From 5290ae2b8e5fecc465e2fe92350ff02aa2e5acae Mon Sep 17 00:00:00 2001 From: Jordan Niethe Date: Wed, 11 Dec 2019 13:35:52 +1100 Subject: powerpc/64: Use {SAVE,REST}_NVGPRS macros In entry_64.S there are places that open code saving and restoring the non-volatile registers. There are already macros for doing this so use them. Signed-off-by: Jordan Niethe Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20191211023552.16480-1-jniethe5@gmail.com --- arch/powerpc/kernel/entry_64.S | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 3fd3ef352e3f..0a82bfd44010 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -597,8 +597,7 @@ _GLOBAL(_switch) std r0,16(r1) stdu r1,-SWITCH_FRAME_SIZE(r1) /* r3-r13 are caller saved -- Cort */ - SAVE_8GPRS(14, r1) - SAVE_10GPRS(22, r1) + SAVE_NVGPRS(r1) std r0,_NIP(r1) /* Return to switch caller */ mfcr r23 std r23,_CCR(r1) @@ -722,8 +721,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) mtcrf 0xFF,r6 /* r3-r13 are destroyed -- Cort */ - REST_8GPRS(14, r1) - REST_10GPRS(22, r1) + REST_NVGPRS(r1) /* convert old thread to its task_struct for return value */ addi r3,r3,-THREAD @@ -1155,8 +1153,7 @@ _GLOBAL(enter_rtas) */ SAVE_GPR(2, r1) /* Save the TOC */ SAVE_GPR(13, r1) /* Save paca */ - SAVE_8GPRS(14, r1) /* Save the non-volatiles */ - SAVE_10GPRS(22, r1) /* ditto */ + SAVE_NVGPRS(r1) /* Save the non-volatiles */ mfcr r4 std r4,_CCR(r1) @@ -1263,8 +1260,7 @@ rtas_restore_regs: /* relocation is on at this point */ REST_GPR(2, r1) /* Restore the TOC */ REST_GPR(13, r1) /* Restore paca */ - REST_8GPRS(14, r1) /* Restore the non-volatiles */ - REST_10GPRS(22, r1) /* ditto */ + REST_NVGPRS(r1) /* Restore the non-volatiles */ GET_PACA(r13) @@ -1298,8 +1294,7 @@ _GLOBAL(enter_prom) */ SAVE_GPR(2, r1) SAVE_GPR(13, r1) - SAVE_8GPRS(14, r1) - SAVE_10GPRS(22, r1) + SAVE_NVGPRS(r1) mfcr r10 mfmsr r11 std r10,_CCR(r1) @@ -1343,8 +1338,7 @@ _GLOBAL(enter_prom) /* Restore other registers */ REST_GPR(2, r1) REST_GPR(13, r1) - REST_8GPRS(14, r1) - REST_10GPRS(22, r1) + REST_NVGPRS(r1) ld r4,_CCR(r1) mtcr r4 -- cgit v1.2.3 From 3b5b9997b331e77ce967eba2c4bc80dc3134a7fe Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Mon, 28 Oct 2019 19:54:22 +1100 Subject: powerpc/powernv/iov: Ensure the pdn for VFs always contains a valid PE number On pseries there is a bug with adding hotplugged devices to an IOMMU group. For a number of dumb reasons fixing that bug first requires re-working how VFs are configured on PowerNV. For background, on PowerNV we use the pcibios_sriov_enable() hook to do two things: 1. Create a pci_dn structure for each of the VFs, and 2. Configure the PHB's internal BARs so the MMIO range for each VF maps to a unique PE. Roughly speaking a PE is the hardware counterpart to a Linux IOMMU group since all the devices in a PE share the same IOMMU table. A PE also defines the set of devices that should be isolated in response to a PCI error (i.e. bad DMA, UR/CA, AER events, etc). When isolated all MMIO and DMA traffic to and from devicein the PE is blocked by the root complex until the PE is recovered by the OS. The requirement to block MMIO causes a giant headache because the P8 PHB generally uses a fixed mapping between MMIO addresses and PEs. As a result we need to delay configuring the IOMMU groups for device until after MMIO resources are assigned. For physical devices (i.e. non-VFs) the PE assignment is done in pcibios_setup_bridge() which is called immediately after the MMIO resources for downstream devices (and the bridge's windows) are assigned. For VFs the setup is more complicated because: a) pcibios_setup_bridge() is not called again when VFs are activated, and b) The pci_dev for VFs are created by generic code which runs after pcibios_sriov_enable() is called. The work around for this is a two step process: 1. A fixup in pcibios_add_device() is used to initialised the cached pe_number in pci_dn, then 2. A bus notifier then adds the device to the IOMMU group for the PE specified in pci_dn->pe_number. A side effect fixing the pseries bug mentioned in the first paragraph is moving the fixup out of pcibios_add_device() and into pcibios_bus_add_device(), which is called much later. This results in step 2. failing because pci_dn->pe_number won't be initialised when the bus notifier is run. We can fix this by removing the need for the fixup. The PE for a VF is known before the VF is even scanned so we can initialise pci_dn->pe_number pcibios_sriov_enable() instead. Unfortunately, moving the initialisation causes two problems: 1. We trip the WARN_ON() in the current fixup code, and 2. The EEH core clears pdn->pe_number when recovering a VF and relies on the fixup to correctly re-set it. The only justification for either of these is a comment in eeh_rmv_device() suggesting that pdn->pe_number *must* be set to IODA_INVALID_PE in order for the VF to be scanned. However, this comment appears to have no basis in reality. Both bugs can be fixed by just deleting the code. Tested-by: Alexey Kardashevskiy Reviewed-by: Alexey Kardashevskiy Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20191028085424.12006-1-oohall@gmail.com --- arch/powerpc/kernel/eeh_driver.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 3dd1a422fc29..a1eaffe868de 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -525,12 +525,6 @@ static void eeh_rmv_device(struct eeh_dev *edev, void *userdata) pci_iov_remove_virtfn(edev->physfn, pdn->vf_index); edev->pdev = NULL; - - /* - * We have to set the VF PE number to invalid one, which is - * required to plug the VF successfully. - */ - pdn->pe_number = IODA_INVALID_PE; #endif if (rmv_data) list_add(&edev->rmv_entry, &rmv_data->removed_vf_list); -- cgit v1.2.3 From 30d87ef8b38d471ab5c0f1226926ebd856da8647 Mon Sep 17 00:00:00 2001 From: Shawn Anastasio Date: Mon, 28 Oct 2019 19:54:23 +1100 Subject: powerpc/pci: Fix pcibios_setup_device() ordering Move PCI device setup from pcibios_add_device() and pcibios_fixup_bus() to pcibios_bus_add_device(). This ensures that platform-specific DMA and IOMMU setup occurs after the device has been registered in sysfs, which is a requirement for IOMMU group assignment to work This fixes IOMMU group assignment for hotplugged devices on pseries, where the existing behavior results in IOMMU assignment before registration. Thanks to Lukas Wunner for the suggestion. Signed-off-by: Shawn Anastasio Tested-by: Alexey Kardashevskiy Reviewed-by: Alexey Kardashevskiy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20191028085424.12006-2-oohall@gmail.com --- arch/powerpc/kernel/pci-common.c | 25 +++++++++---------------- 1 file changed, 9 insertions(+), 16 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 1c448cf25506..b89925ede935 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -261,12 +261,6 @@ int pcibios_sriov_disable(struct pci_dev *pdev) #endif /* CONFIG_PCI_IOV */ -void pcibios_bus_add_device(struct pci_dev *pdev) -{ - if (ppc_md.pcibios_bus_add_device) - ppc_md.pcibios_bus_add_device(pdev); -} - static resource_size_t pcibios_io_size(const struct pci_controller *hose) { #ifdef CONFIG_PPC64 @@ -987,15 +981,17 @@ static void pcibios_setup_device(struct pci_dev *dev) ppc_md.pci_irq_fixup(dev); } -int pcibios_add_device(struct pci_dev *dev) +void pcibios_bus_add_device(struct pci_dev *pdev) { - /* - * We can only call pcibios_setup_device() after bus setup is complete, - * since some of the platform specific DMA setup code depends on it. - */ - if (dev->bus->is_added) - pcibios_setup_device(dev); + /* Perform platform-specific device setup */ + pcibios_setup_device(pdev); + + if (ppc_md.pcibios_bus_add_device) + ppc_md.pcibios_bus_add_device(pdev); +} +int pcibios_add_device(struct pci_dev *dev) +{ #ifdef CONFIG_PCI_IOV if (ppc_md.pcibios_fixup_sriov) ppc_md.pcibios_fixup_sriov(dev); @@ -1037,9 +1033,6 @@ void pcibios_fixup_bus(struct pci_bus *bus) /* Now fixup the bus bus */ pcibios_setup_bus_self(bus); - - /* Now fixup devices on that bus */ - pcibios_setup_bus_devices(bus); } EXPORT_SYMBOL(pcibios_fixup_bus); -- cgit v1.2.3 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/kernel/pci-common.c | 25 ------------------------- arch/powerpc/kernel/pci-hotplug.c | 1 - arch/powerpc/kernel/pci_of_scan.c | 1 - 3 files changed, 27 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index b89925ede935..f8a59d7b724c 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1000,24 +1000,6 @@ int pcibios_add_device(struct pci_dev *dev) return 0; } -void pcibios_setup_bus_devices(struct pci_bus *bus) -{ - struct pci_dev *dev; - - pr_debug("PCI: Fixup bus devices %d (%s)\n", - bus->number, bus->self ? pci_name(bus->self) : "PHB"); - - list_for_each_entry(dev, &bus->devices, bus_list) { - /* Cardbus can call us to add new devices to a bus, so ignore - * those who are already fully discovered - */ - if (pci_dev_is_added(dev)) - continue; - - pcibios_setup_device(dev); - } -} - void pcibios_set_master(struct pci_dev *dev) { /* No special bus mastering setup handling */ @@ -1036,13 +1018,6 @@ void pcibios_fixup_bus(struct pci_bus *bus) } EXPORT_SYMBOL(pcibios_fixup_bus); -void pci_fixup_cardbus(struct pci_bus *bus) -{ - /* Now fixup devices on that bus */ - pcibios_setup_bus_devices(bus); -} - - static int skip_isa_ioresource_align(struct pci_dev *dev) { if (pci_has_flag(PCI_CAN_SKIP_ISA_ALIGN) && diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c index fc62c4bc47b1..d6a67f814983 100644 --- a/arch/powerpc/kernel/pci-hotplug.c +++ b/arch/powerpc/kernel/pci-hotplug.c @@ -134,7 +134,6 @@ void pci_hp_add_devices(struct pci_bus *bus) */ slotno = PCI_SLOT(PCI_DN(dn->child)->devfn); pci_scan_slot(bus, PCI_DEVFN(slotno, 0)); - pcibios_setup_bus_devices(bus); max = bus->busn_res.start; /* * Scan bridges that are already configured. We don't touch diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index f91d7e94872e..c3024f104765 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -414,7 +414,6 @@ static void __of_scan_bus(struct device_node *node, struct pci_bus *bus, */ if (!rescan_existing) pcibios_setup_bus_self(bus); - pcibios_setup_bus_devices(bus); /* Now scan child busses */ for_each_pci_bridge(dev, bus) -- 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/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 ------------------------------------ 5 files changed, 57 insertions(+), 87 deletions(-) delete mode 100644 arch/powerpc/kernel/idle_power4.S (limited to 'arch/powerpc/kernel') 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 -- 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/kernel/hw_breakpoint.c | 15 +++++----- arch/powerpc/kernel/process.c | 57 +++++++++++++++++++++++-------------- 2 files changed, 43 insertions(+), 29 deletions(-) (limited to 'arch/powerpc/kernel') 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 902137ba8e469ed07c7f120a390161937a6288fb Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 2 Dec 2019 07:57:27 +0000 Subject: powerpc/32: Add VDSO version of getcpu on non SMP Commit 18ad51dd342a ("powerpc: Add VDSO version of getcpu") added getcpu() for PPC64 only, by making use of a user readable general purpose SPR. PPC32 doesn't have any such SPR. For non SMP, just return CPU id 0 from the VDSO directly. PPC32 doesn't support CONFIG_NUMA so NUMA node is always 0. Before the patch, vdsotest reported: getcpu: syscall: 1572 nsec/call getcpu: libc: 1787 nsec/call getcpu: vdso: not tested Now, vdsotest reports: getcpu: syscall: 1582 nsec/call getcpu: libc: 502 nsec/call getcpu: vdso: 187 nsec/call Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/eaac4b6494ecff1811220fccc895bf282aab884a.1575273217.