On Fri, 19 Nov 2021, Oleksandr wrote: > On 19.11.21 03:19, Stefano Stabellini wrote: > > On Wed, 10 Nov 2021, Oleksandr wrote: > > > On 28.10.21 04:40, Stefano Stabellini wrote: > > > > > > Hi Stefano > > > > > > I am sorry for the late response. > > > > > > > On Tue, 26 Oct 2021, Oleksandr Tyshchenko wrote: > > > > > From: Oleksandr Tyshchenko > > > > > > > > > > This patch implements arch_xen_unpopulated_init() on Arm where > > > > > the extended regions (if any) are gathered from DT and inserted > > > > > into passed Xen resource to be used as unused address space > > > > > for Xen scratch pages by unpopulated-alloc code. > > > > > > > > > > The extended region (safe range) is a region of guest physical > > > > > address space which is unused and could be safely used to create > > > > > grant/foreign mappings instead of wasting real RAM pages from > > > > > the domain memory for establishing these mappings. > > > > > > > > > > The extended regions are chosen by the hypervisor at the domain > > > > > creation time and advertised to it via "reg" property under > > > > > hypervisor node in the guest device-tree. As region 0 is reserved > > > > > for grant table space (always present), the indexes for extended > > > > > regions are 1...N. > > > > > > > > > > If arch_xen_unpopulated_init() fails for some reason the default > > > > > behaviour will be restored (allocate xenballooned pages). > > > > > > > > > > This patch also removes XEN_UNPOPULATED_ALLOC dependency on x86. > > > > > > > > > > Signed-off-by: Oleksandr Tyshchenko > > > > > --- > > > > > Changes RFC -> V2: > > > > > - new patch, instead of > > > > > "[RFC PATCH 2/2] xen/unpopulated-alloc: Query hypervisor to > > > > > provide > > > > > unallocated space" > > > > > --- > > > > > arch/arm/xen/enlighten.c | 112 > > > > > +++++++++++++++++++++++++++++++++++++++++++++++ > > > > > drivers/xen/Kconfig | 2 +- > > > > > 2 files changed, 113 insertions(+), 1 deletion(-) > > > > > > > > > > diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c > > > > > index dea46ec..1a1e0d3 100644 > > > > > --- a/arch/arm/xen/enlighten.c > > > > > +++ b/arch/arm/xen/enlighten.c > > > > > @@ -62,6 +62,7 @@ static __read_mostly unsigned int xen_events_irq; > > > > > static phys_addr_t xen_grant_frames; > > > > > #define GRANT_TABLE_INDEX 0 > > > > > +#define EXT_REGION_INDEX 1 > > > > > uint32_t xen_start_flags; > > > > > EXPORT_SYMBOL(xen_start_flags); > > > > > @@ -303,6 +304,117 @@ static void __init xen_acpi_guest_init(void) > > > > > #endif > > > > > } > > > > > +#ifdef CONFIG_XEN_UNPOPULATED_ALLOC > > > > > +int arch_xen_unpopulated_init(struct resource *res) > > > > > +{ > > > > > + struct device_node *np; > > > > > + struct resource *regs, *tmp_res; > > > > > + uint64_t min_gpaddr = -1, max_gpaddr = 0; > > > > > + unsigned int i, nr_reg = 0; > > > > > + struct range mhp_range; > > > > > + int rc; > > > > > + > > > > > + if (!xen_domain()) > > > > > + return -ENODEV; > > > > > + > > > > > + np = of_find_compatible_node(NULL, NULL, "xen,xen"); > > > > > + if (WARN_ON(!np)) > > > > > + return -ENODEV; > > > > > + > > > > > + /* Skip region 0 which is reserved for grant table space */ > > > > > + while (of_get_address(np, nr_reg + EXT_REGION_INDEX, NULL, > > > > > NULL)) > > > > > + nr_reg++; > > > > > + if (!nr_reg) { > > > > > + pr_err("No extended regions are found\n"); > > > > > + return -EINVAL; > > > > > + } > > > > > + > > > > > + regs = kcalloc(nr_reg, sizeof(*regs), GFP_KERNEL); > > > > > + if (!regs) > > > > > + return -ENOMEM; > > > > > + > > > > > + /* > > > > > + * Create resource from extended regions provided by the > > > > > hypervisor to > > > > > be > > > > > + * used as unused address space for Xen scratch pages. > > > > > + */ > > > > > + for (i = 0; i < nr_reg; i++) { > > > > > + rc = of_address_to_resource(np, i + EXT_REGION_INDEX, > > > > > ®s[i]); > > > > > + if (rc) > > > > > + goto err; > > > > > + > > > > > + if (max_gpaddr < regs[i].end) > > > > > + max_gpaddr = regs[i].end; > > > > > + if (min_gpaddr > regs[i].start) > > > > > + min_gpaddr = regs[i].start; > > > > > + } > > > > > + > > > > > + /* Check whether the resource range is within the hotpluggable > > > > > range > > > > > */ > > > > > + mhp_range = mhp_get_pluggable_range(true); > > > > > + if (min_gpaddr < mhp_range.start) > > > > > + min_gpaddr = mhp_range.start; > > > > > + if (max_gpaddr > mhp_range.end) > > > > > + max_gpaddr = mhp_range.end; > > > > > + > > > > > + res->start = min_gpaddr; > > > > > + res->end = max_gpaddr; > > > > > + > > > > > + /* > > > > > + * Mark holes between extended regions as unavailable. The > > > > > rest of > > > > > that > > > > > + * address space will be available for the allocation. > > > > > + */ > > > > > + for (i = 1; i < nr_reg; i++) { > > > > > + resource_size_t start, end; > > > > > + > > > > > + start = regs[i - 1].end + 1; > > > > > + end = regs[i].start - 1; > > > > > + > > > > > + if (start > (end + 1)) { > > > > Should this be: > > > > > > > > if (start >= end) > > > > > > > > ? > > > Yes, we can do this here (since the checks are equivalent) but ... > > > > > > > > + rc = -EINVAL; > > > > > + goto err; > > > > > + } > > > > > + > > > > > + /* There is no hole between regions */ > > > > > + if (start == (end + 1)) > > > > Also here, shouldn't it be: > > > > > > > > if (start == end) > > > > > > > > ? > > >    ... not here. > > > > > > As > > > > > > "(start == (end + 1))" is equal to "(regs[i - 1].end + 1 == > > > regs[i].start)" > > > > > > but > > > > > > "(start == end)" is equal to "(regs[i - 1].end + 1 == regs[i].start - 1)" > > OK. But the check: > > > > if (start >= end) > > > > Actually covers both cases so that's the only check we need? > > Sorry, I don't entirely understand the question. > Is the question to use only a single check in that loop? > > Paste the updated code which I have locally for the convenience. > >  [snip] > >     /* >      * Mark holes between extended regions as unavailable. The rest of that >      * address space will be available for the allocation. >      */ >     for (i = 1; i < nr_reg; i++) { >         resource_size_t start, end; > >         start = regs[i - 1].end + 1; >         end = regs[i].start - 1; > >         if (start > (end + 1)) { >             rc = -EINVAL; >             goto err; >         } > >         /* There is no hole between regions */ >         if (start == (end + 1)) >             continue; > >         tmp_res = kzalloc(sizeof(*tmp_res), GFP_KERNEL); >         if (!tmp_res) { >             rc = -ENOMEM; >             goto err; >         } > >         tmp_res->name = "Unavailable space"; >         tmp_res->start = start; >         tmp_res->end = end; > >         rc = insert_resource(&xen_resource, tmp_res); >         if (rc) { >             pr_err("Cannot insert resource %pR (%d)\n", tmp_res, rc); >             kfree(tmp_res); >             goto err; >         } >     } > > [snip] > > > 1. The first check is to detect an overlap (which is a wrong configuration, > correct?) and bail out if true (for example, regX: 0x81000000...0x82FFFFFF and > regY: 0x82000000...0x83FFFFFF). > 2. The second check is just to skip current iteration as there is no > space/hole between regions (for example, regX: 0x81000000...0x82FFFFFF and > regY: 0x83000000...0x83FFFFFF). > Therefore I think they should be distinguished. > > Yes, both check could be transformed to a single one, but this way the > overlaps will be ignored: > if (start >= (end + 1)) >     continue; > > Or I really missed something? You are right it is better to distinguish the two cases. I suggest the code below because I think it is a clearer, even if it might be slightly less efficient. I don't feel too strongly about it though. resource_size_t start, end; /* There is no hole between regions */ if ( regs[i - 1].end + 1 == regs[i].start ) continue; if ( regs[i - 1].end + 1 > regs[i].start) { rc = -EINVAL; goto err; } start = regs[i - 1].end + 1; end = regs[i].start - 1;