From 5b7a08e0ea5bb51f886f2f5e2373de2bf5981dd2 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 28 Nov 2019 20:58:05 +0100 Subject: [PATCH 1/2] arm64: KVM: Invoke compute_layout() before alternatives are applied compute_layout() is invoked as part of an alternative fixup under stop_machine(). This function invokes get_random_long() which acquires a sleeping lock on -RT which can not be acquired in this context. Rename compute_layout() to kvm_compute_layout() and invoke it before stop_machine() applies the alternatives. Add a __init prefix to kvm_compute_layout() because the caller has it, too (and so the code can be discarded after boot). Reviewed-by: James Morse Acked-by: Marc Zyngier Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/kvm_mmu.h | 1 + arch/arm64/kernel/smp.c | 4 ++++ arch/arm64/kvm/va_layout.c | 8 +------- 3 files changed, 6 insertions(+), 7 deletions(-) diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index befe37d..53d846f 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -91,6 +91,7 @@ void kvm_update_va_mask(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst); +void kvm_compute_layout(void); static inline unsigned long __kern_hyp_va(unsigned long v) { diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index dc9fe87..02d41ea 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -39,6 +40,7 @@ #include #include #include +#include #include #include #include @@ -408,6 +410,8 @@ static void __init hyp_mode_check(void) "CPU: CPUs started in inconsistent modes"); else pr_info("CPU: All CPU(s) started at EL1\n"); + if (IS_ENABLED(CONFIG_KVM_ARM_HOST)) + kvm_compute_layout(); } void __init smp_cpus_done(unsigned int max_cpus) diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c index 2cf7d4b..dab1fea 100644 --- a/arch/arm64/kvm/va_layout.c +++ b/arch/arm64/kvm/va_layout.c @@ -22,7 +22,7 @@ static u64 tag_val; static u64 va_mask; -static void compute_layout(void) +__init void kvm_compute_layout(void) { phys_addr_t idmap_addr = __pa_symbol(__hyp_idmap_text_start); u64 hyp_va_msb; @@ -110,9 +110,6 @@ void __init kvm_update_va_mask(struct alt_instr *alt, BUG_ON(nr_inst != 5); - if (!has_vhe() && !va_mask) - compute_layout(); - for (i = 0; i < nr_inst; i++) { u32 rd, rn, insn, oinsn; @@ -156,9 +153,6 @@ void kvm_patch_vector_branch(struct alt_instr *alt, return; } - if (!va_mask) - compute_layout(); - /* * Compute HYP VA by using the same computation as kern_hyp_va() */ -- 1.8.3.1 From d2d093ca412b7fd66acd745d00e3ebd4764fe127 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 28 Dec 2019 11:57:14 +0000 Subject: [PATCH 2/2] arm64: kvm: Fix IDMAP overlap with HYP VA Booting 5.4 on LX2160A reveals that KVM is non-functional: kvm: Limiting the IPA size due to kernel Virtual Address limit kvm [1]: IPA Size Limit: 43bits kvm [1]: IDMAP intersecting with HYP VA, unable to continue kvm [1]: error initializing Hyp mode: -22 Debugging shows: kvm [1]: IDMAP page: 81a26000 kvm [1]: HYP VA range: 0:22ffffffff as RAM is located at: 80000000-fbdfffff : System RAM 2080000000-237fffffff : System RAM Comparing this with the same kernel on Armada 8040 shows: kvm: Limiting the IPA size due to kernel Virtual Address limit kvm [1]: IPA Size Limit: 43bits kvm [1]: IDMAP page: 2a26000 kvm [1]: HYP VA range: 4800000000:493fffffff ... kvm [1]: Hyp mode initialized successfully which indicates that hyp_va_msb is set, and is always set to the opposite value of the idmap page to avoid the overlap. This does not happen with the LX2160A. Further debugging shows vabits_actual = 39, kva_msb = 38 on LX2160A and kva_msb = 33 on Armada 8040. Looking at the bit layout of the HYP VA, there is still one bit available for hyp_va_msb. Set this bit appropriately. This allows