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/vdso32/Makefile | 4 +--- arch/powerpc/kernel/vdso32/getcpu.S | 17 +++++++++++++++++ arch/powerpc/kernel/vdso32/vdso32.lds.S | 2 +- 3 files changed, 19 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index 06f54d947057..e147bbdc12cd 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -2,9 +2,7 @@ # List of files in the vdso, has to be asm only for now -obj-vdso32-$(CONFIG_PPC64) = getcpu.o -obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o \ - $(obj-vdso32-y) +obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o # Build rules diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso32/getcpu.S index 63e914539e1a..90b39af14383 100644 --- a/arch/powerpc/kernel/vdso32/getcpu.S +++ b/arch/powerpc/kernel/vdso32/getcpu.S @@ -15,6 +15,7 @@ * int __kernel_getcpu(unsigned *cpu, unsigned *node); * */ +#if defined(CONFIG_PPC64) V_FUNCTION_BEGIN(__kernel_getcpu) .cfi_startproc mfspr r5,SPRN_SPRG_VDSO_READ @@ -31,3 +32,19 @@ V_FUNCTION_BEGIN(__kernel_getcpu) blr .cfi_endproc V_FUNCTION_END(__kernel_getcpu) +#elif !defined(CONFIG_SMP) +V_FUNCTION_BEGIN(__kernel_getcpu) + .cfi_startproc + cmpwi cr0, r3, 0 + cmpwi cr1, r4, 0 + li r5, 0 + beq cr0, 1f + stw r5, 0(r3) +1: li r3, 0 /* always success */ + crclr cr0*4+so + beqlr cr1 + stw r5, 0(r4) + blr + .cfi_endproc +V_FUNCTION_END(__kernel_getcpu) +#endif diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S index 00c025ba4a92..5206c2eb2a1d 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -155,7 +155,7 @@ VERSION __kernel_sync_dicache_p5; __kernel_sigtramp32; __kernel_sigtramp_rt32; -#ifdef CONFIG_PPC64 +#if defined(CONFIG_PPC64) || !defined(CONFIG_SMP) __kernel_getcpu; #endif -- cgit v1.2.3 From 654abc69ef2e69712e6d4e8a6cb9292b97a4aa39 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 2 Dec 2019 07:57:28 +0000 Subject: powerpc/vdso32: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE This is copied and adapted from commit 5c929885f1bb ("powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE") from Santosh Sivaraj Benchmark from vdsotest-all: clock-gettime-realtime: syscall: 3601 nsec/call clock-gettime-realtime: libc: 1072 nsec/call clock-gettime-realtime: vdso: 931 nsec/call clock-gettime-monotonic: syscall: 4034 nsec/call clock-gettime-monotonic: libc: 1213 nsec/call clock-gettime-monotonic: vdso: 1076 nsec/call clock-gettime-realtime-coarse: syscall: 2722 nsec/call clock-gettime-realtime-coarse: libc: 805 nsec/call clock-gettime-realtime-coarse: vdso: 668 nsec/call clock-gettime-monotonic-coarse: syscall: 2949 nsec/call clock-gettime-monotonic-coarse: libc: 882 nsec/call clock-gettime-monotonic-coarse: vdso: 745 nsec/call Additional test passed with: vdsotest -d 30 clock-gettime-monotonic-coarse verify Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://github.com/linuxppc/issues/issues/41 Link: https://lore.kernel.org/r/d1d24a376e396540194eeb85a2efe481e92ade24.1575273217.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/vdso32/gettimeofday.S | 64 +++++++++++++++++++++++++++---- 1 file changed, 57 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 3306672f57a9..e9ce8ee56edb 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -69,7 +69,13 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) cmpli cr0,r3,CLOCK_REALTIME cmpli cr1,r3,CLOCK_MONOTONIC cror cr0*4+eq,cr0*4+eq,cr1*4+eq - bne cr0,99f + + cmpli cr5,r3,CLOCK_REALTIME_COARSE + cmpli cr6,r3,CLOCK_MONOTONIC_COARSE + cror cr5*4+eq,cr5*4+eq,cr6*4+eq + + cror cr0*4+eq,cr0*4+eq,cr5*4+eq + bne cr0, .Lgettime_fallback mflr r12 /* r12 saves lr */ .cfi_register lr,r12 @@ -78,8 +84,10 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) mr r9,r3 /* datapage ptr in r9 */ lis r7,NSEC_PER_SEC@h /* want nanoseconds */ ori r7,r7,NSEC_PER_SEC@l -50: bl __do_get_tspec@local /* get sec/nsec from tb & kernel */ - bne cr1,80f /* not monotonic -> all done */ + beq cr5, .Lcoarse_clocks +.Lprecise_clocks: + bl __do_get_tspec@local /* get sec/nsec from tb & kernel */ + bne cr1, .Lfinish /* not monotonic -> all done */ /* * CLOCK_MONOTONIC @@ -103,12 +111,53 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) add r9,r9,r0 lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9) cmpl cr0,r8,r0 /* check if updated */ - bne- 50b + bne- .Lprecise_clocks + b .Lfinish_monotonic + + /* + * For coarse clocks we get data directly from the vdso data page, so + * we don't need to call __do_get_tspec, but we still need to do the + * counter trick. + */ +.Lcoarse_clocks: + lwz r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9) + andi. r0,r8,1 /* pending update ? loop */ + bne- .Lcoarse_clocks + add r9,r9,r0 /* r0 is already 0 */ + + /* + * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE + * too + */ + lwz r3,STAMP_XTIME_SEC+LOPART(r9) + lwz r4,STAMP_XTIME_NSEC+LOPART(r9) + bne cr6,1f + + /* CLOCK_MONOTONIC_COARSE */ + lwz r5,(WTOM_CLOCK_SEC+LOPART)(r9) + lwz r6,WTOM_CLOCK_NSEC(r9) + + /* check if counter has updated */ + or r0,r6,r5 +1: or r0,r0,r3 + or r0,r0,r4 + xor r0,r0,r0 + add r3,r3,r0 + lwz r0,CFG_TB_UPDATE_COUNT+LOPART(r9) + cmpl cr0,r0,r8 /* check if updated */ + bne- .Lcoarse_clocks + + /* Counter has not updated, so continue calculating proper values for + * sec and nsec if monotonic coarse, or just return with the proper + * values for realtime. + */ + bne cr6, .Lfinish /* Calculate and store result. Note that this mimics the C code, * which may cause funny results if nsec goes negative... is that * possible at all ? */ +.Lfinish_monotonic: add r3,r3,r5 add r4,r4,r6 cmpw cr0,r4,r7 @@ -116,11 +165,12 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) blt 1f subf r4,r7,r4 addi r3,r3,1 -1: bge cr1,80f +1: bge cr1, .Lfinish addi r3,r3,-1 add r4,r4,r7 -80: stw r3,TSPC32_TV_SEC(r11) +.Lfinish: + stw r3,TSPC32_TV_SEC(r11) stw r4,TSPC32_TV_NSEC(r11) mtlr r12 @@ -131,7 +181,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) /* * syscall fallback */ -99: +.Lgettime_fallback: li r0,__NR_clock_gettime .cfi_restore lr sc -- 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/kernel/vdso32/cacheflush.S | 9 ++++----- arch/powerpc/kernel/vdso32/datapage.S | 28 +++------------------------- arch/powerpc/kernel/vdso32/gettimeofday.S | 12 +++++------- 3 files changed, 12 insertions(+), 37 deletions(-) (limited to 'arch/powerpc/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/kernel/asm-offsets.c | 2 +- arch/powerpc/kernel/vdso.c | 5 ----- arch/powerpc/kernel/vdso32/cacheflush.S | 23 +++++++++++++++++++++++ 3 files changed, 24 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/kernel') 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 6e2f9e9cfd560f5d9ce86503e5ae66330ccb97fc Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 2 Dec 2019 07:57:32 +0000 Subject: powerpc/vdso32: use LOAD_REG_IMMEDIATE() Use LOAD_REG_IMMEDIATE() to load registers with immediate value. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/36f111437e66e601929308f5d5dce230e1ce472f.1575273217.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/vdso32/gettimeofday.S | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 74973548529a..9aafacea9c4a 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -37,8 +37,7 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday) get_datapage r9, r0 cmplwi r10,0 /* check if tv is NULL */ beq 3f - lis r7,1000000@ha /* load up USEC_PER_SEC */ - addi r7,r7,1000000@l /* so we get microseconds in r4 */ + LOAD_REG_IMMEDIATE(r7, 1000000) /* load up USEC_PER_SEC */ bl __do_get_tspec@local /* get sec/usec from tb & kernel */ stw r3,TVAL32_TV_SEC(r10) stw r4,TVAL32_TV_USEC(r10) @@ -81,8 +80,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) .cfi_register lr,r12 mr r11,r4 /* r11 saves tp */ get_datapage r9, r0 - lis r7,NSEC_PER_SEC@h /* want nanoseconds */ - ori r7,r7,NSEC_PER_SEC@l + LOAD_REG_IMMEDIATE(r7, NSEC_PER_SEC) /* load up NSEC_PER_SEC */ beq cr5, .Lcoarse_clocks .Lprecise_clocks: bl __do_get_tspec@local /* get sec/nsec from tb & kernel */ -- cgit v1.2.3 From e33ffc956b086675551b86f5f83cf50ca47aa71c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 2 Dec 2019 07:57:33 +0000 Subject: powerpc/vdso32: implement clock_getres entirely clock_getres returns hrtimer_res for all clocks but coarse ones for which it returns KTIME_LOW_RES. return EINVAL for unknown clocks. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/37f94e47c91070b7606fb3ec3fe6fd2302a475a0.1575273217.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/asm-offsets.c | 3 +++ arch/powerpc/kernel/vdso32/gettimeofday.S | 19 +++++++++++-------- 2 files changed, 14 insertions(+), 8 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 0013197d89a6..90e53d432f2e 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -413,7 +413,10 @@ int main(void) DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC); DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE); DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE); + DEFINE(CLOCK_MAX, CLOCK_TAI); DEFINE(NSEC_PER_SEC, NSEC_PER_SEC); + DEFINE(EINVAL, EINVAL); + DEFINE(KTIME_LOW_RES, KTIME_LOW_RES); #ifdef CONFIG_BUG DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry)); diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 9aafacea9c4a..20ae38f3a5a3 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -196,17 +196,20 @@ V_FUNCTION_END(__kernel_clock_gettime) V_FUNCTION_BEGIN(__kernel_clock_getres) .cfi_startproc /* Check for supported clock IDs */ - cmpwi cr0,r3,CLOCK_REALTIME - cmpwi cr1,r3,CLOCK_MONOTONIC - cror cr0*4+eq,cr0*4+eq,cr1*4+eq - bne cr0,99f + cmplwi cr0, r3, CLOCK_MAX + cmpwi cr1, r3, CLOCK_REALTIME_COARSE + cmpwi cr7, r3, CLOCK_MONOTONIC_COARSE + bgt cr0, 99f + LOAD_REG_IMMEDIATE(r5, KTIME_LOW_RES) + beq cr1, 1f + beq cr7, 1f mflr r12 .cfi_register lr,r12 get_datapage r3, r0 lwz r5, CLOCK_HRTIMER_RES(r3) mtlr r12 - li r3,0 +1: li r3,0 cmpli cr0,r4,0 crclr cr0*4+so beqlr @@ -215,11 +218,11 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) blr /* - * syscall fallback + * invalid clock */ 99: - li r0,__NR_clock_getres - sc + li r3, EINVAL + crset so blr .cfi_endproc V_FUNCTION_END(__kernel_clock_getres) -- cgit v1.2.3 From bfc2eae0ad72a43d2a270acce2581c065223aa12 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 2 Dec 2019 07:57:35 +0000 Subject: powerpc/vdso32: miscellaneous optimisations Various optimisations by inverting branches and removing redundant instructions. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/b4e79f963845545bcce1459cd6fcfe46bdde7863.1575273217.