From 8d48bf8206f77aa8687f0e241e901e5197e52423 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 5 Nov 2021 10:41:51 +0100 Subject: x86/boot: Pull up cmdline preparation and early param parsing Dan reports that Anjaneya Chagam can no longer use the efi=nosoftreserve kernel command line parameter to suppress "soft reservation" behavior. This is due to the fact that the following call-chain happens at boot: early_reserve_memory |-> efi_memblock_x86_reserve_range |-> efi_fake_memmap_early which does if (!efi_soft_reserve_enabled()) return; and that would have set EFI_MEM_NO_SOFT_RESERVE after having parsed "nosoftreserve". However, parse_early_param() gets called *after* it, leading to the boot cmdline not being taken into account. Therefore, carve out the command line preparation into a separate function which does the early param parsing too. So that it all goes together. And then call that function before early_reserve_memory() so that the params would have been parsed by then. Fixes: 8aa83e6395ce ("x86/setup: Call early_reserve_memory() earlier") Reported-by: Dan Williams Reviewed-by: Dan Williams Signed-off-by: Borislav Petkov Tested-by: Anjaneya Chagam Cc: Link: https://lore.kernel.org/r/e8dd8993c38702ee6dd73b3c11f158617e665607.camel@intel.com --- arch/x86/kernel/setup.c | 66 +++++++++++++++++++++++++++++-------------------- 1 file changed, 39 insertions(+), 27 deletions(-) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 49b596db5631..c410be738ae7 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -742,6 +742,28 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) return 0; } +static char *prepare_command_line(void) +{ +#ifdef CONFIG_CMDLINE_BOOL +#ifdef CONFIG_CMDLINE_OVERRIDE + strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); +#else + if (builtin_cmdline[0]) { + /* append boot loader cmdline to builtin */ + strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE); + strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE); + strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); + } +#endif +#endif + + strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); + + parse_early_param(); + + return command_line; +} + /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -830,6 +852,23 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); + /* + * x86_configure_nx() is called before parse_early_param() (called by + * prepare_command_line()) to detect whether hardware doesn't support + * NX (so that the early EHCI debug console setup can safely call + * set_fixmap()). It may then be called again from within noexec_setup() + * during parsing early parameters to honor the respective command line + * option. + */ + x86_configure_nx(); + + /* + * This parses early params and it needs to run before + * early_reserve_memory() because latter relies on such settings + * supplied as early params. + */ + *cmdline_p = prepare_command_line(); + /* * Do some memory reservations *before* memory is added to memblock, so * memblock allocations won't overwrite it. @@ -863,33 +902,6 @@ void __init setup_arch(char **cmdline_p) bss_resource.start = __pa_symbol(__bss_start); bss_resource.end = __pa_symbol(__bss_stop)-1; -#ifdef CONFIG_CMDLINE_BOOL -#ifdef CONFIG_CMDLINE_OVERRIDE - strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); -#else - if (builtin_cmdline[0]) { - /* append boot loader cmdline to builtin */ - strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE); - strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE); - strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); - } -#endif -#endif - - strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); - *cmdline_p = command_line; - - /* - * x86_configure_nx() is called before parse_early_param() to detect - * whether hardware doesn't support NX (so that the early EHCI debug - * console setup can safely call set_fixmap()). It may then be called - * again from within noexec_setup() during parsing early parameters - * to honor the respective command line option. - */ - x86_configure_nx(); - - parse_early_param(); - #ifdef CONFIG_MEMORY_HOTPLUG /* * Memory used by the kernel cannot be hot-removed because Linux -- cgit v1.2.3 From ac5d272a0ad0419f52e08c91953356e32b075af7 Mon Sep 17 00:00:00 2001 From: Reinette Chatre Date: Mon, 15 Nov 2021 11:29:04 -0800 Subject: x86/sgx: Fix free page accounting The SGX driver maintains a single global free page counter, sgx_nr_free_pages, that reflects the number of free pages available across all NUMA nodes. Correspondingly, a list of free pages is associated with each NUMA node and sgx_nr_free_pages is updated every time a page is added or removed from any of the free page lists. The main usage of sgx_nr_free_pages is by the reclaimer that runs when it (sgx_nr_free_pages) goes below a watermark to ensure that there are always some free pages available to, for example, support efficient page faults. With sgx_nr_free_pages accessed and modified from a few places it is essential to ensure that these accesses are done safely but this is not the case. sgx_nr_free_pages is read without any protection and updated with inconsistent protection