From a13f18f59d2646754cda3662a9e215ff43e7a7d5 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Thu, 24 Sep 2015 15:53:56 +0100 Subject: Documentation: arm: Fix typo in the idle-states bindings examples The idle-states bindings mandate that the entry-method string in the idle-states node must be "psci" for ARM v8 64-bit systems, but the examples in the bindings report a wrong entry-method string. Owing to this typo, some dts in the kernel wrongly defined the entry-method property, since they likely cut and pasted the example definition without paying attention to the bindings definitions. This patch fixes the typo in the DT idle states bindings examples and respective dts in the kernel so that the bindings and related dts files are made compliant. Signed-off-by: Lorenzo Pieralisi Cc: Howard Chen Cc: Rob Herring Cc: Mark Rutland Cc: Heiko Stuebner Signed-off-by: Rob Herring --- arch/arm64/boot/dts/mediatek/mt8173.dtsi | 2 +- arch/arm64/boot/dts/rockchip/rk3368.dtsi | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi index d18ee4259ee5..06a15644be38 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi @@ -81,7 +81,7 @@ }; idle-states { - entry-method = "arm,psci"; + entry-method = "psci"; CPU_SLEEP_0: cpu-sleep-0 { compatible = "arm,idle-state"; diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi index a712bea3bf2c..cc093a482aa4 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -106,7 +106,7 @@ }; idle-states { - entry-method = "arm,psci"; + entry-method = "psci"; cpu_sleep: cpu-sleep-0 { compatible = "arm,idle-state"; -- cgit v1.2.3 From 920552b213e3dc832a874b4e7ba29ecddbab31bc Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 18 Sep 2015 12:34:53 +0200 Subject: KVM: disable halt_poll_ns as default for s390x We observed some performance degradation on s390x with dynamic halt polling. Until we can provide a proper fix, let's enable halt_poll_ns as default only for supported architectures. Architectures are now free to set their own halt_poll_ns default value. Signed-off-by: David Hildenbrand Signed-off-by: Paolo Bonzini --- arch/arm/include/asm/kvm_host.h | 1 + arch/arm64/include/asm/kvm_host.h | 1 + arch/mips/include/asm/kvm_host.h | 1 + arch/powerpc/include/asm/kvm_host.h | 1 + arch/s390/include/asm/kvm_host.h | 1 + arch/x86/include/asm/kvm_host.h | 1 + virt/kvm/kvm_main.c | 4 ++-- 7 files changed, 8 insertions(+), 2 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 3df1e975f72a..c4072d9f32c7 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -33,6 +33,7 @@ #define KVM_PRIVATE_MEM_SLOTS 4 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 #define KVM_HAVE_ONE_REG +#define KVM_HALT_POLL_NS_DEFAULT 500000 #define KVM_VCPU_MAX_FEATURES 2 diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 4562459456a6..ed039688c221 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -33,6 +33,7 @@ #define KVM_USER_MEM_SLOTS 32 #define KVM_PRIVATE_MEM_SLOTS 4 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 +#define KVM_HALT_POLL_NS_DEFAULT 500000 #include #include diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 3a54dbca9f7e..5a1a882e0a75 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -61,6 +61,7 @@ #define KVM_PRIVATE_MEM_SLOTS 0 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 +#define KVM_HALT_POLL_NS_DEFAULT 500000 diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 195886a583ba..827a38d7a9db 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -44,6 +44,7 @@ #ifdef CONFIG_KVM_MMIO #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 #endif +#define KVM_HALT_POLL_NS_DEFAULT 500000 /* These values are internal and can be increased later */ #define KVM_NR_IRQCHIPS 1 diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 6ce4a0b7e8da..8ced426091e1 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -35,6 +35,7 @@ */ #define KVM_NR_IRQCHIPS 1 #define KVM_IRQCHIP_NUM_PINS 4096 +#define KVM_HALT_POLL_NS_DEFAULT 0 #define SIGP_CTRL_C 0x80 #define SIGP_CTRL_SCN_MASK 0x3f diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 349f80a82b82..2beee0382088 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -40,6 +40,7 @@ #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 +#define KVM_HALT_POLL_NS_DEFAULT 500000 #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 04146a2e1d81..8db1d9361993 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -66,8 +66,8 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); -/* halt polling only reduces halt latency by 5-7 us, 500us is enough */ -static unsigned int halt_poll_ns = 500000; +/* Architectures should define their poll value according to the halt latency */ +static unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT; module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR); /* Default doubles per-vcpu halt_poll_ns. */ -- cgit v1.2.3 From 0ce3cc008ec04258b6a6314b09f1a6012810881a Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 25 Sep 2015 23:02:19 +0100 Subject: arm64/efi: Fix boot crash by not padding between EFI_MEMORY_RUNTIME regions The new Properties Table feature introduced in UEFIv2.5 may split memory regions that cover PE/COFF memory images into separate code and data regions. Since these regions only differ in the type (runtime code vs runtime data) and the permission bits, but not in the memory type attributes (UC/WC/WT/WB), the spec does not require them to be aligned to 64 KB. Since the relative offset of PE/COFF .text and .data segments cannot be changed on the fly, this means that we can no longer pad out those regions to be mappable using 64 KB pages. Unfortunately, there is no annotation in the UEFI memory map that identifies data regions that were split off from a code region, so we must apply this logic to all adjacent runtime regions whose attributes only differ in the permission bits. So instead of rounding each memory region to 64 KB alignment at both ends, only round down regions that are not directly preceded by another runtime region with the same type attributes. Since the UEFI spec does not mandate that the memory map be sorted, this means we also need to sort it first. Note that this change will result in all EFI_MEMORY_RUNTIME regions whose start addresses are not aligned to the OS page size to be mapped with executable permissions (i.e., on kernels compiled with 64 KB pages). However, since these mappings are only active during the time that UEFI Runtime Services are being invoked, the window for abuse is rather small. Tested-by: Mark Salter Tested-by: Mark Rutland [UEFI 2.4 only] Signed-off-by: Ard Biesheuvel Signed-off-by: Matt Fleming Reviewed-by: Mark Salter Reviewed-by: Mark Rutland Cc: # v4.0+ Cc: Catalin Marinas Cc: Leif Lindholm Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/1443218539-7610-3-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- arch/arm64/kernel/efi.c | 3 +- drivers/firmware/efi/libstub/arm-stub.c | 88 +++++++++++++++++++++++++++------ 2 files changed, 75 insertions(+), 16 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index e8ca6eaedd02..13671a9cf016 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -258,7 +258,8 @@ static bool __init efi_virtmap_init(void) */ if (!is_normal_ram(md)) prot = __pgprot(PROT_DEVICE_nGnRE); - else if (md->type == EFI_RUNTIME_SERVICES_CODE) + else if (md->type == EFI_RUNTIME_SERVICES_CODE || + !PAGE_ALIGNED(md->phys_addr)) prot = PAGE_KERNEL_EXEC; else prot = PAGE_KERNEL; diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index e29560e6b40b..950c87f5d279 100644 --- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -13,6 +13,7 @@ */ #include +#include #include #include "efistub.h" @@ -305,6 +306,44 @@ fail: */ #define EFI_RT_VIRTUAL_BASE 0x40000000 +static int cmp_mem_desc(const void *l, const void *r) +{ + const efi_memory_desc_t *left = l, *right = r; + + return (left->phys_addr > right->phys_addr) ? 1 : -1; +} + +/* + * Returns whether region @left ends exactly where region @right starts, + * or false if either argument is NULL. + */ +static bool regions_are_adjacent(efi_memory_desc_t *left, + efi_memory_desc_t *right) +{ + u64 left_end; + + if (left == NULL || right == NULL) + return false; + + left_end = left->phys_addr + left->num_pages * EFI_PAGE_SIZE; + + return left_end == right->phys_addr; +} + +/* + * Returns whether region @left and region @right have compatible memory type + * mapping attributes, and are both EFI_MEMORY_RUNTIME regions. + */ +static bool regions_have_compatible_memory_type_attrs(efi_memory_desc_t *left, + efi_memory_desc_t *right) +{ + static const u64 mem_type_mask = EFI_MEMORY_WB | EFI_MEMORY_WT | + EFI_MEMORY_WC | EFI_MEMORY_UC | + EFI_MEMORY_RUNTIME; + + return ((left->attribute ^ right->attribute) & mem_type_mask) == 