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/vdso32/datapage.S | 3 +-- arch/powerpc/kernel/vdso32/getcpu.S | 6 +++--- arch/powerpc/kernel/vdso32/gettimeofday.S | 18 +++++++++--------- 3 files changed, 13 insertions(+), 14 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S index 1095d818f94a..217bb630f8f9 100644 --- a/arch/powerpc/kernel/vdso32/datapage.S +++ b/arch/powerpc/kernel/vdso32/datapage.S @@ -30,11 +30,10 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) .cfi_startproc mflr r12 .cfi_register lr,r12 - mr r4,r3 + mr. r4,r3 get_datapage r3, r0 mtlr r12 addi r3,r3,CFG_SYSCALL_MAP32 - cmpli cr0,r4,0 beqlr li r0,NR_syscalls stw r0,0(r4) diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso32/getcpu.S index 90b39af14383..ff5e214fec41 100644 --- a/arch/powerpc/kernel/vdso32/getcpu.S +++ b/arch/powerpc/kernel/vdso32/getcpu.S @@ -25,10 +25,10 @@ V_FUNCTION_BEGIN(__kernel_getcpu) rlwinm r7,r5,16,31-15,31-0 beq cr0,1f stw r6,0(r3) -1: beq cr1,2f - stw r7,0(r4) -2: crclr cr0*4+so +1: crclr cr0*4+so li r3,0 /* always success */ + beqlr cr1 + stw r7,0(r4) blr .cfi_endproc V_FUNCTION_END(__kernel_getcpu) diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 20ae38f3a5a3..a3951567118a 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -32,10 +32,9 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday) mflr r12 .cfi_register lr,r12 - mr r10,r3 /* r10 saves tv */ + mr. r10,r3 /* r10 saves tv */ mr r11,r4 /* r11 saves tz */ get_datapage r9, r0 - cmplwi r10,0 /* check if tv is NULL */ beq 3f LOAD_REG_IMMEDIATE(r7, 1000000) /* load up USEC_PER_SEC */ bl __do_get_tspec@local /* get sec/usec from tb & kernel */ @@ -43,15 +42,16 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday) stw r4,TVAL32_TV_USEC(r10) 3: cmplwi r11,0 /* check if tz is NULL */ - beq 1f + mtlr r12 + crclr cr0*4+so + li r3,0 + beqlr + lwz r4,CFG_TZ_MINUTEWEST(r9)/* fill tz */ lwz r5,CFG_TZ_DSTTIME(r9) stw r4,TZONE_TZ_MINWEST(r11) stw r5,TZONE_TZ_DSTTIME(r11) -1: mtlr r12 - crclr cr0*4+so - li r3,0 blr .cfi_endproc V_FUNCTION_END(__kernel_gettimeofday) @@ -245,10 +245,10 @@ V_FUNCTION_BEGIN(__kernel_time) lwz r3,STAMP_XTIME_SEC+LOPART(r9) cmplwi r11,0 /* check if t is NULL */ - beq 2f - stw r3,0(r11) /* store result at *t */ -2: mtlr r12 + mtlr r12 crclr cr0*4+so + beqlr + stw r3,0(r11) /* store result at *t */ blr .cfi_endproc V_FUNCTION_END(__kernel_time) -- cgit v1.2.3 From b1268f4cdba71c0cd40b533778812340d36de8ae Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Mon, 15 Jul 2019 18:56:08 +1000 Subject: powerpc/eeh_cache: Don't use pci_dn when inserting new ranges At the point where we start inserting ranges into the EEH address cache the binding between pci_dev and eeh_dev has already been set up. Instead of consulting the pci_dn tree we can retrieve the eeh_dev directly using pci_dev_to_eeh_dev(). Signed-off-by: Oliver O'Halloran Reviewed-by: Sam Bobroff Tested-by: Sam Bobroff Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190715085612.8802-2-oohall@gmail.com --- arch/powerpc/kernel/eeh_cache.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c index cf11277ebd02..6b50bf15d8c1 100644 --- a/arch/powerpc/kernel/eeh_cache.c +++ b/arch/powerpc/kernel/eeh_cache.c @@ -159,18 +159,10 @@ eeh_addr_cache_insert(struct pci_dev *dev, resource_size_t alo, static void __eeh_addr_cache_insert_dev(struct pci_dev *dev) { - struct pci_dn *pdn; struct eeh_dev *edev; int i; - pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn); - if (!pdn) { - pr_warn("PCI: no pci dn found for dev=%s\n", - pci_name(dev)); - return; - } - - edev = pdn_to_eeh_dev(pdn); + edev = pci_dev_to_eeh_dev(dev); if (!edev) { pr_warn("PCI: no EEH dev found for %s\n", pci_name(dev)); -- cgit v1.2.3 From 89f51839bd75b1aa8fa062a5f2b4bbcde560f6e2 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Mon, 15 Jul 2019 18:56:09 +1000 Subject: powerpc/eeh_sysfs: Fix incorrect comment The EEH_ATTR_SHOW() helper is used to display fields from struct eeh_dev not struct pci_dn. Signed-off-by: Oliver O'Halloran Reviewed-by: Sam Bobroff Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190715085612.8802-3-oohall@gmail.com --- arch/powerpc/kernel/eeh_sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c index ab44d965a53c..6afd82662b76 100644 --- a/arch/powerpc/kernel/eeh_sysfs.c +++ b/arch/powerpc/kernel/eeh_sysfs.c @@ -14,7 +14,7 @@ /** * EEH_SHOW_ATTR -- Create sysfs entry for eeh statistic * @_name: name of file in sysfs directory - * @_memb: name of member in struct pci_dn to access + * @_memb: name of member in struct eeh_dev to access * @_format: printf format for display * * All of the attributes look very similar, so just -- cgit v1.2.3 From 4107248c5615ab20b64073f2dd5917b3961239dc Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Mon, 15 Jul 2019 18:56:10 +1000 Subject: powerpc/eeh_sysfs: ifdef pseries sr-iov sysfs properties There are several EEH sysfs properties that only exists when the "ibm,is-open-sriov-pf" property appears in the device tree node of the PCI device. This used on pseries to indicate to the guest that the hypervisor allows the guest to configure the SR-IOV capability. Doing this requires some handshaking between the guest, hypervisor and userspace when a VF is EEH frozen which is why these properties exist. This is all dead code on non-pseries platforms so wrap it in an #ifdef CONFIG_PPC_PSERIES to make the dependency clearer. Signed-off-by: Oliver O'Halloran Tested-by: Sam Bobroff Reviewed-by: Sam Bobroff Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190715085612.8802-4-oohall@gmail.com --- arch/powerpc/kernel/eeh_sysfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c index 6afd82662b76..64a6dd519bf6 100644 --- a/arch/powerpc/kernel/eeh_sysfs.c +++ b/arch/powerpc/kernel/eeh_sysfs.c @@ -75,7 +75,7 @@ static ssize_t eeh_pe_state_store(struct device *dev, static DEVICE_ATTR_RW(eeh_pe_state); -#ifdef CONFIG_PCI_IOV +#if defined(CONFIG_PCI_IOV) && defined(CONFIG_PPC_PSERIES) static ssize_t eeh_notify_resume_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -132,7 +132,7 @@ static void eeh_notify_resume_remove(struct pci_dev *pdev) #else static inline int eeh_notify_resume_add(struct pci_dev *pdev) { return 0; } static inline void eeh_notify_resume_remove(struct pci_dev *pdev) { } -#endif /* CONFIG_PCI_IOV */ +#endif /* CONFIG_PCI_IOV && CONFIG PPC_PSERIES*/ void eeh_sysfs_add_device(struct pci_dev *pdev) { -- cgit v1.2.3 From 758b423275f0738fa4d382057c03f3d45c12905d Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Mon, 15 Jul 2019 18:56:11 +1000 Subject: powerpc/eeh_sysfs: Remove double pci_dn lookup. In eeh_notify_resume_show() the pci_dn for the device is looked up once in the declaration block and then once after checking for a NULL eeh_dev. Remove the second lookup since it's pointless. Signed-off-by: Oliver O'Halloran Reviewed-by: Sam Bobroff Tested-by: Sam Bobroff Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190715085612.8802-5-oohall@gmail.com --- arch/powerpc/kernel/eeh_sysfs.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c index 64a6dd519bf6..a6638ea54797 100644 --- a/arch/powerpc/kernel/eeh_sysfs.c +++ b/arch/powerpc/kernel/eeh_sysfs.c @@ -86,7 +86,6 @@ static ssize_t eeh_notify_resume_show(struct device *dev, if (!edev || !edev->pe) return -ENODEV; - pdn = pci_get_pdn(pdev); return sprintf(buf, "%d\n", pdn->last_allow_rc); } -- cgit v1.2.3 From 3489cdc417b20d929b33eff4d8312b4dd1f39ca1 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Mon, 15 Jul 2019 18:56:12 +1000 Subject: powerpc/eeh_sysfs: Make clearing EEH_DEV_SYSFS saner The eeh_sysfs_remove_device() function is supposed to clear the EEH_DEV_SYSFS flag since it indicates the EEH sysfs entries have been added for a pci_dev. When the sysfs files are removed eeh_remove_device() the eeh_dev and the pci_dev have already been de-associated. This then causes the pci_dev_to_eeh_dev() call in eeh_sysfs_remove_device() to return NULL so the flag can't be cleared from the still-live eeh_dev. This problem is worked around in the caller by clearing the flag manually. However, this behaviour doesn't make a whole lot of sense, so this patch fixes it by: a) Re-ordering eeh_remove_device() so that eeh_sysfs_remove_device() is called before de-associating the pci_dev and eeh_dev. b) Making eeh_sysfs_remove_device() emit a warning if there's no corresponding eeh_dev for a pci_dev. The paths where the sysfs files are only reachable if EEH was setup for the device for the device in the first place so hitting this warning indicates a programming error. Signed-off-by: Oliver O'Halloran Reviewed-by: Sam Bobroff Tested-by: Sam Bobroff Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190715085612.8802-6-oohall@gmail.com --- arch/powerpc/kernel/eeh.c | 30 +++++++++++++++++------------- arch/powerpc/kernel/eeh_sysfs.c | 15 ++++++++------- 2 files changed, 25 insertions(+), 20 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index bc8a551013be..daf9ff34a255 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -1191,7 +1191,6 @@ void eeh_add_device_late(struct pci_dev *dev) eeh_rmv_from_parent_pe(edev); eeh_addr_cache_rmv_dev(edev->pdev); eeh_sysfs_remove_device(edev->pdev); - edev->mode &= ~EEH_DEV_SYSFS; /* * We definitely should have the PCI device removed @@ -1296,17 +1295,11 @@ void eeh_remove_device(struct pci_dev *dev) edev->pdev = NULL; /* - * The flag "in_error" is used to trace EEH devices for VFs - * in error state or not. It's set in eeh_report_error(). If - * it's not set, eeh_report_{reset,resume}() won't be called - * for the VF EEH device. + * eeh_sysfs_remove_device() uses pci_dev_to_eeh_dev() so we need to + * remove the sysfs files before clearing dev.archdata.edev */ - edev->in_error = false; - dev->dev.archdata.edev = NULL; - if (!(edev->pe->state & EEH_PE_KEEP)) - eeh_rmv_from_parent_pe(edev); - else - edev->mode |= EEH_DEV_DISCONNECTED; + if (edev->mode & EEH_DEV_SYSFS) + eeh_sysfs_remove_device(dev); /* * We're removing from the PCI subsystem, that means @@ -1317,8 +1310,19 @@ void eeh_remove_device(struct pci_dev *dev) edev->mode |= EEH_DEV_NO_HANDLER; eeh_addr_cache_rmv_dev(dev); - eeh_sysfs_remove_device(dev); - edev->mode &= ~EEH_DEV_SYSFS; + + /* + * The flag "in_error" is used to trace EEH devices for VFs + * in error state or not. It's set in eeh_report_error(). If + * it's not set, eeh_report_{reset,resume}() won't be called + * for the VF EEH device. + */ + edev->in_error = false; + dev->dev.archdata.edev = NULL; + if (!(edev->pe->state & EEH_PE_KEEP)) + eeh_rmv_from_parent_pe(edev); + else + edev->mode |= EEH_DEV_DISCONNECTED; } int eeh_unfreeze_pe(struct eeh_pe *pe) diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c index a6638ea54797..4fb0f1e1017a 100644 --- a/arch/powerpc/kernel/eeh_sysfs.c +++ b/arch/powerpc/kernel/eeh_sysfs.c @@ -159,22 +159,23 @@ void eeh_sysfs_remove_device(struct pci_dev *pdev) { struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev); + if (!edev) { + WARN_ON(eeh_enabled()); + return; + } + + edev->mode &= ~EEH_DEV_SYSFS; + /* * The parent directory might have been removed. We needn't * continue for that case. */ - if (!pdev->dev.kobj.sd) { - if (edev) - edev->mode &= ~EEH_DEV_SYSFS; + if (!pdev->dev.kobj.sd) return; - } device_remove_file(&pdev->dev, &dev_attr_eeh_mode); device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr); device_remove_file(&pdev->dev, &dev_attr_eeh_pe_state); eeh_notify_resume_remove(pdev); - - if (edev) - edev->mode &= ~EEH_DEV_SYSFS; } -- cgit v1.2.3 From 1fb4124ca9d456656a324f1ee29b7bf942f59ac8 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Wed, 21 Aug 2019 16:26:53 +1000 Subject: powerpc/sriov: Remove VF eeh_dev state when disabling SR-IOV When disabling virtual functions on an SR-IOV adapter we currently do not correctly remove the EEH state for the now-dead virtual functions. When removing the pci_dn that was created for the VF when SR-IOV was enabled we free the corresponding eeh_dev without removing it from the child device list of the eeh_pe that contained it. This can result in crashes due to the use-after-free. Signed-off-by: Oliver O'Halloran Reviewed-by: Sam Bobroff Tested-by: Sam Bobroff Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190821062655.19735-1-oohall@gmail.com --- arch/powerpc/kernel/pci_dn.