KVM to be functional on the LX2160A, but without any HYP VA randomisation: kvm: Limiting the IPA size due to kernel Virtual Address limit kvm [1]: IPA Size Limit: 43bits kvm [1]: IDMAP page: 81a24000 kvm [1]: HYP VA range: 4000000000:62ffffffff ... kvm [1]: Hyp mode initialized successfully Fixes: ed57cac83e05 ("arm64: KVM: Introduce EL2 VA randomisation") Signed-off-by: Russell King [maz: small additional cleanups, preserved case where the tag is legitimately 0 and we can just use the mask, Fixes tag] Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/E1ilAiY-0000MA-RG@rmk-PC.armlinux.org.uk --- arch/arm64/kvm/va_layout.c | 56 +++++++++++++++++++++------------------------- 1 file changed, 25 insertions(+), 31 deletions(-) diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c index dab1fea..a4f48c1 100644 --- a/arch/arm64/kvm/va_layout.c +++ b/arch/arm64/kvm/va_layout.c @@ -13,52 +13,46 @@ #include /* - * The LSB of the random hyp VA tag or 0 if no randomization is used. + * The LSB of the HYP VA tag */ static u8 tag_lsb; /* - * The random hyp VA tag value with the region bit if hyp randomization is used + * The HYP VA tag value with the region bit */ static u64 tag_val; static u64 va_mask; +/* + * We want to generate a hyp VA with the following format (with V == + * vabits_actual): + * + * 63 ... V | V-1 | V-2 .. tag_lsb | tag_lsb - 1 .. 0 + * --------------------------------------------------------- + * | 0000000 | hyp_va_msb | random tag | kern linear VA | + * |--------- tag_val -----------|----- va_mask ---| + * + * which does not conflict with the idmap regions. + */ __init void kvm_compute_layout(void) { phys_addr_t idmap_addr = __pa_symbol(__hyp_idmap_text_start); u64 hyp_va_msb; - int kva_msb; /* Where is my RAM region? */ hyp_va_msb = idmap_addr & BIT(vabits_actual - 1); hyp_va_msb ^= BIT(vabits_actual - 1); - kva_msb = fls64((u64)phys_to_virt(memblock_start_of_DRAM()) ^ + tag_lsb = fls64((u64)phys_to_virt(memblock_start_of_DRAM()) ^ (u64)(high_memory - 1)); - if (kva_msb == (vabits_actual - 1)) { - /* - * No space in the address, let's compute the mask so - * that it covers (vabits_actual - 1) bits, and the region - * bit. The tag stays set to zero. - */ - va_mask = BIT(vabits_actual - 1) - 1; - va_mask |= hyp_va_msb; - } else { - /* - * We do have some free bits to insert a random tag. - * Hyp VAs are now created from kernel linear map VAs - * using the following formula (with V == vabits_actual): - * - * 63 ... V | V-1 | V-2 .. tag_lsb | tag_lsb - 1 .. 0 - * --------------------------------------------------------- - * | 0000000 | hyp_va_msb | random tag | kern linear VA | - */ - tag_lsb = kva_msb; - va_mask = GENMASK_ULL(tag_lsb - 1, 0); - tag_val = get_random_long() & GENMASK_ULL(vabits_actual - 2, tag_lsb); - tag_val |= hyp_va_msb; - tag_val >>= tag_lsb; + va_mask = GENMASK_ULL(tag_lsb - 1, 0); + tag_val = hyp_va_msb; + + if (tag_lsb != (vabits_actual - 1)) { + /* We have some free bits to insert a random tag. */ + tag_val |= get_random_long() & GENMASK_ULL(vabits_actual - 2, tag_lsb); } + tag_val >>= tag_lsb; } static u32 compute_instruction(int n, u32 rd, u32 rn) @@ -117,11 +111,11 @@ void __init kvm_update_va_mask(struct alt_instr *alt, * VHE doesn't need any address translation, let's NOP * everything. * - * Alternatively, if we don't have any spare bits in - * the address, NOP everything after masking that - * kernel VA. + * Alternatively, if the tag is zero (because the layout + * dictates it and we don't have any spare bits in the + * address), NOP everything after masking the kernel VA. */ - if (has_vhe() || (!tag_lsb && i > 0)) { + if (has_vhe() || (!tag_val && i > 0)) { updptr[i] = cpu_to_le32(aarch64_insn_gen_nop()); continue; } -- 1.8.3.1