0; +} + /* * efi_get_virtmap() - create a virtual mapping for the EFI memory map * @@ -317,33 +356,52 @@ void efi_get_virtmap(efi_memory_desc_t *memory_map, unsigned long map_size, int *count) { u64 efi_virt_base = EFI_RT_VIRTUAL_BASE; - efi_memory_desc_t *out = runtime_map; + efi_memory_desc_t *in, *prev = NULL, *out = runtime_map; int l; - for (l = 0; l < map_size; l += desc_size) { - efi_memory_desc_t *in = (void *)memory_map + l; + /* + * To work around potential issues with the Properties Table feature + * introduced in UEFI 2.5, which may split PE/COFF executable images + * in memory into several RuntimeServicesCode and RuntimeServicesData + * regions, we need to preserve the relative offsets between adjacent + * EFI_MEMORY_RUNTIME regions with the same memory type attributes. + * The easiest way to find adjacent regions is to sort the memory map + * before traversing it. + */ + sort(memory_map, map_size / desc_size, desc_size, cmp_mem_desc, NULL); + + for (l = 0; l < map_size; l += desc_size, prev = in) { u64 paddr, size; + in = (void *)memory_map + l; if (!(in->attribute & EFI_MEMORY_RUNTIME)) continue; + paddr = in->phys_addr; + size = in->num_pages * EFI_PAGE_SIZE; + /* * Make the mapping compatible with 64k pages: this allows * a 4k page size kernel to kexec a 64k page size kernel and * vice versa. */ - paddr = round_down(in->phys_addr, SZ_64K); - size = round_up(in->num_pages * EFI_PAGE_SIZE + - in->phys_addr - paddr, SZ_64K); - - /* - * Avoid wasting memory on PTEs by choosing a virtual base that - * is compatible with section mappings if this region has the - * appropriate size and physical alignment. (Sections are 2 MB - * on 4k granule kernels) - */ - if (IS_ALIGNED(in->phys_addr, SZ_2M) && size >= SZ_2M) - efi_virt_base = round_up(efi_virt_base, SZ_2M); + if (!regions_are_adjacent(prev, in) || + !regions_have_compatible_memory_type_attrs(prev, in)) { + + paddr = round_down(in->phys_addr, SZ_64K); + size += in->phys_addr - paddr; + + /* + * Avoid wasting memory on PTEs by choosing a virtual + * base that is compatible with section mappings if this + * region has the appropriate size and physical + * alignment. (Sections are 2 MB on 4k granule kernels) + */ + if (IS_ALIGNED(in->phys_addr, SZ_2M) && size >= SZ_2M) + efi_virt_base = round_up(efi_virt_base, SZ_2M); + else + efi_virt_base = round_up(efi_virt_base, SZ_64K); + } in->virt_addr = efi_virt_base + in->phys_addr - paddr; efi_virt_base += size; -- cgit v1.2.3 From 1a541b4e3cd6f5795022514114854b3e1345f24e Mon Sep 17 00:00:00 2001 From: Steve Capper Date: Thu, 1 Oct 2015 13:06:07 +0100 Subject: arm64: Fix THP protection change logic 6910fa1 ("arm64: enable PTE type bit in the mask for pte_modify") fixes a problem whereby a large block of PROT_NONE mapped memory is incorrectly mapped as block descriptors when mprotect is called. Unfortunately, a subtle bug was introduced by this fix to the THP logic. If one mmaps a large block of memory, then faults it such that it is collapsed into THPs; resulting calls to mprotect on this area of memory will lead to incorrect table descriptors being written instead of block descriptors. This is because pmd_modify calls pte_modify which is now allowed to modify the type of the page table entry. This patch reverts commit 6910fa16dbe142f6a0fd0fd7c249f9883ff7fc8a, and fixes the problem it was trying to address by adjusting PAGE_NONE to represent a table entry. Thus no change in pte type is required when moving from PROT_NONE to a different protection. Fixes: 6910fa16dbe1 ("arm64: enable PTE type bit in the mask for pte_modify") Cc: # 4.0+ Cc: Feng Kan Reported-by: Ganapatrao Kulkarni Tested-by: Ganapatrao Kulkarni Reviewed-by: Catalin Marinas Signed-off-by: Steve Capper Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/pgtable.