[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <c3b0424d-8f04-4d16-a56d-e22784d2ed4d@nvidia.com>
Date: Fri, 6 Sep 2024 13:58:31 -0500
From: Shanker Donthineni <sdonthineni@...dia.com>
To: Steven Price <steven.price@....com>, kvm@...r.kernel.org,
kvmarm@...ts.linux.dev
Cc: Catalin Marinas <catalin.marinas@....com>, Marc Zyngier <maz@...nel.org>,
Will Deacon <will@...nel.org>, James Morse <james.morse@....com>,
Oliver Upton <oliver.upton@...ux.dev>,
Suzuki K Poulose <suzuki.poulose@....com>, Zenghui Yu
<yuzenghui@...wei.com>, linux-arm-kernel@...ts.infradead.org,
linux-kernel@...r.kernel.org, Joey Gouly <joey.gouly@....com>,
Alexandru Elisei <alexandru.elisei@....com>,
Christoffer Dall <christoffer.dall@....com>, Fuad Tabba <tabba@...gle.com>,
linux-coco@...ts.linux.dev,
Ganapatrao Kulkarni <gankulkarni@...amperecomputing.com>,
Gavin Shan <gshan@...hat.com>, Alper Gun <alpergun@...gle.com>,
Vikram Sethi <vsethi@...dia.com>
Subject: Re: [PATCH v5 05/19] arm64: Detect if in a realm and set RIPAS RAM
Hi Steven,
On 8/19/24 08:19, Steven Price wrote:
> External email: Use caution opening links or attachments
>
>
> From: Suzuki K Poulose <suzuki.poulose@....com>
>
> Detect that the VM is a realm guest by the presence of the RSI
> interface.
>
> If in a realm then all memory needs to be marked as RIPAS RAM initially,
> the loader may or may not have done this for us. To be sure iterate over
> all RAM and mark it as such. Any failure is fatal as that implies the
> RAM regions passed to Linux are incorrect - which would mean failing
> later when attempting to access non-existent RAM.
>
> Signed-off-by: Suzuki K Poulose <suzuki.poulose@....com>
> Co-developed-by: Steven Price <steven.price@....com>
> Signed-off-by: Steven Price <steven.price@....com>
> ---
> Changes since v4:
> * Minor tidy ups.
> Changes since v3:
> * Provide safe/unsafe versions for converting memory to protected,
> using the safer version only for the early boot.
> * Use the new psci_early_test_conduit() function to avoid calling an
> SMC if EL3 is not present (or not configured to handle an SMC).
> Changes since v2:
> * Use DECLARE_STATIC_KEY_FALSE rather than "extern struct
> static_key_false".
> * Rename set_memory_range() to rsi_set_memory_range().
> * Downgrade some BUG()s to WARN()s and handle the condition by
> propagating up the stack. Comment the remaining case that ends in a
> BUG() to explain why.
> * Rely on the return from rsi_request_version() rather than checking
> the version the RMM claims to support.
> * Rename the generic sounding arm64_setup_memory() to
> arm64_rsi_setup_memory() and move the call site to setup_arch().
> ---
> arch/arm64/include/asm/rsi.h | 65 ++++++++++++++++++++++++++++++
> arch/arm64/kernel/Makefile | 3 +-
> arch/arm64/kernel/rsi.c | 78 ++++++++++++++++++++++++++++++++++++
> arch/arm64/kernel/setup.c | 8 ++++
> 4 files changed, 153 insertions(+), 1 deletion(-)
> create mode 100644 arch/arm64/include/asm/rsi.h
> create mode 100644 arch/arm64/kernel/rsi.c
>
> diff --git a/arch/arm64/include/asm/rsi.h b/arch/arm64/include/asm/rsi.h
> new file mode 100644
> index 000000000000..2bc013badbc3
> --- /dev/null
> +++ b/arch/arm64/include/asm/rsi.h
> @@ -0,0 +1,65 @@
> +/* SPDX-License-Identifier: GPL-2.0-only */
> +/*
> + * Copyright (C) 2024 ARM Ltd.
> + */
> +
> +#ifndef __ASM_RSI_H_
> +#define __ASM_RSI_H_
> +
> +#include <linux/jump_label.h>
> +#include <asm/rsi_cmds.h>
> +
> +DECLARE_STATIC_KEY_FALSE(rsi_present);
> +
> +void __init arm64_rsi_init(void);
> +void __init arm64_rsi_setup_memory(void);
> +static inline bool is_realm_world(void)
> +{
> + return static_branch_unlikely(&rsi_present);
> +}
> +
> +static inline int rsi_set_memory_range(phys_addr_t start, phys_addr_t end,
> + enum ripas state, unsigned long flags)
> +{
> + unsigned long ret;
> + phys_addr_t top;
> +
> + while (start != end) {
> + ret = rsi_set_addr_range_state(start, end, state, flags, &top);
> + if (WARN_ON(ret || top < start || top > end))
> + return -EINVAL;
> + start = top;
> + }
> +
> + return 0;
> +}
> +
> +/*
> + * Convert the specified range to RAM. Do not use this if you rely on the
> + * contents of a page that may already be in RAM state.
> + */
> +static inline int rsi_set_memory_range_protected(phys_addr_t start,
> + phys_addr_t end)
> +{
> + return rsi_set_memory_range(start, end, RSI_RIPAS_RAM,
> + RSI_CHANGE_DESTROYED);
> +}
> +
> +/*
> + * Convert the specified range to RAM. Do not convert any pages that may have
> + * been DESTROYED, without our permission.