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 9524009ca1ae..d876eda92609 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -244,9 +244,22 @@ void remove_dev_pci_data(struct pci_dev *pdev) continue; #ifdef CONFIG_EEH - /* Release EEH device for the VF */ + /* + * Release EEH state for this VF. The PCI core + * has already torn down the pci_dev for this VF, but + * we're responsible to removing the eeh_dev since it + * has the same lifetime as the pci_dn that spawned it. + */ edev = pdn_to_eeh_dev(pdn); if (edev) { + /* + * We allocate pci_dn's for the totalvfs count, + * but only only the vfs that were activated + * have a configured PE. + */ + if (edev->pe) + eeh_rmv_from_parent_pe(edev); + pdn->edev = NULL; kfree(edev); } -- 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/kernel/pci_dn.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'arch/powerpc/kernel') 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) -- cgit v1.2.3 From a4af49f34f76f1e6125b22b50d18580426d935e0 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Wed, 21 Aug 2019 16:26:55 +1000 Subject: powerpc/pcidn: Warn when sriov pci_dn management is used incorrectly These functions can only be used on a SR-IOV capable physical function and they're only called in pcibios_sriov_enable / disable. Make them emit a warning in the future if they're used incorrectly and remove the dead code that checks if the device is a VF. Signed-off-by: Oliver O'Halloran Reviewed-by: Sam Bobroff Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190821062655.19735-3-oohall@gmail.com --- arch/powerpc/kernel/pci_dn.c | 17 +++-------------- 1 file changed, 3 insertions(+), 14 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index c158ac897efb..4e654df55969 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -158,8 +158,8 @@ struct pci_dn *add_sriov_vf_pdns(struct pci_dev *pdev) int i; /* Only support IOV for now */ - if (!pdev->is_physfn) - return pci_get_pdn(pdev); + if (WARN_ON(!pdev->is_physfn)) + return NULL; /* Check if VFs have been populated */ pdn = pci_get_pdn(pdev); @@ -199,19 +199,8 @@ void remove_sriov_vf_pdns(struct pci_dev *pdev) struct pci_dn *pdn, *tmp; int i; - /* - * VF and VF PE are created/released dynamically, so we need to - * bind/unbind them. Otherwise the VF and VF PE would be mismatched - * when re-enabling SR-IOV. - */ - if (pdev->is_virtfn) { - pdn = pci_get_pdn(pdev); - pdn->pe_number = IODA_INVALID_PE; - return; - } - /* Only support IOV PF for now */ - if (!pdev->is_physfn) + if (WARN_ON(!pdev->is_physfn)) return; /* Check if VFs have been populated */ -- cgit v1.2.3 From 4e0942c0302b5ad76b228b1a7b8c09f658a1d58a Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Wed, 16 Oct 2019 12:25:36 +1100 Subject: powerpc/eeh: Only dump stack once if an MMIO loop is detected Many drivers don't check for errors when they get a 0xFFs response from an MMIO load. As a result after an EEH event occurs a driver can get stuck in a polling loop unless it some kind of internal timeout logic. Currently EEH tries to detect and report stuck drivers by dumping a stack trace after eeh_dev_check_failure() is called EEH_MAX_FAILS times on an already frozen PE. The value of EEH_MAX_FAILS was chosen so that a dump would occur every few seconds if the driver was spinning in a loop. This results in a lot of spurious stack traces in the kernel log. Fix this by limiting it to printing one stack trace for each PE freeze. If the driver is truely stuck the kernel's hung task detector is better suited to reporting the probelm anyway. Signed-off-by: Oliver O'Halloran Reviewed-by: Sam Bobroff Tested-by: Sam Bobroff Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20191016012536.22588-1-oohall@gmail.com --- arch/powerpc/kernel/eeh.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index daf9ff34a255..17cb3e9b5697 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -503,7 +503,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) rc = 1; if (pe->state & EEH_PE_ISOLATED) { pe->check_count++; - if (pe->check_count % EEH_MAX_FAILS == 0) { + if (pe->check_count == EEH_MAX_FAILS) { dn = pci_device_to_OF_node(dev); if (dn) location = of_get_property(dn, "ibm,loc-code", -- cgit v1.2.3 From 3ab3f3c9df348324029e3fbdf381f551b1df8f1e Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 10 Jan 2020 18:02:03 +1100 Subject: powerpc/pci: Fold pcibios_setup_device() into pcibios_bus_add_device() pcibios_bus_add_device() is the only caller of pcibios_setup_device(). Fold them together since there's no real reason to keep them separate. Signed-off-by: Oliver O'Halloran Reviewed-by: Alexey Kardashevskiy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200110070207.439-2-oohall@gmail.com --- arch/powerpc/kernel/pci-common.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index f8a59d7b724c..c6c03416a151 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -958,7 +958,7 @@ void pcibios_setup_bus_self(struct pci_bus *bus) phb->controller_ops.dma_bus_setup(bus); } -static void pcibios_setup_device(struct pci_dev *dev) +void pcibios_bus_add_device(struct pci_dev *dev) { struct pci_controller *phb; /* Fixup NUMA node as it may not be setup yet by the generic @@ -979,15 +979,9 @@ static void pcibios_setup_device(struct pci_dev *dev) pci_read_irq_line(dev); if (ppc_md.pci_irq_fixup) ppc_md.pci_irq_fixup(dev); -} - -void pcibios_bus_add_device(struct pci_dev *pdev) -{ - /* Perform platform-specific device setup */ - pcibios_setup_device(pdev); if (ppc_md.pcibios_bus_add_device) - ppc_md.pcibios_bus_add_device(pdev); + ppc_md.pcibios_bus_add_device(dev); } int pcibios_add_device(struct pci_dev *dev) -- cgit v1.2.3 From def0bfdbd6039e96a9eb2baaa4470b079daab0d4 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 23 Jan 2020 17:30:47 +0000 Subject: powerpc: use probe_user_read() and probe_user_write() Instead of opencoding, use probe_user_read() to failessly read a user location and probe_user_write() for writing to user. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/e041f5eedb23f09ab553be8a91c3de2087147320.1579800517.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/process.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 7fcf72e58826..fad50db9dcf2 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1277,16 +1277,6 @@ void show_user_instructions(struct pt_regs *regs) pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int)); - /* - * Make sure the NIP points at userspace, not kernel text/data or - * elsewhere. - */ - if (!__access_ok(pc, NR_INSN_TO_PRINT * sizeof(int), USER_DS)) { - pr_info("%s[%d]: Bad NIP, not dumping instructions.\n", - current->comm, current->pid); - return; - } - seq_buf_init(&s, buf, sizeof(buf)); while (n) { @@ -1297,7 +1287,7 @@ void show_user_instructions(struct pt_regs *regs) for (i = 0; i < 8 && n; i++, n--, pc += sizeof(int)) { int instr; - if (probe_kernel_address((const void *)pc, instr)) { + if (probe_user_read(&instr, (void __user *)pc, sizeof(instr))) { seq_buf_printf(&s, "XXXXXXXX "); continue; } -- 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/kernel/dt_cpu_ftrs.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/kernel') 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); -- cgit v1.2.3 From 39bccfd164970557c5cfc60b2db029f70542549f Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:22 +0000 Subject: powerpc/32: replace MTMSRD() by mtmsr On PPC32, MTMSRD() is simply defined as mtmsr. Replace MTMSRD(reg) by mtmsr reg in files dedicated to PPC32, this makes the code less obscure. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/22469e78230edea3dbd0c79a555d73124f6c6d93.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/entry_32.S | 18 +++++++++--------- arch/powerpc/kernel/head_32.h | 4 ++-- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index d60908ea37fb..6273b4862482 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -397,7 +397,7 @@ ret_from_syscall: LOAD_REG_IMMEDIATE(r10,MSR_KERNEL) /* doesn't include MSR_EE */ /* Note: We don't bother telling lockdep about it */ SYNC - MTMSRD(r10) + mtmsr r10 lwz r9,TI_FLAGS(r2) li r8,-MAX_ERRNO andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK) @@ -554,7 +554,7 @@ syscall_exit_work: */ ori r10,r10,MSR_EE SYNC - MTMSRD(r10) + mtmsr r10 /* Save NVGPRS if they're not saved already */ lwz r4,_TRAP(r1) @@ -697,7 +697,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_SPE) and. r0,r0,r11 /* FP or altivec or SPE enabled? */ beq+ 1f andc r11,r11,r0 - MTMSRD(r11) + mtmsr r11 isync 1: stw r11,_MSR(r1) mfcr r10 @@ -831,7 +831,7 @@ ret_from_except: /* Note: We don't bother telling lockdep about it */ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL) SYNC /* Some chip revs have problems here... */ - MTMSRD(r10) /* disable interrupts */ + mtmsr r10 /* disable interrupts */ lwz r3,_MSR(r1) /* Returning to user mode? */ andi. r0,r3,MSR_PR @@ -998,7 +998,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) */ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL & ~MSR_RI) SYNC - MTMSRD(r10) /* clear the RI bit */ + mtmsr r10 /* clear the RI bit */ .globl exc_exit_restart exc_exit_restart: lwz r12,_NIP(r1) @@ -1234,7 +1234,7 @@ do_resched: /* r10 contains MSR_KERNEL here */ #endif ori r10,r10,MSR_EE SYNC - MTMSRD(r10) /* hard-enable interrupts */ + mtmsr r10 /* hard-enable interrupts */ bl schedule recheck: /* Note: And we don't tell it we are disabling them again @@ -1243,7 +1243,7 @@ recheck: */ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL) SYNC - MTMSRD(r10) /* disable interrupts */ + mtmsr r10 /* disable interrupts */ lwz r9,TI_FLAGS(r2) andi. r0,r9,_TIF_NEED_RESCHED bne- do_resched @@ -1252,7 +1252,7 @@ recheck: do_user_signal: /* r10 contains MSR_KERNEL here */ ori r10,r10,MSR_EE SYNC - MTMSRD(r10) /* hard-enable interrupts */ + mtmsr r10 /* hard-enable interrupts */ /* save r13-r31 in the exception frame, if not already done */ lwz r3,_TRAP(r1) andi. r0,r3,1 @@ -1341,7 +1341,7 @@ _GLOBAL(enter_rtas) stw r9,8(r1) LOAD_REG_IMMEDIATE(r0,MSR_KERNEL) SYNC /* disable interrupts so SRR0/1 */ - MTMSRD(r0) /* don't get trashed */ + mtmsr r0 /* don't get trashed */ li r9,MSR_KERNEL & ~(MSR_IR|MSR_DR) mtlr r6 stw r7, THREAD + RTAS_SP(r2) diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index 8abc7783dbe5..b2ca8c9ffd8b 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -50,7 +50,7 @@ rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */ #else li r10,MSR_KERNEL & ~(MSR_IR|MSR_DR) /* can take exceptions */ - MTMSRD(r10) /* (except for mach check in rtas) */ + mtmsr r10 /* (except for mach check in rtas) */ #endif stw r0,GPR0(r11) lis r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */ @@ -80,7 +80,7 @@ rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */ #else LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~(MSR_IR|MSR_DR)) /* can take exceptions */ - MTMSRD(r10) /* (except for mach check in rtas) */ + mtmsr r10 /* (except for mach check in rtas) */ #endif lis r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */ stw r2,GPR2(r11) -- cgit v1.2.3 From 1f1c4d0122eebd204468684f21f0270ea8a4999d Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:23 +0000 Subject: powerpc/32: Add EXCEPTION_PROLOG_0 in head_32.h This patch creates a macro for the very first part of exception prolog, this will help when implementing CONFIG_VMAP_STACK Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/2249fe62f481121a180e9655ad2b998093f318f3.