by any one of the spin locks associated with the individual NUMA nodes. For example: CPU_A CPU_B ----- ----- spin_lock(&nodeA->lock); spin_lock(&nodeB->lock); ... ... sgx_nr_free_pages--; /* NOT SAFE */ sgx_nr_free_pages--; spin_unlock(&nodeA->lock); spin_unlock(&nodeB->lock); Since sgx_nr_free_pages may be protected by different spin locks while being modified from different CPUs, the following scenario is possible: CPU_A CPU_B ----- ----- {sgx_nr_free_pages = 100} spin_lock(&nodeA->lock); spin_lock(&nodeB->lock); sgx_nr_free_pages--; sgx_nr_free_pages--; /* LOAD sgx_nr_free_pages = 100 */ /* LOAD sgx_nr_free_pages = 100 */ /* sgx_nr_free_pages-- */ /* sgx_nr_free_pages-- */ /* STORE sgx_nr_free_pages = 99 */ /* STORE sgx_nr_free_pages = 99 */ spin_unlock(&nodeA->lock); spin_unlock(&nodeB->lock); In the above scenario, sgx_nr_free_pages is decremented from two CPUs but instead of sgx_nr_free_pages ending with a value that is two less than it started with, it was only decremented by one while the number of free pages were actually reduced by two. The consequence of sgx_nr_free_pages not being protected is that its value may not accurately reflect the actual number of free pages on the system, impacting the availability of free pages in support of many flows. The problematic scenario is when the reclaimer does not run because it believes there to be sufficient free pages while any attempt to allocate a page fails because there are no free pages available. In the SGX driver the reclaimer's watermark is only 32 pages so after encountering the above example scenario 32 times a user space hang is possible when there are no more free pages because of repeated page faults caused by no free pages made available. The following flow was encountered: asm_exc_page_fault ... sgx_vma_fault() sgx_encl_load_page() sgx_encl_eldu() // Encrypted page needs to be loaded from backing // storage into newly allocated SGX memory page sgx_alloc_epc_page() // Allocate a page of SGX memory __sgx_alloc_epc_page() // Fails, no free SGX memory ... if (sgx_should_reclaim(SGX_NR_LOW_PAGES)) // Wake reclaimer wake_up(&ksgxd_waitq); return -EBUSY; // Return -EBUSY giving reclaimer time to run return -EBUSY; return -EBUSY; return VM_FAULT_NOPAGE; The reclaimer is triggered in above flow with the following code: static bool sgx_should_reclaim(unsigned long watermark) { return sgx_nr_free_pages < watermark && !list_empty(&sgx_active_page_list); } In the problematic scenario there were no free pages available yet the value of sgx_nr_free_pages was above the watermark. The allocation of SGX memory thus always failed because of a lack of free pages while no free pages were made available because the reclaimer is never started because of sgx_nr_free_pages' incorrect value. The consequence was that user space kept encountering VM_FAULT_NOPAGE that caused the same address to be accessed repeatedly with the same result. Change the global free page counter to an atomic type that ensures simultaneous updates are done safely. While doing so, move the updating of the variable outside of the spin lock critical section to which it does not belong. Cc: stable@vger.kernel.org Fixes: 901ddbb9ecf5 ("x86/sgx: Add a basic NUMA allocation scheme to sgx_alloc_epc_page()") Suggested-by: Dave Hansen Signed-off-by: Reinette Chatre Signed-off-by: Dave Hansen Reviewed-by: Tony Luck Acked-by: Jarkko Sakkinen Link: https://lkml.kernel.org/r/a95a40743bbd3f795b465f30922dde7f1ea9e0eb.1637004094.git.reinette.chatre@intel.com --- arch/x86/kernel/cpu/sgx/main.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 63d3de02bbcc..8471a8b9b48e 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -28,8 +28,7 @@ static DECLARE_WAIT_QUEUE_HEAD(ksgxd_waitq); static LIST_HEAD(sgx_active_page_list); static DEFINE_SPINLOCK(sgx_reclaimer_lock); -/* The free page list lock protected variables prepend the lock. */ -static unsigned long sgx_nr_free_pages; +static atomic_long_t sgx_nr_free_pages = ATOMIC_LONG_INIT(0); /* Nodes with one or more EPC sections. */ static nodemask_t sgx_numa_mask; @@ -403,14 +402,15 @@ skip: spin_lock(&node->lock); list_add_tail(&epc_page->list, &node->free_page_list); - sgx_nr_free_pages++; spin_unlock(&node->lock); + atomic_long_inc(&sgx_nr_free_pages); } } static bool sgx_should_reclaim(unsigned long watermark) { - return sgx_nr_free_pages < watermark && !list_empty(&sgx_active_page_list); + return atomic_long_read(&sgx_nr_free_pages) < watermark && + !list_empty(&sgx_active_page_list); } static int ksgxd(void *p) @@ -471,9 +471,9 @@ static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid) page = list_first_entry(&node->free_page_list, struct sgx_epc_page, list); list_del_init(&page->list); - sgx_nr_free_pages--; spin_unlock(&node->lock); + atomic_long_dec(&sgx_nr_free_pages); return page; } @@ -625,9 +625,9 @@ void sgx_free_epc_page(struct sgx_epc_page *page) spin_lock(&node->lock); list_add_tail(&page->list, &node->free_page_list); - sgx_nr_free_pages++; spin_unlock(&node->lock); + atomic_long_inc(&sgx_nr_free_pages); } static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size, -- cgit v1.2.3