> + */
> +static inline int rsi_set_memory_range_protected_safe(phys_addr_t start,
> + phys_addr_t end)
> +{
> + return rsi_set_memory_range(start, end, RSI_RIPAS_RAM,
> + RSI_NO_CHANGE_DESTROYED);
> +}
> +
> +static inline int rsi_set_memory_range_shared(phys_addr_t start,
> + phys_addr_t end)
> +{
> + return rsi_set_memory_range(start, end, RSI_RIPAS_EMPTY,
> + RSI_NO_CHANGE_DESTROYED);
> +}
> +#endif /* __ASM_RSI_H_ */
> diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
> index 2b112f3b7510..71c29a2a2f19 100644
> --- a/arch/arm64/kernel/Makefile
> +++ b/arch/arm64/kernel/Makefile
> @@ -33,7 +33,8 @@ obj-y := debug-monitors.o entry.o irq.o fpsimd.o \
> return_address.o cpuinfo.o cpu_errata.o \
> cpufeature.o alternative.o cacheinfo.o \
> smp.o smp_spin_table.o topology.o smccc-call.o \
> - syscall.o proton-pack.o idle.o patching.o pi/
> + syscall.o proton-pack.o idle.o patching.o pi/ \
> + rsi.o
>
> obj-$(CONFIG_COMPAT) += sys32.o signal32.o \
> sys_compat.o
> diff --git a/arch/arm64/kernel/rsi.c b/arch/arm64/kernel/rsi.c
> new file mode 100644
> index 000000000000..128a9a05a96b
> --- /dev/null
> +++ b/arch/arm64/kernel/rsi.c
> @@ -0,0 +1,78 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/*
> + * Copyright (C) 2023 ARM Ltd.
> + */
> +
> +#include <linux/jump_label.h>
> +#include <linux/memblock.h>
> +#include <linux/psci.h>
> +#include <asm/rsi.h>
> +
> +DEFINE_STATIC_KEY_FALSE_RO(rsi_present);
> +EXPORT_SYMBOL(rsi_present);
> +
> +static bool rsi_version_matches(void)
> +{
> + unsigned long ver_lower, ver_higher;
> + unsigned long ret = rsi_request_version(RSI_ABI_VERSION,
> + &ver_lower,
> + &ver_higher);
> +
> + if (ret == SMCCC_RET_NOT_SUPPORTED)
> + return false;
> +
> + if (ret != RSI_SUCCESS) {
> + pr_err("RME: RMM doesn't support RSI version %lu.%lu. Supported range: %lu.%lu-%lu.%lu\n",
> + RSI_ABI_VERSION_MAJOR, RSI_ABI_VERSION_MINOR,
> + RSI_ABI_VERSION_GET_MAJOR(ver_lower),
> + RSI_ABI_VERSION_GET_MINOR(ver_lower),
> + RSI_ABI_VERSION_GET_MAJOR(ver_higher),
> + RSI_ABI_VERSION_GET_MINOR(ver_higher));
> + return false;
> + }
> +
> + pr_info("RME: Using RSI version %lu.%lu\n",
> + RSI_ABI_VERSION_GET_MAJOR(ver_lower),
> + RSI_ABI_VERSION_GET_MINOR(ver_lower));
> +
> + return true;
> +}
> +
> +void __init arm64_rsi_setup_memory(void)
> +{
> + u64 i;
> + phys_addr_t start, end;
> +
> + if (!is_realm_world())
> + return;
> +
> + /*
> + * Iterate over the available memory ranges and convert the state to
> + * protected memory. We should take extra care to ensure that we DO NOT
> + * permit any "DESTROYED" pages to be converted to "RAM".
> + *
> + * BUG_ON is used because if the attempt to switch the memory to
> + * protected has failed here, then future accesses to the memory are
> + * simply going to be reflected as a SEA (Synchronous External Abort)
> + * which we can't handle. Bailing out early prevents the guest limping
> + * on and dying later.
> + */
> + for_each_mem_range(i, &start, &end) {
> + BUG_ON(rsi_set_memory_range_protected_safe(start, end));
> + }
> +}
> +
> +void __init arm64_rsi_init(void)
> +{
> + /*
> + * If PSCI isn't using SMC, RMM isn't present. Don't try to execute an
> + * SMC as it could be UNDEFINED.
> + */
> + if (!psci_early_test_conduit(SMCCC_CONDUIT_SMC))
> + return;
For ACPI-based kernel boot flow, control never reaches this point because the above
function does not check the PSCI conduit method when the kernel is booted via UEFI.
As a result, the boot process fails when using ACPI. It works fine with DTB based
boot.
> + if (!rsi_version_matches())
> + return;
> +
> + static_branch_enable(&rsi_present);
> +}
> +
> diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
> index a096e2451044..143f87615af0 100644
> --- a/arch/arm64/kernel/setup.c
> +++ b/arch/arm64/kernel/setup.c
> @@ -43,6 +43,7 @@
> #include <asm/cpu_ops.h>
> #include <asm/kasan.h>
> #include <asm/numa.h>
> +#include <asm/rsi.h>
> #include <asm/scs.h>
> #include <asm/sections.h>
> #include <asm/setup.h>
> @@ -293,6 +294,11 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
> * cpufeature code and early parameters.
> */
> jump_label_init();
> + /*
> + * Init RSI before early param so that "earlycon" console uses the
> + * shared alias when in a realm
> + */
> + arm64_rsi_init();
> parse_early_param();
>
> dynamic_scs_init();
> @@ -328,6 +334,8 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
>
> arm64_memblock_init();
>
> + arm64_rsi_setup_memory();
> +
> paging_init();
>
> acpi_table_upgrade();
> --
> 2.34.1
>
Powered by blists - more mailing lists