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index b0329be95cb1..26b066690593 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -79,7 +79,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY) #define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN) -#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN) +#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_PXN | PTE_UXN) #define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) #define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE) #define PAGE_COPY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) @@ -496,7 +496,7 @@ static inline pud_t *pud_offset(pgd_t *pgd, unsigned long addr) static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | - PTE_PROT_NONE | PTE_WRITE | PTE_TYPE_MASK; + PTE_PROT_NONE | PTE_VALID | PTE_WRITE; /* preserve the hardware dirty information */ if (pte_hw_dirty(pte)) pte = pte_mkdirty(pte); -- cgit v1.2.3 From ee556d00cf20012e889344a0adbbf809ab5015a3 Mon Sep 17 00:00:00 2001 From: Li Bin Date: Wed, 30 Sep 2015 10:49:55 +0800 Subject: arm64: ftrace: fix function_graph tracer panic When function graph tracer is enabled, the following operation will trigger panic: mount -t debugfs nodev /sys/kernel echo next_tgid > /sys/kernel/tracing/set_ftrace_filter echo function_graph > /sys/kernel/tracing/current_tracer ls /proc/ ------------[ cut here ]------------ [ 198.501417] Unable to handle kernel paging request at virtual address cb88537fdc8ba316 [ 198.506126] pgd = ffffffc008f79000 [ 198.509363] [cb88537fdc8ba316] *pgd=00000000488c6003, *pud=00000000488c6003, *pmd=0000000000000000 [ 198.517726] Internal error: Oops: 94000005 [#1] SMP [ 198.518798] Modules linked in: [ 198.520582] CPU: 1 PID: 1388 Comm: ls Tainted: G [ 198.521800] Hardware name: linux,dummy-virt (DT) [ 198.522852] task: ffffffc0fa9e8000 ti: ffffffc0f9ab0000 task.ti: ffffffc0f9ab0000 [ 198.524306] PC is at next_tgid+0x30/0x100 [ 198.525205] LR is at return_to_handler+0x0/0x20 [ 198.526090] pc : [] lr : [] pstate: 60000145 [ 198.527392] sp : ffffffc0f9ab3d40 [ 198.528084] x29: ffffffc0f9ab3d40 x28: ffffffc0f9ab0000 [ 198.529406] x27: ffffffc000d6a000 x26: ffffffc000b786e8 [ 198.530659] x25: ffffffc0002a1900 x24: ffffffc0faf16c00 [ 198.531942] x23: ffffffc0f9ab3ea0 x22: 0000000000000002 [ 198.533202] x21: ffffffc000d85050 x20: 0000000000000002 [ 198.534446] x19: 0000000000000002 x18: 0000000000000000 [ 198.535719] x17: 000000000049fa08 x16: ffffffc000242efc [ 198.537030] x15: 0000007fa472b54c x14: ffffffffff000000 [ 198.538347] x13: ffffffc0fada84a0 x12: 0000000000000001 [ 198.539634] x11: ffffffc0f9ab3d70 x10: ffffffc0f9ab3d70 [ 198.540915] x9 : ffffffc0000907c0 x8 : ffffffc0f9ab3d40 [ 198.542215] x7 : 0000002e330f08f0 x6 : 0000000000000015 [ 198.543508] x5 : 0000000000000f08 x4 : ffffffc0f9835ec0 [ 198.544792] x3 : cb88537fdc8ba316 x2 : cb88537fdc8ba306 [ 198.546108] x1 : 0000000000000002 x0 : ffffffc000d85050 [ 198.547432] [ 198.547920] Process ls (pid: 1388, stack limit = 0xffffffc0f9ab0020) [ 198.549170] Stack: (0xffffffc0f9ab3d40 to 0xffffffc0f9ab4000) [ 198.582568] Call trace: [ 198.583313] [] next_tgid+0x30/0x100 [ 198.584359] [] ftrace_graph_caller+0x6c/0x70 [ 198.585503] [] ftrace_graph_caller+0x6c/0x70 [ 198.586574] [] ftrace_graph_caller+0x6c/0x70 [ 198.587660] [] ftrace_graph_caller+0x6c/0x70 [ 198.588896] Code: aa0003f5 2a0103f4 b4000102 91004043 (885f7c60) [ 198.591092] ---[ end trace 6a346f8f20949ac8 ]--- This is because when using function graph tracer, if the traced function return value is in multi regs ([x0-x7]), return_to_handler may corrupt them. So in return_to_handler, the parameter regs should be protected properly. Cc: # 3.18+ Signed-off-by: Li Bin Acked-by: AKASHI Takahiro Signed-off-by: Catalin Marinas --- arch/arm64/kernel/entry-ftrace.S | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 08cafc518b9a..0f03a8fe2314 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -178,6 +178,24 @@ ENTRY(ftrace_stub) ENDPROC(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER + /* save return value regs*/ + .macro save_return_regs + sub sp, sp, #64 + stp x0, x1, [sp] + stp x2, x3, [sp, #16] + stp x4, x5, [sp, #32] + stp x6, x7, [sp, #48] + .endm + + /* restore return value regs*/ + .macro restore_return_regs + ldp x0, x1, [sp] + ldp x2, x3, [sp, #16] + ldp x4, x5, [sp, #32] + ldp x6, x7, [sp, #48] + add sp, sp, #64 + .endm + /* * void ftrace_graph_caller(void) * @@ -204,11 +222,11 @@ ENDPROC(ftrace_graph_caller) * only when CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST is enabled. */ ENTRY(return_to_handler) - str x0, [sp, #-16]! + save_return_regs mov x0, x29 // parent's fp bl ftrace_return_to_handler// addr = ftrace_return_to_hander(fp); mov x30, x0 // restore the original return address - ldr x0, [sp], #16 + restore_return_regs ret END(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -- cgit v1.2.3