access(unsigned long flags) { } static inline bool bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h index 1d70c80366fd..85ed2390fb99 100644 --- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h @@ -46,6 +46,20 @@ static inline void prevent_user_access(void __user *to, const void __user *from, mtspr(SPRN_MD_AP, MD_APG_KUAP); } +static inline unsigned long prevent_user_access_return(void) +{ + unsigned long flags = mfspr(SPRN_MD_AP); + + mtspr(SPRN_MD_AP, MD_APG_KUAP); + + return flags; +} + +static inline void restore_user_access(unsigned long flags) +{ + mtspr(SPRN_MD_AP, flags); +} + static inline bool bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index af905d7fc1df..2f500debae21 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -465,9 +465,8 @@ static __must_check inline bool user_access_begin(const void __user *ptr, size_t } #define user_access_begin user_access_begin #define user_access_end prevent_current_access_user - -static inline unsigned long user_access_save(void) { return 0UL; } -static inline void user_access_restore(unsigned long flags) { } +#define user_access_save prevent_user_access_return +#define user_access_restore restore_user_access #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) #define unsafe_get_user(x, p, e) unsafe_op_wrap(__get_user_allowed(x, p), e) -- cgit v1.2.3