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/head_32.S | 4 +--- arch/powerpc/kernel/head_32.h | 9 ++++++--- arch/powerpc/kernel/head_8xx.S | 9 ++------- 3 files changed, 9 insertions(+), 13 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 4a24f8f026c7..9e868567b716 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -272,9 +272,7 @@ __secondary_hold_acknowledge: */ . = 0x200 DO_KVM 0x200 - mtspr SPRN_SPRG_SCRATCH0,r10 - mtspr SPRN_SPRG_SCRATCH1,r11 - mfcr r10 + EXCEPTION_PROLOG_0 #ifdef CONFIG_PPC_CHRP mfspr r11, SPRN_SPRG_THREAD lwz r11, RTAS_SP(r11) diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index b2ca8c9ffd8b..8e345f8d4b0e 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -10,13 +10,16 @@ * We assume sprg3 has the physical address of the current * task's thread_struct. */ - .macro EXCEPTION_PROLOG + EXCEPTION_PROLOG_0 + EXCEPTION_PROLOG_1 + EXCEPTION_PROLOG_2 +.endm + +.macro EXCEPTION_PROLOG_0 mtspr SPRN_SPRG_SCRATCH0,r10 mtspr SPRN_SPRG_SCRATCH1,r11 mfcr r10 - EXCEPTION_PROLOG_1 - EXCEPTION_PROLOG_2 .endm .macro EXCEPTION_PROLOG_1 diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 19f583e18402..dac7c0a34eea 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -494,10 +494,7 @@ InstructionTLBError: */ . = 0x1400 DataTLBError: - mtspr SPRN_SPRG_SCRATCH0, r10 - mtspr SPRN_SPRG_SCRATCH1, r11 - mfcr r10 - + EXCEPTION_PROLOG_0 mfspr r11, SPRN_DAR cmpwi cr0, r11, RPN_PATTERN beq- FixupDAR /* must be a buggy dcbX, icbi insn. */ @@ -530,9 +527,7 @@ DARFixed:/* Return from dcbx instruction bug workaround */ */ . = 0x1c00 DataBreakpoint: - mtspr SPRN_SPRG_SCRATCH0, r10 - mtspr SPRN_SPRG_SCRATCH1, r11 - mfcr r10 + EXCEPTION_PROLOG_0 mfspr r11, SPRN_SRR0 cmplwi cr0, r11, (.Ldtlbie - PAGE_OFFSET)@l cmplwi cr7, r11, (.Litlbie - PAGE_OFFSET)@l -- cgit v1.2.3 From 1ca9db5b6556c38aacac4c50a617aa3f7efbb306 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:24 +0000 Subject: powerpc/32: save DEAR/DAR before calling handle_page_fault handle_page_fault() is the only function that save DAR/DEAR itself. Save DAR/DEAR before calling handle_page_fault() to prepare for VMAP stack which will require to save even before. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/3a4d58d378091086f00fde42b59610c80289e120.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/entry_32.S | 1 - arch/powerpc/kernel/head_32.S | 2 ++ arch/powerpc/kernel/head_40x.S | 2 ++ arch/powerpc/kernel/head_8xx.S | 2 ++ arch/powerpc/kernel/head_booke.h | 2 ++ arch/powerpc/kernel/head_fsl_booke.S | 1 + 6 files changed, 9 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 6273b4862482..317ad9df8ba8 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -621,7 +621,6 @@ ppc_swapcontext: */ .globl handle_page_fault handle_page_fault: - stw r4,_DAR(r1) addi r3,r1,STACK_FRAME_OVERHEAD #ifdef CONFIG_PPC_BOOK3S_32 andis. r0,r5,DSISR_DABRMATCH@h diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 9e868567b716..bebb49d877f2 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -310,6 +310,7 @@ BEGIN_MMU_FTR_SECTION END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) 1: lwz r5,_DSISR(r11) /* get DSISR value */ mfspr r4,SPRN_DAR + stw r4, _DAR(r11) EXC_XFER_LITE(0x300, handle_page_fault) @@ -327,6 +328,7 @@ BEGIN_MMU_FTR_SECTION END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) 1: mr r4,r12 andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */ + stw r4, _DAR(r11) EXC_XFER_LITE(0x400, handle_page_fault) /* External interrupt */ diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index 585ea1976550..9bb663977e84 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -313,6 +313,7 @@ _ENTRY(saved_ksp_limit) START_EXCEPTION(0x0400, InstructionAccess) EXCEPTION_PROLOG mr r4,r12 /* Pass SRR0 as arg2 */ + stw r4, _DEAR(r11) li r5,0 /* Pass zero as arg3 */ EXC_XFER_LITE(0x400, handle_page_fault) @@ -676,6 +677,7 @@ DataAccess: mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */ stw r5,_ESR(r11) mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */ + stw r4, _DEAR(r11) EXC_XFER_LITE(0x300, handle_page_fault) /* Other PowerPC processors, namely those derived from the 6xx-series diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index dac7c0a34eea..fb284d95c76a 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -486,6 +486,7 @@ InstructionTLBError: tlbie r4 /* 0x400 is InstructionAccess exception, needed by bad_page_fault() */ .Litlbie: + stw r4, _DAR(r11) EXC_XFER_LITE(0x400, handle_page_fault) /* This is the data TLB error on the MPC8xx. This could be due to @@ -504,6 +505,7 @@ DARFixed:/* Return from dcbx instruction bug workaround */ mfspr r5,SPRN_DSISR stw r5,_DSISR(r11) mfspr r4,SPRN_DAR + stw r4, _DAR(r11) andis. r10,r5,DSISR_NOHPTE@h beq+ .Ldtlbie tlbie r4 diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index 2ae635df9026..37fc84ed90e3 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -467,6 +467,7 @@ label: mfspr r5,SPRN_ESR; /* Grab the ESR and save it */ \ stw r5,_ESR(r11); \ mfspr r4,SPRN_DEAR; /* Grab the DEAR */ \ + stw r4, _DEAR(r11); \ EXC_XFER_LITE(0x0300, handle_page_fault) #define INSTRUCTION_STORAGE_EXCEPTION \ @@ -475,6 +476,7 @@ label: mfspr r5,SPRN_ESR; /* Grab the ESR and save it */ \ stw r5,_ESR(r11); \ mr r4,r12; /* Pass SRR0 as arg2 */ \ + stw r4, _DEAR(r11); \ li r5,0; /* Pass zero as arg3 */ \ EXC_XFER_LITE(0x0400, handle_page_fault) diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 6f7a3a7162c5..840af004041e 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -378,6 +378,7 @@ interrupt_base: mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */ andis. r10,r5,(ESR_ILK|ESR_DLK)@h bne 1f + stw r4, _DEAR(r11) EXC_XFER_LITE(0x0300, handle_page_fault) 1: addi r3,r1,STACK_FRAME_OVERHEAD -- cgit v1.2.3 From 5ae8fabc644632d31babbc7162aa876c79aaadb3 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:25 +0000 Subject: powerpc/32: move MSR_PR test into EXCEPTION_PROLOG_0 In order to simplify VMAP stack implementation, move MSR_PR test into EXCEPTION_PROLOG_0. This requires to not modify cr0 between EXCEPTION_PROLOG_0 and EXCEPTION_PROLOG_1. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/5c8b5bba692b92654dbd363a229a1ba91db725bb.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/head_32.h | 4 ++-- arch/powerpc/kernel/head_8xx.S | 39 ++++++++++++++++++++------------------- 2 files changed, 22 insertions(+), 21 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index 8e345f8d4b0e..436ffd862d2a 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -19,12 +19,12 @@ .macro EXCEPTION_PROLOG_0 mtspr SPRN_SPRG_SCRATCH0,r10 mtspr SPRN_SPRG_SCRATCH1,r11 + mfspr r11, SPRN_SRR1 /* check whether user or kernel */ mfcr r10 + andi. r11, r11, MSR_PR .endm .macro EXCEPTION_PROLOG_1 - mfspr r11,SPRN_SRR1 /* check whether user or kernel */ - andi. r11,r11,MSR_PR tophys(r11,r1) /* use tophys(r1) if kernel */ beq 1f mfspr r11,SPRN_SPRG_THREAD diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index fb284d95c76a..175c3cfc8014 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -497,8 +497,8 @@ InstructionTLBError: DataTLBError: EXCEPTION_PROLOG_0 mfspr r11, SPRN_DAR - cmpwi cr0, r11, RPN_PATTERN - beq- FixupDAR /* must be a buggy dcbX, icbi insn. */ + cmpwi cr1, r11, RPN_PATTERN + beq- cr1, FixupDAR /* must be a buggy dcbX, icbi insn. */ DARFixed:/* Return from dcbx instruction bug workaround */ EXCEPTION_PROLOG_1 EXCEPTION_PROLOG_2 @@ -531,9 +531,9 @@ DARFixed:/* Return from dcbx instruction bug workaround */ DataBreakpoint: EXCEPTION_PROLOG_0 mfspr r11, SPRN_SRR0 - cmplwi cr0, r11, (.Ldtlbie - PAGE_OFFSET)@l + cmplwi cr1, r11, (.Ldtlbie - PAGE_OFFSET)@l cmplwi cr7, r11, (.Litlbie - PAGE_OFFSET)@l - beq- cr0, 11f + beq- cr1, 11f beq- cr7, 11f EXCEPTION_PROLOG_1 EXCEPTION_PROLOG_2 @@ -578,9 +578,9 @@ FixupDAR:/* Entry point for dcbx workaround. */ mfspr r10, SPRN_SRR0 mtspr SPRN_MD_EPN, r10 rlwinm r11, r10, 16, 0xfff8 - cmpli cr0, r11, PAGE_OFFSET@h + cmpli cr1, r11, PAGE_OFFSET@h mfspr r11, SPRN_M_TWB /* Get level 1 table */ - blt+ 3f + blt+ cr1, 3f rlwinm r11, r10, 16, 0xfff8 0: cmpli cr7, r11, (PAGE_OFFSET + 0x1800000)@h @@ -595,7 +595,7 @@ FixupDAR:/* Entry point for dcbx workaround. */ 3: lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */ mtspr SPRN_MD_TWC, r11 - mtcr r11 + mtcrf 0x01, r11 mfspr r11, SPRN_MD_TWC lwz r11, 0(r11) /* Get the pte */ bt 28,200f /* bit 28 = Large page (8M) */ @@ -608,16 +608,16 @@ FixupDAR:/* Entry point for dcbx workaround. */ * no need to include them here */ xoris r10, r11, 0x7c00 /* check if major OP code is 31 */ rlwinm r10, r10, 0, 21, 5 - cmpwi cr0, r10, 2028 /* Is dcbz? */ - beq+ 142f - cmpwi cr0, r10, 940 /* Is dcbi? */ - beq+ 142f - cmpwi cr0, r10, 108 /* Is dcbst? */ - beq+ 144f /* Fix up store bit! */ - cmpwi cr0, r10, 172 /* Is dcbf? */ - beq+ 142f - cmpwi cr0, r10, 1964 /* Is icbi? */ - beq+ 142f + cmpwi cr1, r10, 2028 /* Is dcbz? */ + beq+ cr1, 142f + cmpwi cr1, r10, 940 /* Is dcbi? */ + beq+ cr1, 142f + cmpwi cr1, r10, 108 /* Is dcbst? */ + beq+ cr1, 144f /* Fix up store bit! */ + cmpwi cr1, r10, 172 /* Is dcbf? */ + beq+ cr1, 142f + cmpwi cr1, r10, 1964 /* Is icbi? */ + beq+ cr1, 142f 141: mfspr r10,SPRN_M_TW b DARFixed /* Nope, go back to normal TLB processing */ @@ -676,8 +676,9 @@ FixupDAR:/* Entry point for dcbx workaround. */ add r10, r10, r30 ;b 151f add r10, r10, r31 151: - rlwinm. r11,r11,19,24,28 /* offset into jump table for reg RA */ - beq 152f /* if reg RA is zero, don't add it */ + rlwinm r11,r11,19,24,28 /* offset into jump table for reg RA */ + cmpwi cr1, r11, 0 + beq cr1, 152f /* if reg RA is zero, don't add it */ addi r11, r11, 150b@l /* add start of table */ mtctr r11 /* load ctr with jump address */ rlwinm r11,r11,0,16,10 /* make sure we don't execute this more than once */ -- cgit v1.2.3 From c9c84fd945bbaadbf69d953be308e6f35737fef6 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:26 +0000 Subject: powerpc/32: add a macro to get and/or save DAR and DSISR on stack. Refactor reading and saving of DAR and DSISR in exception vectors. This will ease the implementation of VMAP stack. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1286b3e51b07727c6b4b05f2df9af3f9b1717fb5.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/head_32.S | 5 +---- arch/powerpc/kernel/head_32.h | 11 +++++++++++ arch/powerpc/kernel/head_8xx.S | 23 +++++++---------------- 3 files changed, 19 insertions(+), 20 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index bebb49d877f2..449625b4ff03 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -339,10 +339,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) DO_KVM 0x600 Alignment: EXCEPTION_PROLOG - mfspr r4,SPRN_DAR - stw r4,_DAR(r11) - mfspr r5,SPRN_DSISR - stw r5,_DSISR(r11) + save_dar_dsisr_on_stack r4, r5, r11 addi r3,r1,STACK_FRAME_OVERHEAD EXC_XFER_STD(0x600, alignment_exception) diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index 436ffd862d2a..f19a1ab91fb5 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -144,6 +144,17 @@ RFI /* jump to handler, enable MMU */ .endm +.macro save_dar_dsisr_on_stack reg1, reg2, sp + mfspr \reg1, SPRN_DAR + mfspr \reg2, SPRN_DSISR + stw \reg1, _DAR(\sp) + stw \reg2, _DSISR(\sp) +.endm + +.macro get_and_save_dar_dsisr_on_stack reg1, reg2, sp + save_dar_dsisr_on_stack \reg1, \reg2, \sp +.endm + /* * Note: code which follows this uses cr0.eq (set if from kernel), * r11, r12 (SRR0), and r9 (SRR1). diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 175c3cfc8014..25e19af49705 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -128,12 +128,9 @@ instruction_counter: . = 0x200 MachineCheck: EXCEPTION_PROLOG - mfspr r4,SPRN_DAR - stw r4,_DAR(r11) - li r5,RPN_PATTERN - mtspr SPRN_DAR,r5 /* Tag DAR, to be used in DTLB Error */ - mfspr r5,SPRN_DSISR - stw r5,_DSISR(r11) + save_dar_dsisr_on_stack r4, r5, r11 + li r6, RPN_PATTERN + mtspr SPRN_DAR, r6 /* Tag DAR, to be used in DTLB Error */ addi r3,r1,STACK_FRAME_OVERHEAD EXC_XFER_STD(0x200, machine_check_exception) @@ -156,12 +153,9 @@ InstructionAccess: . = 0x600 Alignment: EXCEPTION_PROLOG - mfspr r4,SPRN_DAR - stw r4,_DAR(r11) - li r5,RPN_PATTERN - mtspr SPRN_DAR,r5 /* Tag DAR, to be used in DTLB Error */ - mfspr r5,SPRN_DSISR - stw r5,_DSISR(r11) + save_dar_dsisr_on_stack r4, r5, r11 + li r6, RPN_PATTERN + mtspr SPRN_DAR, r6 /* Tag DAR, to be used in DTLB Error */ addi r3,r1,STACK_FRAME_OVERHEAD EXC_XFER_STD(0x600, alignment_exception) @@ -502,10 +496,7 @@ DataTLBError: DARFixed:/* Return from dcbx instruction bug workaround */ EXCEPTION_PROLOG_1 EXCEPTION_PROLOG_2 - mfspr r5,SPRN_DSISR - stw r5,_DSISR(r11) - mfspr r4,SPRN_DAR - stw r4, _DAR(r11) + get_and_save_dar_dsisr_on_stack r4, r5, r11 andis. r10,r5,DSISR_NOHPTE@h beq+ .Ldtlbie tlbie r4 -- 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/kernel/asm-offsets.c | 6 ++ arch/powerpc/kernel/entry_32.S | 4 +- arch/powerpc/kernel/head_32.h | 128 +++++++++++++++++++++++++++++++++----- 3 files changed, 122 insertions(+), 16 deletions(-) (limited to 'arch/powerpc/kernel') 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/kernel/setup_32.c | 2 +- arch/powerpc/kernel/setup_64.c | 2 +- arch/powerpc/kernel/vmlinux.lds.S | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/kernel') 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 3978eb78517c1fc06dd75405d732af45c80f5bd2 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:29 +0000 Subject: powerpc/32: Add early stack overflow detection with VMAP stack. To avoid recursive faults, stack overflow detection has to be performed before writing in the stack in exception prologs. Do it by checking the alignment. If the stack pointer alignment is wrong, it means it is pointing to the following or preceding page. Without VMAP stack, a stack overflow is catastrophic. With VMAP stack, a stack overflow isn't destructive, so don't panic. Kill the task with SIGSEGV instead. A dedicated overflow stack is set up for each CPU. lkdtm: Performing direct entry EXHAUST_STACK lkdtm: Calling function with 512 frame size to depth 32 ... lkdtm: loop 32/32 ... lkdtm: loop 31/32 ... lkdtm: loop 30/32 ... lkdtm: loop 29/32 ... lkdtm: loop 28/32 ... lkdtm: loop 27/32 ... lkdtm: loop 26/32 ... lkdtm: loop 25/32 ... lkdtm: loop 24/32 ... lkdtm: loop 23/32 ... lkdtm: loop 22/32 ... lkdtm: loop 21/32 ... lkdtm: loop 20/32 ... Kernel stack overflow in process test[359], r1=c900c008 Oops: Kernel stack overflow, sig: 6 [#1] BE PAGE_SIZE=4K MMU=Hash PowerMac Modules linked in: CPU: 0 PID: 359 Comm: test Not tainted 5.3.0-rc7+ #2225 NIP: c0622060 LR: c0626710 CTR: 00000000 REGS: c0895f48 TRAP: 0000 Not tainted (5.3.0-rc7+) MSR: 00001032 CR: 28004224 XER: 00000000 GPR00: c0626ca4 c900c008 c783c000 c07335cc c900c010 c07335cc c900c0f0 c07335cc GPR08: c900c0f0 00000001 00000000 00000000 28008222 00000000 00000000 00000000 GPR16: 00000000 00000000 10010128 10010000 b799c245 10010158 c07335cc 00000025 GPR24: c0690000 c08b91d4 c068f688 00000020 c900c0f0 c068f668 c08b95b4 c08b91d4 NIP [c0622060] format_decode+0x0/0x4d4 LR [c0626710] vsnprintf+0x80/0x5fc Call Trace: [c900c068] [c0626ca4] vscnprintf+0x18/0x48 [c900c078] [c007b944] vprintk_store+0x40/0x214 [c900c0b8] [c007bf50] vprintk_emit+0x90/0x1dc [c900c0e8] [c007c5cc] printk+0x50/0x60 [c900c128] [c03da5b0] recursive_loop+0x44/0x6c [c900c338] [c03da5c4] recursive_loop+0x58/0x6c [c900c548] [c03da5c4] recursive_loop+0x58/0x6c [c900c758] [c03da5c4] recursive_loop+0x58/0x6c [c900c968] [c03da5c4] recursive_loop+0x58/0x6c [c900cb78] [c03da5c4] recursive_loop+0x58/0x6c [c900cd88] [c03da5c4] recursive_loop+0x58/0x6c [c900cf98] [c03da5c4] recursive_loop+0x58/0x6c [c900d1a8] [c03da5c4] recursive_loop+0x58/0x6c [c900d3b8] [c03da5c4] recursive_loop+0x58/0x6c [c900d5c8] [c03da5c4] recursive_loop+0x58/0x6c [c900d7d8] [c03da5c4] recursive_loop+0x58/0x6c [c900d9e8] [c03da5c4] recursive_loop+0x58/0x6c [c900dbf8] [c03da5c4] recursive_loop+0x58/0x6c [c900de08] [c03da67c] lkdtm_EXHAUST_STACK+0x30/0x4c [c900de18] [c03da3e8] direct_entry+0xc8/0x140 [c900de48] [c029fb40] full_proxy_write+0x64/0xcc [c900de68] [c01500f8] __vfs_write+0x30/0x1d0 [c900dee8] [c0152cb8] vfs_write+0xb8/0x1d4 [c900df08] [c0152f7c] ksys_write+0x58/0xe8 [c900df38] [c0014208] ret_from_syscall+0x0/0x34 --- interrupt: c01 at 0xf806664 LR = 0x1000c868 Instruction dump: 4bffff91 80010014 7c832378 7c0803a6 38210010 4e800020 3d20c08a 3ca0c089 8089a0cc 38a58f0c 38600001 4ba2d494 <9421ffe0> 7c0802a6 bfc10018 7c9f2378 Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1b89c121b4070c7ee99e4f22cc178f15a736b07b.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/entry_32.S | 4 ++++ arch/powerpc/kernel/head_32.h | 28 ++++++++++++++++++++++++++++ arch/powerpc/kernel/setup.h | 2 +- arch/powerpc/kernel/setup_32.c | 12 ++++++++++++ arch/powerpc/kernel/traps.c | 9 +++++++++ 5 files changed, 54 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 8f6617cf2689..7e5a1722e4f2 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -182,9 +182,11 @@ transfer_to_handler: */ kuap_save_and_lock r11, r12, r9, r2, r0 addi r2, r12, -THREAD +#ifndef CONFIG_VMAP_STACK lwz r9,KSP_LIMIT(r12) cmplw r1,r9 /* if r1 <= ksp_limit */ ble- stack_ovf /* then the kernel stack overflowed */ +#endif 5: #if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500) lwz r12,TI_LOCAL_FLAGS(r2) @@ -289,6 +291,7 @@ reenable_mmu: b fast_exception_return #endif +#ifndef CONFIG_VMAP_STACK /* * On kernel stack overflow, load up an initial stack pointer * and call StackOverflow(regs), which should not return. @@ -314,6 +317,7 @@ stack_ovf: mtspr SPRN_SRR1,r10 SYNC RFI +#endif #ifdef CONFIG_TRACE_IRQFLAGS trace_syscall_entry_irq_off: diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index e36987aede86..c39209d56020 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -55,6 +55,10 @@ addi r11, r11, THREAD_SIZE - INT_FRAME_SIZE tophys_novmstack r11, r11 1: +#ifdef CONFIG_VMAP_STACK + mtcrf 0x7f, r11 + bt 32 - THREAD_ALIGN_SHIFT, stack_overflow +#endif .endm .macro EXCEPTION_PROLOG_2 handle_dar_dsisr=0 @@ -299,4 +303,28 @@ label: EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, transfer_to_handler, \ ret_from_except) +.macro vmap_stack_overflow_exception +#ifdef CONFIG_VMAP_STACK +#ifdef CONFIG_SMP + mfspr r11, SPRN_SPRG_THREAD + tovirt(r11, r11) + lwz r11, TASK_CPU - THREAD(r11) + slwi r11, r11, 3 + addis r11, r11, emergency_ctx@ha +#else + lis r11, emergency_ctx@ha +#endif + lwz r11, emergency_ctx@l(r11) + cmpwi cr1, r11, 0 + bne cr1, 1f + lis r11, init_thread_union@ha + addi r11, r11, init_thread_union@l +1: addi r11, r11, THREAD_SIZE - INT_FRAME_SIZE + EXCEPTION_PROLOG_2 + SAVE_NVGPRS(r11) + addi r3, r1, STACK_FRAME_OVERHEAD + EXC_XFER_STD(0, stack_overflow_exception) +#endif +.endm + #endif /* __HEAD_32_H__ */ diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h index c82577c4b15d..2dd0d9cb5a20 100644 --- a/arch/powerpc/kernel/setup.h +++ b/arch/powerpc/kernel/setup.h @@ -35,7 +35,7 @@ void exc_lvl_early_init(void); static inline void exc_lvl_early_init(void) { }; #endif -#ifdef CONFIG_PPC64 +#if defined(CONFIG_PPC64) || defined(CONFIG_VMAP_STACK) void emergency_stack_init(void); #else static inline void emergency_stack_init(void) { }; diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index f014c4f7a337..a55b4d9ab824 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -161,6 +161,18 @@ void __init irqstack_early_init(void) } } +#ifdef CONFIG_VMAP_STACK +void *emergency_ctx[NR_CPUS] __ro_after_init; + +void __init emergency_stack_init(void) +{ + unsigned int i; + + for_each_possible_cpu(i) + emergency_ctx[i] = alloc_stack(); +} +#endif + #if defined(CONFIG_BOOKE) || defined(CONFIG_40x) void __init exc_lvl_early_init(void) { diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 014ff0701f24..82a3438300fd 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1637,6 +1637,15 @@ void StackOverflow(struct pt_regs *regs) panic("kernel stack overflow"); } +void stack_overflow_exception(struct pt_regs *regs) +{ + enum ctx_state prev_state = exception_enter(); + + die("Kernel stack overflow", regs, SIGSEGV); + + exception_exit(prev_state); +} + void kernel_fp_unavailable_exception(struct pt_regs *regs) { enum ctx_state prev_state = exception_enter(); -- cgit v1.2.3 From 547db12fd8a0ce753c6bafd130827f1755c93fe6 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:30 +0000 Subject: powerpc/32: Use vmapped stacks for interrupts In order to also catch overflows on IRQ stacks, use vmapped stacks. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/d33ad1b36ddff4dcc19f96c592c12a61cf85d406.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/irq.c | 22 ++++++++++++++++++++++ arch/powerpc/kernel/setup_32.c | 3 +++ 2 files changed, 25 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index add67498c126..5c9b11878555 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -50,6 +50,7 @@ #include #include #include +#include #include #include @@ -664,8 +665,29 @@ void do_IRQ(struct pt_regs *regs) set_irq_regs(old_regs); } +static void *__init alloc_vm_stack(void) +{ + return __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, VMALLOC_START, + VMALLOC_END, THREADINFO_GFP, PAGE_KERNEL, + 0, NUMA_NO_NODE, (void*)_RET_IP_); +} + +static void __init vmap_irqstack_init(void) +{ + int i; + + for_each_possible_cpu(i) { + softirq_ctx[i] = alloc_vm_stack(); + hardirq_ctx[i] = alloc_vm_stack(); + } +} + + void __init init_IRQ(void) { + if (IS_ENABLED(CONFIG_VMAP_STACK)) + vmap_irqstack_init(); + if (ppc_md.init_IRQ) ppc_md.init_IRQ(); } diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index a55b4d9ab824..5b49b26eb154 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -153,6 +153,9 @@ void __init irqstack_early_init(void) { unsigned int i; + if (IS_ENABLED(CONFIG_VMAP_STACK)) + return; + /* interrupt stacks must be in lowmem, we get that for free on ppc32 * as the memblock is limited to lowmem by default */ for_each_possible_cpu(i) { -- cgit v1.2.3 From 6edc318585410b9cae5a7e4d156f09c8e5e3a700 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:31 +0000 Subject: powerpc/8xx: Use alternative scratch registers in DTLB miss handler In preparation of handling CONFIG_VMAP_STACK, DTLB miss handler need to use different scratch registers than other exception handlers in order to not jeopardise exception entry on stack DTLB misses. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/c5287ea59ae9630f505019b309bf94029241635f.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/head_8xx.S | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 25e19af49705..3de9c5f1746c 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -193,8 +193,9 @@ SystemCall: 0: lwz r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0) addi r10, r10, 1 stw r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0) - mfspr r10, SPRN_SPRG_SCRATCH0 - mfspr r11, SPRN_SPRG_SCRATCH1 + mfspr r10, SPRN_DAR + mtspr SPRN_DAR, r11 /* Tag DAR */ + mfspr r11, SPRN_M_TW rfi #endif @@ -337,8 +338,8 @@ ITLBMissLinear: . = 0x1200 DataStoreTLBMiss: - mtspr SPRN_SPRG_SCRATCH0, r10 - mtspr SPRN_SPRG_SCRATCH1, r11 + mtspr SPRN_DAR, r10 + mtspr SPRN_M_TW, r11 mfcr r11 /* If we are faulting a kernel address, we have to use the @@ -403,10 +404,10 @@ DataStoreTLBMiss: mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ /* Restore registers */ - mtspr SPRN_DAR, r11 /* Tag DAR */ -0: mfspr r10, SPRN_SPRG_SCRATCH0 - mfspr r11, SPRN_SPRG_SCRATCH1 +0: mfspr r10, SPRN_DAR + mtspr SPRN_DAR, r11 /* Tag DAR */ + mfspr r11, SPRN_M_TW rfi patch_site 0b, patch__dtlbmiss_exit_1 @@ -422,10 +423,10 @@ DTLBMissIMMR: mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ li r11, RPN_PATTERN - mtspr SPRN_DAR, r11 /* Tag DAR */ -0: mfspr r10, SPRN_SPRG_SCRATCH0 - mfspr r11, SPRN_SPRG_SCRATCH1 +0: mfspr r10, SPRN_DAR + mtspr SPRN_DAR, r11 /* Tag DAR */ + mfspr r11, SPRN_M_TW rfi patch_site 0b, patch__dtlbmiss_exit_2 @@ -459,10 +460,10 @@ DTLBMissLinear: mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ li r11, RPN_PATTERN - mtspr SPRN_DAR, r11 /* Tag DAR */ -0: mfspr r10, SPRN_SPRG_SCRATCH0 - mfspr r11, SPRN_SPRG_SCRATCH1 +0: mfspr r10, SPRN_DAR + mtspr SPRN_DAR, r11 /* Tag DAR */ + mfspr r11, SPRN_M_TW rfi patch_site 0b, patch__dtlbmiss_exit_3 -- cgit v1.2.3 From 9260f76ae2533787e92be58d5e509e81b72f5f9c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:32 +0000 Subject: powerpc/8xx: Drop exception entries for non-existing exceptions head_8xx.S has entries for all exceptions from 0x100 to 0x1f00. Several of them do not exist and are never generated by the 8xx in accordance with the documentation. Remove those entry points to make some room for future growing exception code. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/66f92866fe9524cf0f056016921c7d53adaef3a0.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/head_8xx.S | 29 ----------------------------- 1 file changed, 29 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 3de9c5f1746c..5aa63693f790 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -134,18 +134,6 @@ MachineCheck: addi r3,r1,STACK_FRAME_OVERHEAD EXC_XFER_STD(0x200, machine_check_exception) -/* Data access exception. - * This is "never generated" by the MPC8xx. - */ - . = 0x300 -DataAccess: - -/* Instruction access exception. - * This is "never generated" by the MPC8xx. - */ - . = 0x400 -InstructionAccess: - /* External interrupt */ EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE) @@ -162,16 +150,9 @@ Alignment: /* Program check exception */ EXCEPTION(0x700, ProgramCheck, program_check_exception, EXC_XFER_STD) -/* No FPU on MPC8xx. This exception is not supposed to happen. -*/ - EXCEPTION(0x800, FPUnavailable, unknown_exception, EXC_XFER_STD) - /* Decrementer */ EXCEPTION(0x900, Decrementer, timer_interrupt, EXC_XFER_LITE) - EXCEPTION(0xa00, Trap_0a, unknown_exception, EXC_XFER_STD) - EXCEPTION(0xb00, Trap_0b, unknown_exception, EXC_XFER_STD) - /* System call */ . = 0xc00 SystemCall: @@ -179,8 +160,6 @@ SystemCall: /* Single step - not used on 601 */ EXCEPTION(0xd00, SingleStep, single_step_exception, EXC_XFER_STD) - EXCEPTION(0xe00, Trap_0e, unknown_exception, EXC_XFER_STD) - EXCEPTION(0xf00, Trap_0f, unknown_exception, EXC_XFER_STD) /* On the MPC8xx, this is a software emulation interrupt. It occurs * for all unimplemented and illegal instructions. @@ -507,14 +486,6 @@ DARFixed:/* Return from dcbx instruction bug workaround */ /* 0x300 is DataAccess exception, needed by bad_page_fault() */ EXC_XFER_LITE(0x300, handle_page_fault) - EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_STD) - EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_STD) - EXCEPTION(0x1700, Trap_17, unknown_exception, EXC_XFER_STD) - EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_STD) - EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_STD) - EXCEPTION(0x1a00, Trap_1a, unknown_exception, EXC_XFER_STD) - EXCEPTION(0x1b00, Trap_1b, unknown_exception, EXC_XFER_STD) - /* On the MPC8xx, these next four traps are used for development * support of breakpoints and such. Someday I will get around to * using them. -- cgit v1.2.3 From 596419afed72656a4529d3d67475e4b2b1912485 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:33 +0000 Subject: powerpc/8xx: Move DataStoreTLBMiss perf handler Move DataStoreTLBMiss perf handler in order to cope with future growing exception prolog. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/75dd28b04efd2cbdbf01153173d99c11cdff2f08.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/head_8xx.S | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 5aa63693f790..1e718e47fe3c 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -166,18 +166,6 @@ SystemCall: */ EXCEPTION(0x1000, SoftEmu, program_check_exception, EXC_XFER_STD) -/* Called from DataStoreTLBMiss when perf TLB misses events are activated */ -#ifdef CONFIG_PERF_EVENTS - patch_site 0f, patch__dtlbmiss_perf -0: lwz r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0) - addi r10, r10, 1 - stw r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0) - mfspr r10, SPRN_DAR - mtspr SPRN_DAR, r11 /* Tag DAR */ - mfspr r11, SPRN_M_TW - rfi -#endif - . = 0x1100 /* * For the MPC8xx, this is a software tablewalk to load the instruction @@ -486,6 +474,18 @@ DARFixed:/* Return from dcbx instruction bug workaround */ /* 0x300 is DataAccess exception, needed by bad_page_fault() */ EXC_XFER_LITE(0x300, handle_page_fault) +/* Called from DataStoreTLBMiss when perf TLB misses events are activated */ +#ifdef CONFIG_PERF_EVENTS + patch_site 0f, patch__dtlbmiss_perf +0: lwz r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0) + addi r10, r10, 1 + stw r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0) + mfspr r10, SPRN_DAR + mtspr SPRN_DAR, r11 /* Tag DAR */ + mfspr r11, SPRN_M_TW + rfi +#endif + /* On the MPC8xx, these next four traps are used for development * support of breakpoints and such. Someday I will get around to * using them. -- cgit v1.2.3 From afe1ec5ab83029baf0f8368a255dc6b998bde576 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:34 +0000 Subject: powerpc/8xx: Split breakpoint exception Breakpoint exception is big. Split it to support future growth on exception prolog. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1dda3293d86d0f715b13b2633c95d2188a42a02c.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/head_8xx.S | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 1e718e47fe3c..225e242ce1c5 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -490,14 +490,7 @@ DARFixed:/* Return from dcbx instruction bug workaround */ * support of breakpoints and such. Someday I will get around to * using them. */ - . = 0x1c00 -DataBreakpoint: - EXCEPTION_PROLOG_0 - mfspr r11, SPRN_SRR0 - cmplwi cr1, r11, (.Ldtlbie - PAGE_OFFSET)@l - cmplwi cr7, r11, (.Litlbie - PAGE_OFFSET)@l - beq- cr1, 11f - beq- cr7, 11f +do_databreakpoint: EXCEPTION_PROLOG_1 EXCEPTION_PROLOG_2 addi r3,r1,STACK_FRAME_OVERHEAD @@ -505,7 +498,15 @@ DataBreakpoint: stw r4,_DAR(r11) mfspr r5,SPRN_DSISR EXC_XFER_STD(0x1c00, do_break) -11: + + . = 0x1c00 +DataBreakpoint: + EXCEPTION_PROLOG_0 + mfspr r11, SPRN_SRR0 + cmplwi cr1, r11, (.Ldtlbie - PAGE_OFFSET)@l + cmplwi cr7, r11, (.Litlbie - PAGE_OFFSET)@l + cror 4*cr1+eq, 4*cr1+eq, 4*cr7+eq + bne cr1, do_databreakpoint mtcr r10 mfspr r10, SPRN_SPRG_SCRATCH0 mfspr r11, SPRN_SPRG_SCRATCH1 -- cgit v1.2.3 From d52668f6b3e052fa97e93e536c492f5880c73474 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Sun, 26 Jan 2020 00:20:16 +1100 Subject: powerpc/8xx: Move tail of alignment exception out of line When we enable VMAP_STACK there will not be enough room for the alignment handler at 0x600 in head_8xx.S. For now move the tail of the alignment handler out of line, and branch to it. Suggested-by: Christophe Leroy Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/head_8xx.S | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 225e242ce1c5..a6b1b7af2217 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -145,7 +145,7 @@ Alignment: li r6, RPN_PATTERN mtspr SPRN_DAR, r6 /* Tag DAR, to be used in DTLB Error */ addi r3,r1,STACK_FRAME_OVERHEAD - EXC_XFER_STD(0x600, alignment_exception) + b .Lalignment_exception_ool /* Program check exception */ EXCEPTION(0x700, ProgramCheck, program_check_exception, EXC_XFER_STD) @@ -153,6 +153,11 @@ Alignment: /* Decrementer */ EXCEPTION(0x900, Decrementer, timer_interrupt, EXC_XFER_LITE) + /* With VMAP_STACK there's not enough room for this at 0x600 */ + . = 0xa00 +.Lalignment_exception_ool: + EXC_XFER_STD(0x600, alignment_exception) + /* System call */ . = 0xc00 SystemCall: -- cgit v1.2.3 From 99b229161f8d99742cdfd6be21059ebd9eb7b696 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:35 +0000 Subject: powerpc/8xx: Enable CONFIG_VMAP_STACK This patch enables CONFIG_VMAP_STACK. For that, a few changes are done in head_8xx.S. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/d7ba1e34e80898310d6a314cbebe48baa32894ef.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/head_8xx.S | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index a6b1b7af2217..9922306ae512 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -127,7 +127,7 @@ instruction_counter: /* Machine check */ . = 0x200 MachineCheck: - EXCEPTION_PROLOG + EXCEPTION_PROLOG handle_dar_dsisr=1 save_dar_dsisr_on_stack r4, r5, r11 li r6, RPN_PATTERN mtspr SPRN_DAR, r6 /* Tag DAR, to be used in DTLB Error */ @@ -140,7 +140,7 @@ MachineCheck: /* Alignment exception */ . = 0x600 Alignment: - EXCEPTION_PROLOG + EXCEPTION_PROLOG handle_dar_dsisr=1 save_dar_dsisr_on_stack r4, r5, r11 li r6, RPN_PATTERN mtspr SPRN_DAR, r6 /* Tag DAR, to be used in DTLB Error */ @@ -462,20 +462,26 @@ InstructionTLBError: */ . = 0x1400 DataTLBError: - EXCEPTION_PROLOG_0 + EXCEPTION_PROLOG_0 handle_dar_dsisr=1 mfspr r11, SPRN_DAR cmpwi cr1, r11, RPN_PATTERN beq- cr1, FixupDAR /* must be a buggy dcbX, icbi insn. */ DARFixed:/* Return from dcbx instruction bug workaround */ +#ifdef CONFIG_VMAP_STACK + li r11, RPN_PATTERN + mtspr SPRN_DAR, r11 /* Tag DAR, to be used in DTLB Error */ +#endif EXCEPTION_PROLOG_1 - EXCEPTION_PROLOG_2 + EXCEPTION_PROLOG_2 handle_dar_dsisr=1 get_and_save_dar_dsisr_on_stack r4, r5, r11 andis. r10,r5,DSISR_NOHPTE@h beq+ .Ldtlbie tlbie r4 .Ldtlbie: +#ifndef CONFIG_VMAP_STACK li r10,RPN_PATTERN mtspr SPRN_DAR,r10 /* Tag DAR, to be used in DTLB Error */ +#endif /* 0x300 is DataAccess exception, needed by bad_page_fault() */ EXC_XFER_LITE(0x300, handle_page_fault) @@ -491,22 +497,29 @@ DARFixed:/* Return from dcbx instruction bug workaround */ rfi #endif +stack_overflow: + vmap_stack_overflow_exception + /* On the MPC8xx, these next four traps are used for development * support of breakpoints and such. Someday I will get around to * using them. */ do_databreakpoint: EXCEPTION_PROLOG_1 - EXCEPTION_PROLOG_2 + EXCEPTION_PROLOG_2 handle_dar_dsisr=1 addi r3,r1,STACK_FRAME_OVERHEAD mfspr r4,SPRN_BAR stw r4,_DAR(r11) +#ifdef CONFIG_VMAP_STACK + lwz r5,_DSISR(r11) +#else mfspr r5,SPRN_DSISR +#endif EXC_XFER_STD(0x1c00, do_break) . = 0x1c00 DataBreakpoint: - EXCEPTION_PROLOG_0 + EXCEPTION_PROLOG_0 handle_dar_dsisr=1 mfspr r11, SPRN_SRR0 cmplwi cr1, r11, (.Ldtlbie - PAGE_OFFSET)@l cmplwi cr7, r11, (.Litlbie - PAGE_OFFSET)@l @@ -655,7 +668,14 @@ FixupDAR:/* Entry point for dcbx workaround. */ 152: mfdar r11 mtctr r11 /* restore ctr reg from DAR */ +#ifdef CONFIG_VMAP_STACK + mfspr r11, SPRN_SPRG_THREAD + stw r10, DAR(r11) + mfspr r10, SPRN_DSISR + stw r10, DSISR(r11) +#else mtdar r10 /* save fault EA to DAR */ +#endif mfspr r10,SPRN_M_TW b DARFixed /* Go back to normal TLB handling */ -- cgit v1.2.3 From 2e15001ea9ea110837a6eb6dba518416dedb4c39 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:36 +0000 Subject: powerpc/32s: Reorganise DSI handler. The part decidated to handling hash_page() is fully unneeded for processors not having real hash pages like the 603. Lets enlarge the content of the feature fixup, and provide an alternative which jumps directly instead of getting NIPs. Also, in preparation of VMAP stacks, the end of DSI handler has moved to later in the code as it won't fit anymore once VMAP stacks are there. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/c31b22c91af8b011d0a4fd9e52ad6afb4b593f71.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/head_32.S | 31 +++++++++++++++++-------------- 1 file changed, 17 insertions(+), 14 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 449625b4ff03..7ec780858299 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -295,24 +295,20 @@ __secondary_hold_acknowledge: DO_KVM 0x300 DataAccess: EXCEPTION_PROLOG - mfspr r10,SPRN_DSISR - stw r10,_DSISR(r11) + get_and_save_dar_dsisr_on_stack r4, r5, r11 +BEGIN_MMU_FTR_SECTION #ifdef CONFIG_PPC_KUAP - andis. r0,r10,(DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h + andis. r0, r5, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h #else - andis. r0,r10,(DSISR_BAD_FAULT_32S|DSISR_DABRMATCH)@h + andis. r0, r5, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH)@h #endif - bne 1f /* if not, try to put a PTE */ - mfspr r4,SPRN_DAR /* into the hash table */ - rlwinm r3,r10,32-15,21,21 /* DSISR_STORE -> _PAGE_RW */ -BEGIN_MMU_FTR_SECTION + bne handle_page_fault_tramp_2 /* if not, try to put a PTE */ + rlwinm r3, r5, 32 - 15, 21, 21 /* DSISR_STORE -> _PAGE_RW */ bl hash_page -END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) -1: lwz r5,_DSISR(r11) /* get DSISR value */ - mfspr r4,SPRN_DAR - stw r4, _DAR(r11) - EXC_XFER_LITE(0x300, handle_page_fault) - + b handle_page_fault_tramp_1 +FTR_SECTION_ELSE + b handle_page_fault_tramp_2 +ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE) /* Instruction access exception. */ . = 0x400 @@ -642,6 +638,13 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU) . = 0x3000 +handle_page_fault_tramp_1: + lwz r4, _DAR(r11) + lwz r5, _DSISR(r11) + /* fall through */ +handle_page_fault_tramp_2: + EXC_XFER_LITE(0x300, handle_page_fault) + AltiVecUnavailable: EXCEPTION_PROLOG #ifdef CONFIG_ALTIVEC -- cgit v1.2.3 From 94dd54c51a410b9ffa6356c3ed2ab0317f998ded Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:37 +0000 Subject: powerpc/32s: Avoid crossing page boundary while changing SRR0/1. Trying VMAP_STACK with KVM, vmlinux was not starting. This was due to SRR0 and SRR1 clobbered by an ISI due to the rfi being in a different page than the mtsrr0/1: c0003fe0 : c0003fe0: 38 83 00 54 addi r4,r3,84 c0003fe4: 7c 60 00 a6 mfmsr r3 c0003fe8: 70 60 00 30 andi. r0,r3,48 c0003fec: 4d 82 00 20 beqlr c0003ff0: 7c 63 00 78 andc r3,r3,r0 c0003ff4: 7c 9a 03 a6 mtsrr0 r4 c0003ff8: 7c 7b 03 a6 mtsrr1 r3 c0003ffc: 7c 00 04 ac hwsync c0004000: 4c 00 00 64 rfi Align the 4 instruction block used to deactivate MMU to order 4, so that the block never crosses a page boundary. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/30d2cda111b7977227fff067fa7e358440e2b3a4.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/head_32.S | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 7ec780858299..90ef355e958b 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -917,6 +917,8 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) ori r4,r4,2f@l tophys(r4,r4) li r3,MSR_KERNEL & ~(MSR_IR|MSR_DR) + + .align 4 mtspr SPRN_SRR0,r4 mtspr SPRN_SRR1,r3 SYNC @@ -1058,6 +1060,8 @@ _ENTRY(update_bats) rlwinm r0, r6, 0, ~MSR_RI rlwinm r0, r0, 0, ~MSR_EE mtmsr r0 + + .align 4 mtspr SPRN_SRR0, r4 mtspr SPRN_SRR1, r3 SYNC @@ -1097,6 +1101,8 @@ mmu_off: andi. r0,r3,MSR_DR|MSR_IR /* MMU enabled? */ beqlr andc r3,r3,r0 + + .align 4 mtspr SPRN_SRR0,r4 mtspr SPRN_SRR1,r3 sync -- cgit v1.2.3 From cd08f109e26231b279bcc0388428afcac6408ec6 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 21 Dec 2019 08:32:38 +0000 Subject: powerpc/32s: Enable CONFIG_VMAP_STACK A few changes to retrieve DAR and DSISR from struct regs instead of retrieving them directly, as they may have changed due to a TLB miss. Also modifies hash_page() and friends to work with virtual data addresses instead of physical ones. Same on load_up_fpu() and load_up_altivec(). Signed-off-by: Christophe Leroy [mpe: Fix tovirt_vmstack call in head_32.S to fix CHRP build] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/2e2509a242fd5f3e23df4a06530c18060c4d321e.1576916812.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/entry_32.S | 2 +- arch/powerpc/kernel/fpu.S | 3 +++ arch/powerpc/kernel/head_32.S | 16 +++++++++++++--- arch/powerpc/kernel/head_32.h | 4 +++- arch/powerpc/kernel/vector.S | 3 +++ 5 files changed, 23 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 7e5a1722e4f2..3795654d15d1 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -1339,7 +1339,7 @@ _GLOBAL(enter_rtas) lis r6,1f@ha /* physical return address for rtas */ addi r6,r6,1f@l tophys(r6,r6) - tophys(r7,r1) + tophys_novmstack r7, r1 lwz r8,RTASENTRY(r4) lwz r4,RTASBASE(r4) mfmsr r9 diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 0bb991ddd264..3235a8da6af7 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -94,6 +94,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) /* enable use of FP after return */ #ifdef CONFIG_PPC32 mfspr r5,SPRN_SPRG_THREAD /* current task's THREAD (phys) */ +#ifdef CONFIG_VMAP_STACK + tovirt(r5, r5) +#endif lwz r4,THREAD_FPEXC_MODE(r5) ori r9,r9,MSR_FP /* enable FP for current */ or r9,r9,r4 diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 90ef355e958b..0493fcac6409 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -272,14 +272,21 @@ __secondary_hold_acknowledge: */ . = 0x200 DO_KVM 0x200 +MachineCheck: EXCEPTION_PROLOG_0 +#ifdef CONFIG_VMAP_STACK + li r11, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */ + mtmsr r11 + isync +#endif #ifdef CONFIG_PPC_CHRP mfspr r11, SPRN_SPRG_THREAD + tovirt_vmstack r11, r11 lwz r11, RTAS_SP(r11) cmpwi cr1, r11, 0 bne cr1, 7f #endif /* CONFIG_PPC_CHRP */ - EXCEPTION_PROLOG_1 + EXCEPTION_PROLOG_1 for_rtas=1 7: EXCEPTION_PROLOG_2 addi r3,r1,STACK_FRAME_OVERHEAD #ifdef CONFIG_PPC_CHRP @@ -294,7 +301,7 @@ __secondary_hold_acknowledge: . = 0x300 DO_KVM 0x300 DataAccess: - EXCEPTION_PROLOG + EXCEPTION_PROLOG handle_dar_dsisr=1 get_and_save_dar_dsisr_on_stack r4, r5, r11 BEGIN_MMU_FTR_SECTION #ifdef CONFIG_PPC_KUAP @@ -334,7 +341,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) . = 0x600 DO_KVM 0x600 Alignment: - EXCEPTION_PROLOG + EXCEPTION_PROLOG handle_dar_dsisr=1 save_dar_dsisr_on_stack r4, r5, r11 addi r3,r1,STACK_FRAME_OVERHEAD EXC_XFER_STD(0x600, alignment_exception) @@ -645,6 +652,9 @@ handle_page_fault_tramp_1: handle_page_fault_tramp_2: EXC_XFER_LITE(0x300, handle_page_fault) +stack_overflow: + vmap_stack_overflow_exception + AltiVecUnavailable: EXCEPTION_PROLOG #ifdef CONFIG_ALTIVEC diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index c39209d56020..a6a5fbbf8504 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -38,11 +38,13 @@ andi. r11, r11, MSR_PR .endm -.macro EXCEPTION_PROLOG_1 +.macro EXCEPTION_PROLOG_1 for_rtas=0 #ifdef CONFIG_VMAP_STACK + .ifeq \for_rtas li r11, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */ mtmsr r11 isync + .endif subi r11, r1, INT_FRAME_SIZE /* use r1 if kernel */ #else tophys(r11,r1) /* use tophys(r1) if kernel */ diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 8eb867dbad5f..25c14a0981bf 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -67,6 +67,9 @@ _GLOBAL(load_up_altivec) #ifdef CONFIG_PPC32 mfspr r5,SPRN_SPRG_THREAD /* current task's THREAD (phys) */ oris r9,r9,MSR_VEC@h +#ifdef CONFIG_VMAP_STACK + tovirt(r5, r5) +#endif #else ld r4,PACACURRENT(r13) addi r5,r4,THREAD /* Get THREAD */ -- cgit v1.2.3 From 9933819099c4600b41a042f27a074470a43cf6b9 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 27 Jan 2020 10:42:04 +0000 Subject: powerpc/32s: Fix CPU wake-up from sleep mode Commit f7354ccac844 ("powerpc/32: Remove CURRENT_THREAD_INFO and rename TI_CPU") broke the CPU wake-up from sleep mode (i.e. when _TLF_SLEEPING is set) by delaying the tovirt(r2, r2). This is because r2 is not restored by fast_exception_return. It used to work (by chance ?) because CPU wake-up interrupt never comes from user, so r2 is expected to point to 'current' on return. Commit e2fb9f544431 ("powerpc/32: Prepare for Kernel Userspace Access Protection") broke it even more by clobbering r0 which is not restored by fast_exception_return either. Use r6 instead of r0. This is possible because r3-r6 are restored by fast_exception_return and only r3-r5 are used for exception arguments. For r2 it could be converted back to virtual address, but stay on the safe side and restore it from the stack instead. It should be live in the cache at that moment, so loading from the stack should make no difference compared to converting it from phys to virt. Fixes: f7354ccac844 ("powerpc/32: Remove CURRENT_THREAD_INFO and rename TI_CPU") Fixes: e2fb9f544431 ("powerpc/32: Prepare for Kernel Userspace Access Protection") Cc: stable@vger.kernel.org Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/6d02c3ae6ad77af34392e98117e44c2bf6d13ba1.1580121710.git.christophe.leroy@c-s.fr --- arch/powerpc/kernel/entry_32.S | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 3795654d15d1..ac27b6b136d0 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -180,7 +180,7 @@ transfer_to_handler: 2: /* if from kernel, check interrupted DOZE/NAP mode and * check for stack overflow */ - kuap_save_and_lock r11, r12, r9, r2, r0 + kuap_save_and_lock r11, r12, r9, r2, r6 addi r2, r12, -THREAD #ifndef CONFIG_VMAP_STACK lwz r9,KSP_LIMIT(r12) @@ -288,6 +288,7 @@ reenable_mmu: rlwinm r9,r9,0,~MSR_EE lwz r12,_LINK(r11) /* and return to address in LR */ kuap_restore r11, r2, r3, r4, r5 + lwz r2, GPR2(r11) b fast_exception_return #endif -- cgit v1.2.3 From 58b278f568f0509497e2df7310bfd719156a60d1 Mon Sep 17 00:00:00 2001 From: Vaibhav Jain Date: Wed, 28 Aug 2019 13:57:29 +0530 Subject: powerpc: Provide initial documentation for PAPR hcalls This doc patch provides an initial description of the hcall op-codes that are used by Linux kernel running as a guest (LPAR) on top of PowerVM or any other sPAPR compliant hyper-visor (e.g qemu). Apart from documenting the hcalls the doc-patch also provides a rudimentary overview of how hcall ABI, how they are issued with the Linux kernel and how information/control flows between the guest and hypervisor. Signed-off-by: Vaibhav Jain Reviewed-by: Laurent Dufour Acked-by: Nicholas Piggin [mpe: Add SPDX tag, add it to index.rst] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190828082729.16695-1-vaibhav@linux.ibm.com --- arch/powerpc/kernel/exceptions-64s.S | 19 +++---------------- 1 file changed, 3 insertions(+), 16 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index b049c0bfa883..ffc15f4f079d 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1408,22 +1408,9 @@ EXC_VIRT_NONE(0x4b00, 0x100) * * Call convention: * - * syscall register convention is in Documentation/powerpc/syscall64-abi.rst - * - * For hypercalls, the register convention is as follows: - * r0 volatile - * r1-2 nonvolatile - * r3 volatile parameter and return value for status - * r4-r10 volatile input and output value - * r11 volatile hypercall number and output value - * r12 volatile input and output value - * r13-r31 nonvolatile - * LR nonvolatile - * CTR volatile - * XER volatile - * CR0-1 CR5-7 volatile - * CR2-4 nonvolatile - * Other registers nonvolatile + * syscall and hypercalls register conventions are documented in + * Documentation/powerpc/syscall64-abi.rst and + * Documentation/powerpc/papr_hcalls.rst respectively. * * The intersection of volatile registers that don't contain possible * inputs is: cr0, xer, ctr. We may use these as scratch regs upon entry -- cgit v1.2.3